def main(sDir, url_list, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = uu.split(rd + '-')[1].split('/')[0] if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) if preferred_only == 'yes': ps_df, n_streams = cf.get_preferred_stream_info(r) fdatasets = [] for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets = cf.filter_collocated_instruments(main_sensor, fdatasets) num_data = len(fdatasets) save_dir = os.path.join(sDir, array, subsite, r, 'preferred_method_plots') cf.create_dir(save_dir) print(len(fdatasets)) if len(fdatasets) > 3: steps = list(range(3, len(fdatasets) + 3, 3)) for ii in steps: plot_velocity_variables(r, fdatasets[ii - 3:ii], 3, save_dir) else: plot_velocity_variables(r, fdatasets, 3, save_dir)
def main(sDir, f): ff = pd.read_csv(os.path.join(sDir, f)) datasets = cf.get_nc_urls(ff['outputUrl'].tolist()) for d in datasets: print(d) fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( d) save_dir = os.path.join(sDir, subsite, refdes, deployment) cf.create_dir(save_dir) sci_vars = cf.return_science_vars(stream) colors = cm.jet(np.linspace(0, 1, len(sci_vars))) with xr.open_dataset(d, mask_and_scale=False) as ds: ds = ds.swap_dims({'obs': 'time'}) t = ds['time'].data t0 = pd.to_datetime(t.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(t.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) fig, ax = plt.subplots() axes = [ax] for i in range(len(sci_vars)): if i > 0: axes.append(ax.twinx() ) # twin the x-axis to make independent y-axes fig.subplots_adjust(right=0.6) right_additive = (0.98 - 0.6) / float(5) for i in range(len(sci_vars)): if i > 0: axes[i].spines['right'].set_position( ('axes', 1. + right_additive * i)) y = ds[sci_vars[i]] ind = cf.reject_outliers(y, 5) yD = y.data[ind] x = t[ind] #yD = y.data c = colors[i] axes[i].plot(x, yD, '.', markersize=2, color=c) axes[i].set_ylabel((y.name + " (" + y.units + ")"), color=c, fontsize=9) axes[i].tick_params(axis='y', colors=c) if i == len( sci_vars) - 1: # if the last variable has been plotted pf.format_date_axis(axes[i], fig) axes[0].set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '_'.join((fname, 'timeseries')) pf.save_fig(save_dir, sfile)
def main(sDir, f): ff = pd.read_csv(os.path.join(sDir, f)) datasets = cf.get_nc_urls(ff['outputUrl'].tolist()) plt_vars = [ 'ctdmo_seawater_pressure', 'ctdmo_seawater_temperature', 'ctdmo_seawater_conductivity', 'practical_salinity', 'density' ] dms_list = [] for ds in datasets: dms = deploy_method_stream(ds) if dms not in dms_list: dms_list.append(dms) for dd in dms_list: for v in plt_vars: print(v) data = OrderedDict() for ds in datasets: dms = deploy_method_stream(ds) if dms == dd: f = xr.open_dataset(ds) f = f.swap_dims({'obs': 'time'}) refdes = '-'.join((f.subsite, f.node, f.sensor)) yD = f[v].values data[refdes] = {} data[refdes]['time'] = f['time'].values data[refdes]['yD'] = yD data[refdes]['yunits'] = f[v].units data[refdes]['median'] = np.median(yD) data[refdes]['dms'] = dms plot_ctdmo(data, v) plot_ctdmo(data, v, 5) # reject outliers beyond 5 standard deviations
def main(sDir, url_list, start_time, end_time, deployment_num, interval): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] deployments = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) for ud in udatasets: if ud.split('/')[-1].split('_')[0] not in deployments: deployments.append(ud.split('/')[-1].split('_')[0]) datasets = list(itertools.chain(*datasets)) datasets = cf.filter_collocated_instruments(r, datasets) deployments.sort() fdatasets = np.unique(datasets).tolist() for deploy in deployments: if deployment_num is not None: if int(deploy[-4:]) is not deployment_num: print('\nskipping {}'.format(deploy)) continue rdatasets = [s for s in fdatasets if deploy in s] # break deployment into 4 segments or make a list of the time range specified if start_time is not None and end_time is not None: dt_range = [dt.datetime.strftime(start_time, '%Y-%m-%d'), dt.datetime.strftime(end_time, '%Y-%m-%d')] else: # Get deployment info from the data review database dr_data = cf.refdes_datareview_json(r) d_info = [x for x in dr_data['instrument']['deployments'] if x['deployment_number'] == int(deploy[-4:])] d_info = d_info[0] deploy_start = dt.datetime.strptime(str(d_info['start_date']).split('T')[0], '%Y-%m-%d') deploy_stop = dt.datetime.strptime(str(d_info['stop_date']).split('T')[0], '%Y-%m-%d') + dt.timedelta( days=1) dt_range = list(date_range(deploy_start, deploy_stop, 4)) sci_vars_dict = {'time': dict(values=np.array([], dtype=np.datetime64), fv=[], ln=[]), 'bin_depths': dict(values=np.array([]), units=[], fv=[], ln=[])} percentgood = {'percent_good_beam1': dict(values=np.array([])), 'percent_good_beam2': dict(values=np.array([])), 'percent_good_beam3': dict(values=np.array([])), 'percent_good_beam4': dict(values=np.array([]))} if interval is None: toplot = range(len(dt_range) - 1) else: toplot = [interval - 1] for dtri in toplot: stime = dt.datetime.strptime(dt_range[dtri], '%Y-%m-%d') etime = dt.datetime.strptime(dt_range[dtri + 1], '%Y-%m-%d') if len(rdatasets) > 0: for i in range(len(rdatasets)): #for i in range(0, 2): ##### for testing ds = xr.open_dataset(rdatasets[i], mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) print('\nAppending data from {}: file {} of {}'.format(deploy, i + 1, len(rdatasets))) ds = ds.sel(time=slice(stime, etime)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue try: print(fname) except NameError: fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(rdatasets[0]) array = subsite[0:2] sci_vars = cf.return_science_vars(stream) # drop the following list of key words from science variables list sci_vars = notin_list(sci_vars, ['salinity', 'temperature', 'bin_depths', 'beam']) sci_vars = [name for name in sci_vars if ds[name].units != 'mm s-1'] for sci_var in sci_vars: sci_vars_dict.update({sci_var: dict(values=np.array([]), units=[], fv=[], ln=[])}) # append data for the deployment into a dictionary for s_v, info in sci_vars_dict.items(): print(s_v) vv = ds[s_v] try: if vv.units not in info['units']: info['units'].append(vv.units) except AttributeError: print('no units') try: if vv._FillValue not in info['fv']: info['fv'].append(vv._FillValue) except AttributeError: print('no fill value') try: if vv.long_name not in info['ln']: info['ln'].append(vv.long_name) except AttributeError: print('no long name') if len(vv.dims) == 1: info['values'] = np.append(info['values'], vv.values) else: if len(info['values']) == 0: info['values'] = vv.values.T else: info['values'] = np.concatenate((info['values'], vv.values.T), axis=1) # append percent good beams for j, k in percentgood.items(): pgvv = ds[j] fv_pgvv = pgvv._FillValue pgvv = pgvv.values.T.astype(float) pgvv[pgvv == fv_pgvv] = np.nan if len(k['values']) == 0: k['values'] = pgvv else: k['values'] = np.concatenate((k['values'], pgvv), axis=1) if len(sci_vars_dict['time']['values']) > 0: filename = '_'.join(fname.split('_')[:-1]) save_dir = os.path.join(sDir, array, subsite, refdes, 'plots', deployment) cf.create_dir(save_dir) tm = sci_vars_dict['time']['values'] t0 = pd.to_datetime(tm.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tm.max()).strftime('%Y-%m-%dT%H:%M:%S') title_text = ' '.join((deployment, refdes, method)) bd = sci_vars_dict['bin_depths'] ylabel = 'bin_depths ({})'.format(bd['units'][0]) print('\nPlotting interval {}'.format(int(dtri) + 1)) for var in sci_vars: print('----{}'.format(var)) v = sci_vars_dict[var] fv = v['fv'][0] v_name = v['ln'][0] units = v['units'][0] if len(np.shape(v['values'])) == 1: v, n_nan, n_fv, n_ev, n_grange, g_min, g_max, n_std = reject_err_data_1_dims(v['values'], fv, r, var, n=5) if len(tm) > np.sum(np.isnan(v)): # only plot if the array contains values # Plot all data fig, ax = pf.plot_timeseries(tm, v, v_name, stdev=None) ax.set_title((title_text + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, v_name, t0[:10])) pf.save_fig(save_dir, sfile) # Plot data with outliers removed fig, ax = pf.plot_timeseries(tm, v, v_name, stdev=5) title_i = 'removed: {} nans, {} fill values, {} extreme values, {} GR [{}, {}],' \ ' {} outliers +/- 5 SD'.format(n_nan, n_fv , n_ev, n_grange, g_min, g_max, n_std) ax.set_title((title_text + '\n' + t0 + ' - ' + t1 + '\n' + title_i), fontsize=8) sfile = '-'.join((filename, v_name, t0[:10])) + '_rmoutliers' pf.save_fig(save_dir, sfile) else: print('Array of all nans - skipping plot') else: v, n_nan, n_fv, n_ev, n_bb, n_grange, g_min, g_max = reject_err_data_2_dims(v['values'], percentgood, fv, r, var) clabel = '{} ({})'.format(var, units) # check bin depths for extreme values y = bd['values'] # if all the values are negative, take the absolute value (cabled data bin depths are negative) if int(np.nanmin(y)) < 0 and int(np.nanmax(y)) < 0: y = abs(y) y_nan = np.sum(np.isnan(y)) y = np.where(y < 6000, y, np.nan) # replace extreme bin_depths by nans bin_nan = np.sum(np.isnan(y)) - y_nan bin_title = 'removed: {} bin depths > 6000'.format(bin_nan) if 'echo' in var: color = 'BuGn' else: color = 'RdBu' new_y = dropna(y, axis=1) # convert to DataFrame to drop nan y_mask = new_y.loc[list(new_y.index), list(new_y.columns)] v_new = pd.DataFrame(v) v_mask = v_new.loc[list(new_y.index), list(new_y.columns)] tm_mask = tm[new_y.columns] fig, ax, __ = pf.plot_adcp(tm_mask, np.array(y_mask), np.array(v_mask), ylabel, clabel, color, n_stdev=None) if bin_nan > 0: ax.set_title((title_text + '\n' + t0 + ' - ' + t1 + '\n' + bin_title), fontsize=8) else: ax.set_title((title_text + '\n' + t0 + ' - ' + t1), fontsize=8) sfile = '-'.join((filename, var, t0[:10])) pf.save_fig(save_dir, sfile) fig, ax, n_nans_all = pf.plot_adcp(tm_mask, np.array(y_mask), np.array(v_mask), ylabel, clabel, color, n_stdev=5) title_i = 'removed: {} nans, {} fill values, {} extreme values, {} bad beams, {} GR [{}, {}]'.format( n_nan, n_fv, n_ev, n_bb, n_grange, g_min, g_max) if bin_nan > 0: ax.set_title((title_text + '\n' + t0 + ' - ' + t1 + '\n' + title_i + '\n' + bin_title), fontsize=8) else: ax.set_title((title_text + '\n' + t0 + ' - ' + t1 + '\n' + title_i), fontsize=8) sfile = '-'.join((filename, var, t0[:10])) + '_rmoutliers' pf.save_fig(save_dir, sfile)
def main(url_list, sDir, deployment_num, start_time, end_time, preferred_only, n_std, inpercentile, zcell_size, zdbar): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'ENG' not in rd and 'ADCP' not in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments(main_sensor, fdatasets) for fd in fdatasets_sel: part_d = fd.split('/')[-1] print('\n{}'.format(part_d)) ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(fd) array = subsite[0:2] sci_vars = cf.return_science_vars(stream) # if 'CE05MOAS' in r or 'CP05MOAS' in r: # for coastal gliders, get m_water_depth for bathymetry # eng = '-'.join((r.split('-')[0], r.split('-')[1], '00-ENG000000', method, 'glider_eng')) # eng_url = [s for s in url_list if eng in s] # if len(eng_url) == 1: # eng_datasets = cf.get_nc_urls(eng_url) # # filter out collocated datasets # eng_dataset = [j for j in eng_datasets if (eng in j.split('/')[-1] and deployment in j.split('/')[-1])] # if len(eng_dataset) > 0: # ds_eng = xr.open_dataset(eng_dataset[0], mask_and_scale=False) # t_eng = ds_eng['time'].values # m_water_depth = ds_eng['m_water_depth'].values # # # m_altitude = glider height above seafloor # # m_depth = glider depth in the water column # # m_altitude = ds_eng['m_altitude'].values # # m_depth = ds_eng['m_depth'].values # # calc_water_depth = m_altitude + m_depth # # # m_altimeter_status = 0 means a good reading (not nan or -1) # try: # eng_ind = ds_eng['m_altimeter_status'].values == 0 # except KeyError: # eng_ind = (~np.isnan(m_water_depth)) & (m_water_depth >= 0) # # m_water_depth = m_water_depth[eng_ind] # t_eng = t_eng[eng_ind] # # # get rid of any remaining nans or fill values # eng_ind2 = (~np.isnan(m_water_depth)) & (m_water_depth >= 0) # m_water_depth = m_water_depth[eng_ind2] # t_eng = t_eng[eng_ind2] # else: # print('No engineering file for deployment {}'.format(deployment)) # m_water_depth = None # t_eng = None # else: # m_water_depth = None # t_eng = None # else: # m_water_depth = None # t_eng = None if deployment_num is not None: if int(int(deployment[-4:])) is not deployment_num: print(type(int(deployment[-4:])), type(deployment_num)) continue if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue stime = start_time.strftime('%Y-%m-%d') etime = end_time.strftime('%Y-%m-%d') ext = stime + 'to' + etime # .join((ds0_method, ds1_method save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment, ext) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment, ext) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment, ext) else: save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment) time1 = ds['time'].values try: ds_lat1 = ds['lat'].values except KeyError: ds_lat1 = None print('No latitude variable in file') try: ds_lon1 = ds['lon'].values except KeyError: ds_lon1 = None print('No longitude variable in file') # get pressure variable pvarname, y1, y_units, press, y_fillvalue = cf.add_pressure_to_dictionary_of_sci_vars(ds) for sv in sci_vars: print('') print(sv) if 'pressure' not in sv: if sv == 'spkir_abj_cspp_downwelling_vector': pxso.pf_xs_spkir(ds, sv, time1, y1, ds_lat1, ds_lon1, zcell_size, inpercentile, save_dir_profile, save_dir_xsection, deployment, press, y_units, n_std, zdbar) elif 'OPTAA' in r: if sv not in ['wavelength_a', 'wavelength_c']: pxso.pf_xs_optaa(ds, sv, time1, y1, ds_lat1, ds_lon1, zcell_size, inpercentile, save_dir_profile, save_dir_xsection, deployment, press, y_units, n_std, zdbar) else: z1 = ds[sv].values fv = ds[sv]._FillValue sv_units = ds[sv].units # Check if the array is all NaNs if sum(np.isnan(z1)) == len(z1): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z1[z1 != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: # remove unreasonable pressure data (e.g. for surface piercing profilers) if zdbar: po_ind = (0 < y1) & (y1 < zdbar) tm = time1[po_ind] y = y1[po_ind] z = z1[po_ind] ds_lat = ds_lat1[po_ind] ds_lon = ds_lon1[po_ind] else: tm = time1 y = y1 z = z1 ds_lat = ds_lat1 ds_lon = ds_lon1 # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max, lat, lon = \ cf.reject_erroneous_data(r, sv, tm, y, z, fv, ds_lat, ds_lon) # get rid of 0.0 data if sv == 'salinity': ind = ndata > 30 elif sv == 'density': ind = ndata > 1022.5 elif sv == 'conductivity': ind = ndata > 3.45 else: ind = ndata > 0 # if sv == 'sci_flbbcd_chlor_units': # ind = ndata < 7.5 # elif sv == 'sci_flbbcd_cdom_units': # ind = ndata < 25 # else: # ind = ndata > 0.0 # if 'CTD' in r: # ind = zpressure > 0.0 # else: # ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = dtime[ind] zpressure = zpressure[ind] ndata = ndata[ind] if ds_lat is not None and ds_lon is not None: lat = lat[ind] lon = lon[ind] else: lat = None lon = None if len(dtime) > 0: # reject time range from data portal file export t_portal, z_portal, y_portal, lat_portal, lon_portal = \ cf.reject_timestamps_dataportal(subsite, r, dtime, zpressure, ndata, lat, lon) print('removed {} data points using visual inspection of data'.format( len(ndata) - len(z_portal))) # create data groups if len(y_portal) > 0: columns = ['tsec', 'dbar', str(sv)] min_r = int(round(np.nanmin(y_portal) - zcell_size)) max_r = int(round(np.nanmax(y_portal) + zcell_size)) ranges = list(range(min_r, max_r, zcell_size)) groups, d_groups = gt.group_by_depth_range(t_portal, y_portal, z_portal, columns, ranges) if 'scatter' in sv: n_std = None # to use percentile else: n_std = n_std # get percentile analysis for printing on the profile plot y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr, time_ex = cf.reject_timestamps_in_groups( groups, d_groups, n_std, inpercentile) """ Plot all data """ if len(time1) > 0: cf.create_dir(save_dir_profile) cf.create_dir(save_dir_xsection) sname = '-'.join((r, method, sv)) sfileall = '_'.join(('all_data', sname, pd.to_datetime(time1.min()).strftime('%Y%m%d'))) tm0 = pd.to_datetime(time1.min()).strftime('%Y-%m-%dT%H:%M:%S') tm1 = pd.to_datetime(time1.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) + '\n' + tm0 + ' to ' + tm1 if 'SPKIR' in r: title = title + '\nWavelength = 510 nm' ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" clabel = 'Time' fig, ax = pf.plot_profiles(z1, y1, time1, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_profile, sfileall) ''' xsection plot ''' clabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" fig, ax, bar = pf.plot_xsection(subsite, time1, y1, z1, clabel, ylabel, t_eng=None, m_water_depth=None, inpercentile=None, stdev=None) if fig: ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_xsection, sfileall) """ Plot cleaned-up data """ if len(dtime) > 0: if len(y_portal) > 0: sfile = '_'.join(('rm_erroneous_data', sname, pd.to_datetime(t_portal.min()).strftime('%Y%m%d'))) t0 = pd.to_datetime(t_portal.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(t_portal.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) + '\n' + t0 + ' to ' + t1 if 'SPKIR' in r: title = title + '\nWavelength = 510 nm' ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" clabel = 'Time' fig, ax = pf.plot_profiles(z_portal, y_portal, t_portal, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) ax.plot(n_avg, y_avg, '-k') ax.fill_betweenx(y_avg, n0_std, n1_std, color='m', alpha=0.2) if inpercentile: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} unreasonable values'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nexcluded {} suspect data points when inspected visually'.format( len(ndata) - len(z_portal)) + '\n(black) data average in {} dbar segments'.format(zcell_size) + '\n(magenta) {} percentile envelope in {} dbar segments'.format( int(100 - inpercentile * 2), zcell_size),) elif n_std: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} unreasonable values'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nexcluded {} suspect data points when inspected visually'.format( len(ndata) - len(z_portal)) + '\n(black) data average in {} dbar segments'.format(zcell_size) + '\n(magenta) +/- {} SD envelope in {} dbar segments'.format( int(n_std), zcell_size),) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_profile, sfile) ''' xsection plot ''' clabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" # plot non-erroneous data fig, ax, bar = pf.plot_xsection(subsite, t_portal, y_portal, z_portal, clabel, ylabel, t_eng=None, m_water_depth=None, inpercentile=None, stdev=None) ax.set_title(title, fontsize=9) leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} unreasonable values'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nexcluded {} suspect data points when inspected visually'.format( len(ndata) - len(z_portal)), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_xsection, sfile) ''' 4D plot for gliders only ''' if 'MOAS' in r: if ds_lat is not None and ds_lon is not None: cf.create_dir(save_dir_4d) clabel = sv + " (" + sv_units + ")" zlabel = press[0] + " (" + y_units[0] + ")" fig = plt.figure() ax = fig.add_subplot(111, projection='3d') sct = ax.scatter(lon_portal, lat_portal, y_portal, c=z_portal, s=2) cbar = plt.colorbar(sct, label=clabel, extend='both') cbar.ax.tick_params(labelsize=8) ax.invert_zaxis() ax.view_init(25, 32) ax.invert_xaxis() ax.invert_yaxis() ax.set_zlabel(zlabel, fontsize=9) ax.set_ylabel('Latitude', fontsize=9) ax.set_xlabel('Longitude', fontsize=9) ax.set_title(title, fontsize=9) pf.save_fig(save_dir_4d, sfile)
def main(sDir, url_list, start_time, end_time, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): rms = '-'.join((r, row[ii])) for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments( main_sensor, fdatasets) for fd in fdatasets_sel: with xr.open_dataset(fd, mask_and_scale=False) as ds: ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})' .format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd) print('\nPlotting {} {}'.format(r, deployment)) array = subsite[0:2] save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_panel_plots') filename = '_'.join(fname.split('_')[:-1]) sci_vars = cf.return_science_vars(stream) if len(sci_vars) > 1: cf.create_dir(save_dir) colors = cm.jet(np.linspace(0, 1, len(sci_vars))) t = ds['time'].values t0 = pd.to_datetime(t.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(t.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) # Plot data with outliers removed fig, ax = pf.plot_timeseries_panel(ds, t, sci_vars, colors, 5) plt.xticks(fontsize=7) ax[0].set_title((title + '\n' + t0 + ' - ' + t1), fontsize=7) sfile = '-'.join((filename, 'timeseries_panel', t0[:10])) pf.save_fig(save_dir, sfile) else: print( 'Only one science variable in file, no panel plots necessary' )
def main(sDir, plotting_sDir, url_list, sd_calc): dr = pd.read_csv('https://datareview.marine.rutgers.edu/notes/export') drn = dr.loc[dr.type == 'exclusion'] rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) pms = [] for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) pms.append(row[ii]) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments( main_sensor, fdatasets) # find time ranges to exclude from analysis for data review database subsite = r.split('-')[0] subsite_node = '-'.join((subsite, r.split('-')[1])) drne = drn.loc[drn.reference_designator.isin( [subsite, subsite_node, r])] et = [] for i, row in drne.iterrows(): sdate = cf.format_dates(row.start_date) edate = cf.format_dates(row.end_date) et.append([sdate, edate]) # get science variable long names from the Data Review Database stream_sci_vars = cd.sci_var_long_names(r) # check if the science variable long names are the same for each stream sci_vars_dict = cd.sci_var_long_names_check(stream_sci_vars) # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) # build dictionary of science data from the preferred dataset for each deployment print('\nAppending data from files') sci_vars_dict, pressure_unit, pressure_name = cd.append_science_data( ps_df, n_streams, r, fdatasets_sel, sci_vars_dict, et) # analyze combined dataset print('\nAnalyzing combined dataset and writing summary file') array = subsite[0:2] save_dir = os.path.join(sDir, array, subsite) cf.create_dir(save_dir) rows = [] if ('FLM' in r) and ( 'CTDMO' in r ): # calculate Flanking Mooring CTDMO stats based on pressure headers = [ 'common_stream_name', 'preferred_methods_streams', 'deployments', 'long_name', 'units', 't0', 't1', 'fill_value', 'global_ranges', 'n_all', 'press_min_max', 'n_excluded_forpress', 'n_nans', 'n_fillvalues', 'n_grange', 'define_stdev', 'n_outliers', 'n_stats', 'mean', 'min', 'max', 'stdev', 'note' ] else: headers = [ 'common_stream_name', 'preferred_methods_streams', 'deployments', 'long_name', 'units', 't0', 't1', 'fill_value', 'global_ranges', 'n_all', 'n_nans', 'n_fillvalues', 'n_grange', 'define_stdev', 'n_outliers', 'n_stats', 'mean', 'min', 'max', 'stdev' ] for m, n in sci_vars_dict.items(): print('\nSTREAM: ', m) if m == 'common_stream_placeholder': m = 'science_data_stream' if m == 'metbk_hourly': # don't calculate ranges for metbk_hourly continue if ('FLM' in r) and ( 'CTDMO' in r ): # calculate Flanking Mooring CTDMO stats based on pressure # index the pressure variable to filter and calculate stats on the rest of the variables sv_press = 'Seawater Pressure' vinfo_press = n['vars'][sv_press] # first, index where data are nans, fill values, and outside of global ranges fv_press = list(np.unique(vinfo_press['fv']))[0] pdata = vinfo_press['values'] [pind, __, __, __, __, __] = index_dataset(r, vinfo_press['var_name'], pdata, fv_press) pdata_filtered = pdata[pind] [__, pmean, __, __, psd, __] = cf.variable_statistics(pdata_filtered, None) # index of pressure = average of all 'valid' pressure data +/- 1 SD ipress_min = pmean - psd ipress_max = pmean + psd ind_press = (pdata >= ipress_min) & (pdata <= ipress_max) # calculate stats for all variables print('\nPARAMETERS:') for sv, vinfo in n['vars'].items(): print(sv) fv_lst = np.unique(vinfo['fv']).tolist() if len(fv_lst) == 1: fill_value = fv_lst[0] else: print('No unique fill value for {}'.format(sv)) lunits = np.unique(vinfo['units']).tolist() n_all = len(vinfo['t']) # filter data based on pressure index t_filtered = vinfo['t'][ind_press] data_filtered = vinfo['values'][ind_press] deploy_filtered = vinfo['deployments'][ind_press] n_excluded = n_all - len(t_filtered) [dataind, g_min, g_max, n_nan, n_fv, n_grange] = index_dataset(r, vinfo['var_name'], data_filtered, fill_value) t_final = t_filtered[dataind] data_final = data_filtered[dataind] deploy_final = deploy_filtered[dataind] t0 = pd.to_datetime( min(t_final)).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime( max(t_final)).strftime('%Y-%m-%dT%H:%M:%S') deploy = list(np.unique(deploy_final)) deployments = [int(dd) for dd in deploy] if len(data_final) > 1: [num_outliers, mean, vmin, vmax, sd, n_stats ] = cf.variable_statistics(data_final, sd_calc) else: mean = None vmin = None vmax = None sd = None n_stats = None note = 'restricted stats calculation to data points where pressure is within defined ranges' \ ' (average of all pressure data +/- 1 SD)' rows.append([ m, list(np.unique(pms)), deployments, sv, lunits, t0, t1, fv_lst, [g_min, g_max], n_all, [round(ipress_min, 2), round(ipress_max, 2)], n_excluded, n_nan, n_fv, n_grange, sd_calc, num_outliers, n_stats, mean, vmin, vmax, sd, note ]) # plot CTDMO data used for stats psave_dir = os.path.join(plotting_sDir, array, subsite, r, 'timeseries_plots_stats') cf.create_dir(psave_dir) dr_data = cf.refdes_datareview_json(r) deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = cf.get_deployment_information( dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append( pd.to_datetime(deploy_info['stop_date'])) sname = '-'.join((r, sv)) fig, ax = pf.plot_timeseries_all(t_final, data_final, sv, lunits[0], stdev=None) ax.set_title( (r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) if sd_calc: sname = '-'.join((r, sv, 'rmoutliers')) fig, ax = pf.plot_timeseries_all(t_final, data_final, sv, lunits[0], stdev=sd_calc) ax.set_title( (r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) else: if not sd_calc: sdcalc = None print('\nPARAMETERS: ') for sv, vinfo in n['vars'].items(): print(sv) fv_lst = np.unique(vinfo['fv']).tolist() if len(fv_lst) == 1: fill_value = fv_lst[0] else: print(fv_lst) print('No unique fill value for {}'.format(sv)) lunits = np.unique(vinfo['units']).tolist() t = vinfo['t'] if len(t) > 1: data = vinfo['values'] n_all = len(t) if 'SPKIR' in r or 'presf_abc_wave_burst' in m: if 'SPKIR' in r: [dd_data, g_min, g_max, n_nan, n_fv, n_grange] = index_dataset_2d( r, 'spkir_abj_cspp_downwelling_vector', data, fill_value) else: [dd_data, g_min, g_max, n_nan, n_fv, n_grange] = index_dataset_2d( r, 'presf_wave_burst_pressure', data, fill_value) t_final = t t0 = pd.to_datetime( min(t_final)).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime( max(t_final)).strftime('%Y-%m-%dT%H:%M:%S') deploy_final = vinfo['deployments'] deploy = list(np.unique(deploy_final)) deployments = [int(dd) for dd in deploy] num_outliers = [] mean = [] vmin = [] vmax = [] sd = [] n_stats = [] for i in range(len(dd_data)): dd = data[i] # drop nans before calculating stats dd = dd[~np.isnan(dd)] [ num_outliersi, meani, vmini, vmaxi, sdi, n_statsi ] = cf.variable_statistics(dd, sd_calc) num_outliers.append(num_outliersi) mean.append(meani) vmin.append(vmini) vmax.append(vmaxi) sd.append(sdi) n_stats.append(n_statsi) else: [dataind, g_min, g_max, n_nan, n_fv, n_grange] = index_dataset(r, vinfo['var_name'], data, fill_value) t_final = t[dataind] if len(t_final) > 0: t0 = pd.to_datetime( min(t_final)).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime( max(t_final)).strftime('%Y-%m-%dT%H:%M:%S') data_final = data[dataind] # if sv == 'Dissolved Oxygen Concentration': # xx = (data_final > 0) & (data_final < 400) # data_final = data_final[xx] # t_final = t_final[xx] # if sv == 'Seawater Conductivity': # xx = (data_final > 1) & (data_final < 400) # data_final = data_final[xx] # t_final = t_final[xx] deploy_final = vinfo['deployments'][dataind] deploy = list(np.unique(deploy_final)) deployments = [int(dd) for dd in deploy] if len(data_final) > 1: [ num_outliers, mean, vmin, vmax, sd, n_stats ] = cf.variable_statistics( data_final, sd_calc) else: sdcalc = None num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = None else: sdcalc = None num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = None deployments = None t0 = None t1 = None else: sdcalc = None num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = None deployments = None t0 = None t1 = None t_final = [] if sd_calc: print_sd = sd_calc else: print_sd = sdcalc rows.append([ m, list(np.unique(pms)), deployments, sv, lunits, t0, t1, fv_lst, [g_min, g_max], n_all, n_nan, n_fv, n_grange, print_sd, num_outliers, n_stats, mean, vmin, vmax, sd ]) if len(t_final) > 0: # plot data used for stats psave_dir = os.path.join( plotting_sDir, array, subsite, r, 'timeseries_reviewed_datarange') cf.create_dir(psave_dir) dr_data = cf.refdes_datareview_json(r) deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = cf.get_deployment_information( dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append( pd.to_datetime(deploy_info['stop_date'])) sname = '-'.join((r, sv)) # plot hourly averages for streaming data if 'streamed' in sci_vars_dict[list( sci_vars_dict.keys())[0]]['ms'][0]: sname = '-'.join((sname, 'hourlyavg')) df = pd.DataFrame({ 'dfx': t_final, 'dfy': data_final }) dfr = df.resample('H', on='dfx').mean() # Plot all data fig, ax = pf.plot_timeseries_all(dfr.index, dfr['dfy'], sv, lunits[0], stdev=None) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) if sd_calc: sname = '-'.join( (sname, 'hourlyavg_rmoutliers')) fig, ax = pf.plot_timeseries_all(dfr.index, dfr['dfy'], sv, lunits[0], stdev=sd_calc) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) elif 'SPKIR' in r: fig, ax = pf.plot_spkir(t_final, dd_data, sv, lunits[0]) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) # plot each wavelength wavelengths = [ '412nm', '443nm', '490nm', '510nm', '555nm', '620nm', '683nm' ] for wvi in range(len(dd_data)): fig, ax = pf.plot_spkir_wv( t_final, dd_data[wvi], sv, lunits[0], wvi) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) snamewvi = '-'.join((sname, wavelengths[wvi])) pf.save_fig(psave_dir, snamewvi) elif 'presf_abc_wave_burst' in m: fig, ax = pf.plot_presf_2d(t_final, dd_data, sv, lunits[0]) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) snamewave = '-'.join((sname, m)) pf.save_fig(psave_dir, snamewave) else: # plot all data if not streamed fig, ax = pf.plot_timeseries_all(t_final, data_final, sv, lunits[0], stdev=None) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) if sd_calc: sname = '-'.join((r, sv, 'rmoutliers')) fig, ax = pf.plot_timeseries_all(t_final, data_final, sv, lunits[0], stdev=sd_calc) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(psave_dir, sname) fsum = pd.DataFrame(rows, columns=headers) fsum.to_csv('{}/{}_data_ranges.csv'.format(save_dir, r), index=False)
def main(url_list, sDir, deployment_num, start_time, end_time, preferred_only, n_std, inpercentile, zcell_size, zdbar): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'ENG' not in rd and 'ADCP' not in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] deployments = [] for url in url_list: splitter = url.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) catalog_rms = '-'.join((r, splitter[-2], splitter[-1])) if rd_check == r: udatasets = cf.get_nc_urls([url]) for u in udatasets: # filter out collocated data files if catalog_rms == u.split('/')[-1].split('_20')[0][15:]: datasets.append(u) deployments.append( int(u.split('/')[-1].split('_')[0][-4:])) deployments = np.unique(deployments).tolist() fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments( main_sensor, fdatasets) for dep in deployments: if deployment_num is not None: if dep is not deployment_num: print('\nskipping deployment {}'.format(dep)) continue rdatasets = [ s for s in fdatasets_sel if 'deployment%04d' % dep in s ] rdatasets.sort() if len(rdatasets) > 0: sci_vars_dict = {} # rdatasets = rdatasets[0:2] #### for testing for i in range(len(rdatasets)): ds = xr.open_dataset(rdatasets[i], mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) print('\nAppending data from {}: file {} of {}'.format( 'deployment%04d' % dep, i + 1, len(rdatasets))) array = r[0:2] subsite = r.split('-')[0] if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})' .format(start_time, end_time)) continue stime = start_time.strftime('%Y-%m-%d') etime = end_time.strftime('%Y-%m-%d') ext = stime + 'to' + etime # .join((ds0_method, ds1_method save_dir_profile = os.path.join( sDir, array, subsite, r, 'profile_plots', 'deployment%04d' % dep, ext) save_dir_xsection = os.path.join( sDir, array, subsite, r, 'xsection_plots', 'deployment%04d' % dep, ext) else: save_dir_profile = os.path.join( sDir, array, subsite, r, 'profile_plots', 'deployment%04d' % dep) save_dir_xsection = os.path.join( sDir, array, subsite, r, 'xsection_plots', 'deployment%04d' % dep) if len(sci_vars_dict) == 0: fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( rdatasets[0]) sci_vars = cf.return_science_vars(stream) if 'CTDPF' not in r: sci_vars.append('int_ctd_pressure') sci_vars.append('time') sci_vars = list(np.unique(sci_vars)) # initialize the dictionary for sci_var in sci_vars: if sci_var == 'time': sci_vars_dict.update({ sci_var: dict(values=np.array([], dtype=np.datetime64), units=[], fv=[]) }) else: sci_vars_dict.update({ sci_var: dict(values=np.array([]), units=[], fv=[]) }) # append data for the deployment into the dictionary for s_v in sci_vars_dict.keys(): vv = ds[s_v] try: if vv.units not in sci_vars_dict[s_v]['units']: sci_vars_dict[s_v]['units'].append(vv.units) except AttributeError: print('') try: if vv._FillValue not in sci_vars_dict[s_v]['fv']: sci_vars_dict[s_v]['fv'].append(vv._FillValue) vv_data = vv.values try: vv_data[ vv_data == vv. _FillValue] = np.nan # turn fill values to nans except ValueError: print('') except AttributeError: print('') if len(vv.dims) > 1: print('Skipping plot: variable has >1 dimension') else: sci_vars_dict[s_v]['values'] = np.append( sci_vars_dict[s_v]['values'], vv.values) # plot after appending all data into one file data_start = pd.to_datetime( min(sci_vars_dict['time']['values'])).strftime( '%Y-%m-%dT%H:%M:%S') data_stop = pd.to_datetime(max( sci_vars_dict['time']['values'])).strftime( '%Y-%m-%dT%H:%M:%S') time1 = sci_vars_dict['time']['values'] ds_lat1 = np.empty(np.shape(time1)) ds_lon1 = np.empty(np.shape(time1)) # define pressure variable try: pname = 'seawater_pressure' press = sci_vars_dict[pname] except KeyError: pname = 'int_ctd_pressure' press = sci_vars_dict[pname] y1 = press['values'] try: y_units = press['units'][0] except IndexError: y_units = '' for sv in sci_vars_dict.keys(): print('') print(sv) if sv not in [ 'seawater_pressure', 'int_ctd_pressure', 'time' ]: z1 = sci_vars_dict[sv]['values'] fv = sci_vars_dict[sv]['fv'][0] sv_units = sci_vars_dict[sv]['units'][0] # Check if the array is all NaNs if sum(np.isnan(z1)) == len(z1): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z1[z1 != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: # remove unreasonable pressure data (e.g. for surface piercing profilers) if zdbar: po_ind = (0 < y1) & (y1 < zdbar) tm = time1[po_ind] y = y1[po_ind] z = z1[po_ind] ds_lat = ds_lat1[po_ind] ds_lon = ds_lon1[po_ind] else: tm = time1 y = y1 z = z1 ds_lat = ds_lat1 ds_lon = ds_lon1 # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max, lat, lon = \ cf.reject_erroneous_data(r, sv, tm, y, z, fv, ds_lat, ds_lon) # get rid of 0.0 data # if sv == 'salinity': # ind = ndata > 20 # elif sv == 'density': # ind = ndata > 1010 # elif sv == 'conductivity': # ind = ndata > 2 # else: # ind = ndata > 0 # if sv == 'sci_flbbcd_chlor_units': # ind = ndata < 7.5 # elif sv == 'sci_flbbcd_cdom_units': # ind = ndata < 25 # else: # ind = ndata > 0.0 if 'CTD' in r: ind = zpressure > 0.0 else: ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = dtime[ind] zpressure = zpressure[ind] ndata = ndata[ind] if ds_lat is not None and ds_lon is not None: lat = lat[ind] lon = lon[ind] else: lat = None lon = None if len(dtime) > 0: # reject time range from data portal file export t_portal, z_portal, y_portal, lat_portal, lon_portal = \ cf.reject_timestamps_dataportal(subsite, r, dtime, zpressure, ndata, lat, lon) print( 'removed {} data points using visual inspection of data' .format(len(ndata) - len(z_portal))) # create data groups # if len(y_portal) > 0: # columns = ['tsec', 'dbar', str(sv)] # min_r = int(round(np.nanmin(y_portal) - zcell_size)) # max_r = int(round(np.nanmax(y_portal) + zcell_size)) # ranges = list(range(min_r, max_r, zcell_size)) # # groups, d_groups = gt.group_by_depth_range(t_portal, y_portal, z_portal, columns, ranges) # # if 'scatter' in sv: # n_std = None # to use percentile # else: # n_std = n_std # # # get percentile analysis for printing on the profile plot # y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr, time_ex = cf.reject_timestamps_in_groups( # groups, d_groups, n_std, inpercentile) """ Plot all data """ if len(time1) > 0: cf.create_dir(save_dir_profile) cf.create_dir(save_dir_xsection) sname = '-'.join((r, method, sv)) # sfileall = '_'.join(('all_data', sname, pd.to_datetime(time1.min()).strftime('%Y%m%d'))) # tm0 = pd.to_datetime(time1.min()).strftime('%Y-%m-%dT%H:%M:%S') # tm1 = pd.to_datetime(time1.max()).strftime('%Y-%m-%dT%H:%M:%S') sfileall = '_'.join( (sname, pd.to_datetime( t_portal.min()).strftime('%Y%m%d'))) tm0 = pd.to_datetime(t_portal.min()).strftime( '%Y-%m-%dT%H:%M:%S') tm1 = pd.to_datetime(t_portal.max()).strftime( '%Y-%m-%dT%H:%M:%S') title = ' '.join( (deployment, refdes, method)) + '\n' + tm0 + ' to ' + tm1 if 'SPKIR' in r: title = title + '\nWavelength = 510 nm' ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = pname + " (" + y_units + ")" clabel = 'Time' # fig, ax = pf.plot_profiles(z1, y1, time1, ylabel, xlabel, clabel, stdev=None) fig, ax = pf.plot_profiles(z_portal, y_portal, t_portal, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_profile, sfileall) ''' xsection plot ''' clabel = sv + " (" + sv_units + ")" ylabel = pname + " (" + y_units + ")" # fig, ax, bar = pf.plot_xsection(subsite, time1, y1, z1, clabel, ylabel, t_eng=None, # m_water_depth=None, inpercentile=None, stdev=None) fig, ax, bar = pf.plot_xsection( subsite, t_portal, y_portal, z_portal, clabel, ylabel, t_eng=None, m_water_depth=None, inpercentile=None, stdev=None) if fig: ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_xsection, sfileall) """
def main(url_list, sDir, plot_type, start_time, end_time, deployment_num): for i, u in enumerate(url_list): elements = u.split('/')[-2].split('-') r = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = u.split(r + '-')[1].split('/')[0] subsite = r.split('-')[0] array = subsite[0:2] main_sensor = r.split('-')[-1] datasets = cf.get_nc_urls([u]) datasets_sel = cf.filter_collocated_instruments(main_sensor, datasets) save_dir = os.path.join(sDir, array, subsite, r, plot_type) cf.create_dir(save_dir) sname = '-'.join((r, ms, 'track')) print('Appending....') sh = pd.DataFrame() deployments = [] end_times = [] for ii, d in enumerate(datasets_sel): print('\nDataset {} of {}: {}'.format(ii + 1, len(datasets_sel), d.split('/')[-1])) ds = xr.open_dataset(d, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( d) if deployment_num is not None: if int(deployment.split('0')[-1]) is not deployment_num: print(type(int(deployment.split('0')[-1])), type(deployment_num)) continue # get end times of deployments ps_df, n_streams = cf.get_preferred_stream_info(r) dr_data = cf.refdes_datareview_json(r) for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = cf.get_deployment_information( dr_data, int(deploy[-4:])) if int(deploy[-4:]) not in deployments: deployments.append(int(deploy[-4:])) if pd.to_datetime(deploy_info['stop_date']) not in end_times: end_times.append(pd.to_datetime(deploy_info['stop_date'])) data = {'lat': ds['lat'].values, 'lon': ds['lon'].values} new_r = pd.DataFrame(data, columns=['lat', 'lon'], index=ds['time'].values) sh = sh.append(new_r) xD = sh.lon.values yD = sh.lat.values tD = sh.index.values clabel = 'Time' ylabel = 'Latitude' xlabel = 'Longitude' fig, ax = pf.plot_profiles(xD, yD, tD, ylabel, xlabel, clabel, end_times, deployments, stdev=None) ax.invert_yaxis() ax.set_title('Glider Track - ' + r + '\n' + 'x: platform location', fontsize=9) ax.set_xlim(-71.75, -69.75) ax.set_ylim(38.75, 40.75) #cbar.ax.set_yticklabels(end_times) # add Pioneer glider sampling area ax.add_patch( Rectangle((-71.5, 39.0), 1.58, 1.67, linewidth=3, edgecolor='b', facecolor='none')) ax.text(-71, 40.6, 'Pioneer Glider Sampling Area', color='blue', fontsize=8) # add Pioneer AUV sampling area # ax.add_patch(Rectangle((-71.17, 39.67), 0.92, 1.0, linewidth=3, edgecolor='m', facecolor='none')) array_loc = cf.return_array_subsites_standard_loc(array) ax.scatter(array_loc.lon, array_loc.lat, s=40, marker='x', color='k', alpha=0.3) #ax.legend(legn, array_loc.index, scatterpoints=1, loc='lower left', ncol=4, fontsize=8) pf.save_fig(save_dir, sname)
def main(sDir, url_list, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = uu.split(rd + '-')[1].split('/')[0] if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] datasets = [] for u in url_list: print(u) splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) if preferred_only == 'yes': ps_df, n_streams = cf.get_preferred_stream_info(r) fdatasets = [] for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets = cf.filter_collocated_instruments(main_sensor, fdatasets) save_dir = os.path.join(sDir, array, subsite, r, 'preferred_method_plots') cf.create_dir(save_dir) # get the preferred stream information fig, ax = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig.tight_layout(pad=0.4, w_pad=0.5, h_pad=1.0) fig0, ax0 = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig0.tight_layout() fig1, ax1 = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig1.tight_layout() fig2, ax2 = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig2.tight_layout() fig3, ax3 = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig3.tight_layout() fig4, ax4 = pyplot.subplots(nrows=len(fdatasets), ncols=1, sharey=True) fig4.tight_layout() for ii in range(len(fdatasets)): print('\n', fdatasets[ii]) deployment = fdatasets[ii].split('/')[-1].split('_')[0].split( 'deployment')[-1] deployment = int(deployment) ds = xr.open_dataset(fdatasets[ii], mask_and_scale=False) time = ds['time'].values sci_var = cf.return_science_vars(ds.stream) # Plot pressure z_name = [z_var for z_var in sci_var if 'pressure' in z_var] z = ds[z_name[0]].values z_unit = ds[z_name[0]].units ax1[ii].plot(time, z, 'b-', linestyle='--', linewidth=.6, label='V') ax1[ii].set_ylabel(str(deployment), rotation=0, fontsize=8, color='b', labelpad=11) ax1[ii].yaxis.set_label_position("right") ax1[ii].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) if ii < len(fdatasets) - 1: ax1[ii].set_xlabel(' ') else: ax1[ii].set_xlabel('Time', rotation=0, fontsize=8, color='b') if ii == 0: ax1[ii].set_title(r + ' - Pressure ' + z_unit, fontsize=8) sfile = 'pressure_plots' save_file = os.path.join(save_dir, sfile) fig1.savefig(str(save_file), dpi=150) # non science veriable # According to VELPT manufacturer, data are suspect when this instrument is tilted more than 20 degrees # redmine ticket: Marine Hardware #12960 roll = ds['roll_decidegree'].values roll_unit = ds['roll_decidegree'].units pitch = ds['pitch_decidegree'].values pitch_units = ds['pitch_decidegree'].units headng = ds['heading_decidegree'].values headng_units = ds['heading_decidegree'].values tilt_ind = np.logical_or(pitch > 200, roll > 200) pitch_fit = pitch[tilt_ind] roll_fit = roll[tilt_ind] # plot roll ax2[ii].plot(time, roll, 'b-', linestyle='--', linewidth=.6, label='Roll') ax2[ii].plot(time[tilt_ind], roll_fit, 'g.', linestyle='None', marker='.', markersize=0.5, label='Roll < 200') ax2[ii].set_ylabel(str(deployment), rotation=0, fontsize=8, color='b', labelpad=11) ax2[ii].yaxis.set_label_position("right") ax2[ii].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) if ii < len(fdatasets) - 1: ax2[ii].set_xlabel(' ') else: ax2[ii].set_xlabel('Time', rotation=0, fontsize=8, color='b') if ii == 0: ax2[ii].set_title(r + ' - Roll ' + roll_unit, fontsize=8) leg2 = ax2[ii].legend(fontsize=6, bbox_to_anchor=(0., 0.80, 1., .102), loc=3, ncol=3, mode="expand", borderaxespad=0.) leg2._drawFrame = False sfile = 'roll_plots' save_file = os.path.join(save_dir, sfile) fig2.savefig(str(save_file), dpi=150) # plot pitch ax3[ii].plot(time, pitch, 'b-', linestyle='--', linewidth=.6, label='Roll') ax3[ii].plot(time[tilt_ind], pitch_fit, 'g.', linestyle='None', marker='.', markersize=0.5, label='Roll < 200') ax3[ii].set_ylabel(str(deployment), rotation=0, fontsize=8, color='b', labelpad=11) ax3[ii].yaxis.set_label_position("right") ax3[ii].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) if ii < len(fdatasets) - 1: ax3[ii].set_xlabel(' ') else: ax3[ii].set_xlabel('Time', rotation=0, fontsize=8, color='b') if ii == 0: ax3[ii].set_title(r + ' - Pitch ' + roll_unit, fontsize=8) leg3 = ax2[ii].legend(fontsize=6, bbox_to_anchor=(0., 0.80, 1., .102), loc=3, ncol=3, mode="expand", borderaxespad=0.) leg3._drawFrame = False sfile = 'pitch_plots' save_file = os.path.join(save_dir, sfile) fig3.savefig(str(save_file), dpi=150) # plot heading ax4[ii].plot(time, headng, 'b-', linestyle='None', marker='.', markersize=0.5, label='Roll') ax4[ii].plot(time[tilt_ind], headng[tilt_ind], 'g.', linestyle='None', marker='.', markersize=0.5, label='Roll < 200') ax4[ii].set_ylabel(str(deployment), rotation=0, fontsize=8, color='b', labelpad=11) ax4[ii].yaxis.set_label_position("right") ax4[ii].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) if ii < len(fdatasets) - 1: ax4[ii].set_xlabel(' ') else: ax4[ii].set_xlabel('Time', rotation=0, fontsize=8, color='b') if ii == 0: ax4[ii].set_title(r + ' - Heading ' + roll_unit, fontsize=8) leg4 = ax2[ii].legend(fontsize=6, bbox_to_anchor=(0., 0.80, 1., .102), loc=3, ncol=3, mode="expand", borderaxespad=0.) leg4._drawFrame = False sfile = 'heading_plots' save_file = os.path.join(save_dir, sfile) fig4.savefig(str(save_file), dpi=150) # velocity variable u_name = [ u_var for u_var in sci_var if 'eastward_velocity' in u_var ] v_name = [ v_var for v_var in sci_var if 'northward_velocity' in v_var ] w_name = [w_var for w_var in sci_var if 'upward_velocity' in w_var] w = ds[w_name[0]].values w_unit = ds[w_name[0]].units u = ds[u_name[0]].values v = ds[v_name[0]].values uv_magnitude = np.sqrt(u**2 + v**2) uv_maxmag = max(uv_magnitude) # 1D Quiver plot ax[ii].quiver(time, 0, u, v, color='r', units='y', scale_units='y', scale=1, headlength=1, headaxislength=1, width=0.004, alpha=0.5) u_fit = u[tilt_ind] v_fit = v[tilt_ind] ax[ii].quiver(time[tilt_ind], 0, u_fit, v_fit, color='b', units='y', scale_units='y', scale=1, headlength=1, headaxislength=1, width=0.004, alpha=0.5) percent_bad = round(((len(u) - len(u_fit)) / len(u)) * 100, 2) print(len(u_fit), len(u), percent_bad) ax[ii].text(time[-1], 0, ' ' + str(percent_bad) + '%', fontsize=5, style='italic', color='blue') ax[ii].set_ylim(-uv_maxmag, uv_maxmag) ax[ii].set_ylabel(str(deployment), rotation=0, fontsize=8, color='b', labelpad=11) ax[ii].yaxis.set_label_position("right") ax[ii].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) if ii < len(fdatasets) - 1: ax[ii].set_xlabel(' ') else: ax[ii].set_xlabel('Time', rotation=0, fontsize=8, color='b') if ii == 0: ax[ii].set_title( r + ' - Current Velocity ' + w_unit + '\n' + ' Currents in blue when pitch or roll are > 20 degrees', fontsize=8) # ax[ii].text(time[0], uv_magnitude- 0.05, 'mim: ' + str(round(min(uv_magnitude),3)) + ' , max: ' + str(round(max(uv_magnitude),3)), fontsize=8) sfile = 'current_plot' save_file = os.path.join(save_dir, sfile) fig.savefig(str(save_file), dpi=150, bbox_inches='tight')
def main(sDir, url_list, start_time, end_time, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets fdatasets = np.unique(fdatasets).tolist() for fd in fdatasets: ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd) sci_vars = cf.return_science_vars(stream) print('\nPlotting {} {}'.format(r, deployment)) array = subsite[0:2] filename = '_'.join(fname.split('_')[:-1]) save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_plots') cf.create_dir(save_dir) tm = ds['time'].values t0 = pd.to_datetime(tm.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tm.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) # -------- plot entire deployment -------- for var in sci_vars: print(var) vv = ds[var] fv = vv._FillValue # need to round SPKIR values to 1 decimal place to match the global ranges. otherwise, values that # round to zero (e.g. 1.55294e-05) will be excluded by the global range test # v = np.round(vv.values.T, 1) # .T = transpose 2D array v = vv.values.T n_nan = np.sum(np.isnan(v)) # convert fill values to nans v[v == fv] = np.nan n_fv = np.sum(np.isnan(v)) - n_nan # plot before global ranges are removed fig, ax = pf.plot_spkir(tm, v, vv.name, vv.units) ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, var, t0[:10])) pf.save_fig(save_dir, sfile) # reject data outside of global ranges [g_min, g_max] = cf.get_global_ranges(r, var) if g_min is not None and g_max is not None: v[v < g_min] = np.nan v[v > g_max] = np.nan n_grange = np.sum(np.isnan(v)) - n_fv - n_nan else: n_grange = 'no global ranges' # plot after global ranges are removed fig, ax = pf.plot_spkir(tm, v, vv.name, vv.units) title2 = 'removed: {} global ranges [{}, {}]'.format( n_grange, g_min, g_max) ax.set_title((title + '\n' + t0 + ' - ' + t1 + '\n' + title2), fontsize=9) sfile = '-'.join((filename, var, t0[:10], 'rmgr')) pf.save_fig(save_dir, sfile) # -------- break the deployment into months and plot -------- save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_plots', 'monthly') cf.create_dir(save_dir) # create list of start and end dates dt_start = dt.datetime.strptime(t0, '%Y-%m-%dT%H:%M:%S') dt_end = dt.datetime.strptime(t1, '%Y-%m-%dT%H:%M:%S') start_dates = [dt_start.strftime('%m-%d-%YT00:00:00')] end_dates = [] ts1 = dt_start while ts1 <= dt_end: ts2 = ts1 + dt.timedelta(days=1) if ts2.month != ts1.month: start_dates.append(ts2.strftime('%m-%d-%YT00:00:00')) end_dates.append(ts1.strftime('%m-%d-%YT23:59:59')) ts1 = ts2 end_dates.append(dt_end.strftime('%m-%d-%YT23:59:59')) for sd, ed in zip(start_dates, end_dates): sd_format = dt.datetime.strptime(sd, '%m-%d-%YT%H:%M:%S') ed_format = dt.datetime.strptime(ed, '%m-%d-%YT%H:%M:%S') ds_month = ds.sel(time=slice(sd_format, ed_format)) if len(ds_month['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(sd, ed)) continue tm = ds_month['time'].values t0 = pd.to_datetime(tm.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tm.max()).strftime('%Y-%m-%dT%H:%M:%S') for var in sci_vars: print(var) vv = ds_month[var] fv = vv._FillValue v = vv.values.T # transpose 2D array n_nan = np.sum(np.isnan(v)) # convert fill values to nans v[v == fv] = np.nan n_fv = np.sum(np.isnan(v)) - n_nan # reject data outside of global ranges [g_min, g_max] = cf.get_global_ranges(r, var) if g_min is not None and g_max is not None: v[v < g_min] = np.nan v[v > g_max] = np.nan n_grange = np.sum(np.isnan(v)) - n_fv - n_nan else: n_grange = 'no global ranges' # plot after global ranges are removed fig, ax = pf.plot_spkir(tm, v, vv.name, vv.units) title2 = 'removed: {} global ranges [{}, {}]'.format( n_grange, g_min, g_max) ax.set_title( (title + '\n' + t0 + ' - ' + t1 + '\n' + title2), fontsize=9) sfile = '-'.join((filename, var, t0[:7], 'rmgr')) pf.save_fig(save_dir, sfile)
def main(sDir, url_list, start_time, end_time): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments(main_sensor, fdatasets) # get science variable long names from the Data Review Database #stream_sci_vars = cd.sci_var_long_names(r) if 'SPKIR' in r or 'PRESF' in r: # only get the main science variable for SPKIR stream_vars = cd.sci_var_long_names(r) else: stream_vars = var_long_names(r) # check if the science variable long names are the same for each stream and initialize empty arrays sci_vars_dict = cd.sci_var_long_names_check(stream_vars) # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) # build dictionary of science data from the preferred dataset for each deployment print('\nAppending data from files') et = [] sci_vars_dict, __, __ = cd.append_science_data(ps_df, n_streams, r, fdatasets_sel, sci_vars_dict, et, start_time, end_time) # get end times of deployments dr_data = cf.refdes_datareview_json(r) deployments = [] dend_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = get_deployment_information(dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) dend_times.append(pd.to_datetime(deploy_info['stop_date'])) subsite = r.split('-')[0] array = subsite[0:2] save_dir = os.path.join(sDir, array, subsite, r, 'timeseries_plots_preferred_all') cf.create_dir(save_dir) print('\nPlotting data') for m, n in sci_vars_dict.items(): for sv, vinfo in n['vars'].items(): print(sv) if 'SPKIR' in r: fv_lst = np.unique(vinfo['fv']).tolist() if len(fv_lst) == 1: fill_value = fv_lst[0] else: print(fv_lst) print('No unique fill value for {}'.format(sv)) sv_units = np.unique(vinfo['units']).tolist() t = vinfo['t'] if len(t) > 1: data = vinfo['values'] [dd_data, g_min, g_max] = index_dataset_2d(r, 'spkir_abj_cspp_downwelling_vector', data, fill_value) t0 = pd.to_datetime(min(t)).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(max(t)).strftime('%Y-%m-%dT%H:%M:%S') deploy_final = vinfo['deployments'] deploy = list(np.unique(deploy_final)) deployments = [int(dd) for dd in deploy] sname = '-'.join((r, sv)) fig, ax = pf.plot_spkir(t, dd_data, sv, sv_units[0]) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1 + '\n' + 'removed global ranges +/- [{} - {}]'.format(g_min, g_max)), fontsize=8) for etimes in dend_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(save_dir, sname) # plot each wavelength wavelengths = ['412nm', '443nm', '490nm', '510nm', '555nm', '620nm', '683nm'] for wvi in range(len(dd_data)): fig, ax = pf.plot_spkir_wv(t, dd_data[wvi], sv, sv_units[0], wvi) ax.set_title( (r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1 + '\n' + 'removed global ranges +/- [{} - {}]'.format(g_min, g_max)), fontsize=8) for etimes in dend_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) snamewvi = '-'.join((sname, wavelengths[wvi])) pf.save_fig(save_dir, snamewvi) elif 'presf_abc_wave_burst' in m: fv_lst = np.unique(vinfo['fv']).tolist() if len(fv_lst) == 1: fill_value = fv_lst[0] else: print(fv_lst) print('No unique fill value for {}'.format(sv)) sv_units = np.unique(vinfo['units']).tolist() t = vinfo['t'] if len(t) > 1: data = vinfo['values'] [dd_data, g_min, g_max] = index_dataset_2d(r, 'presf_wave_burst_pressure', data, fill_value) t0 = pd.to_datetime(min(t)).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(max(t)).strftime('%Y-%m-%dT%H:%M:%S') deploy_final = vinfo['deployments'] deploy = list(np.unique(deploy_final)) deployments = [int(dd) for dd in deploy] sname = '-'.join((r, sv)) fig, ax = pf.plot_presf_2d(t, dd_data, sv, sv_units[0]) ax.set_title((r + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1 + '\n' + 'removed global ranges +/- [{} - {}]'.format(g_min, g_max)), fontsize=8) for etimes in dend_times: ax.axvline(x=etimes, color='k', linestyle='--', linewidth=.6) pf.save_fig(save_dir, sname) else: if type(vinfo['values']) != dict: # if the variable is not a 2D array if 'Spectra' not in sv: if len(vinfo['t']) < 1: print('no variable data to plot') else: sv_units = vinfo['units'][0] sv_name = vinfo['var_name'] t0 = pd.to_datetime(min(vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(max(vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') x = vinfo['t'] y = vinfo['values'] # reject NaNs and values of 0.0 nan_ind = (~np.isnan(y)) & (y != 0.0) x_nonan = x[nan_ind] y_nonan = y[nan_ind] # reject fill values fv_ind = y_nonan != vinfo['fv'][0] x_nonan_nofv = x_nonan[fv_ind] y_nonan_nofv = y_nonan[fv_ind] # reject extreme values Ev_ind = cf.reject_extreme_values(y_nonan_nofv) y_nonan_nofv_nE = y_nonan_nofv[Ev_ind] x_nonan_nofv_nE = x_nonan_nofv[Ev_ind] # reject values outside global ranges: global_min, global_max = cf.get_global_ranges(r, sv_name) if any(e is None for e in [global_min, global_max]): y_nonan_nofv_nE_nogr = y_nonan_nofv_nE x_nonan_nofv_nE_nogr = x_nonan_nofv_nE else: gr_ind = cf.reject_global_ranges(y_nonan_nofv_nE, global_min, global_max) y_nonan_nofv_nE_nogr = y_nonan_nofv_nE[gr_ind] x_nonan_nofv_nE_nogr = x_nonan_nofv_nE[gr_ind] if len(y_nonan_nofv) > 0: if m == 'common_stream_placeholder': sname = '-'.join((r, sv)) else: sname = '-'.join((r, m, sv)) plt_deploy = [int(x) for x in list(np.unique(vinfo['deployments']))] # plot hourly averages for cabled and FDCHP data if 'streamed' in sci_vars_dict[list(sci_vars_dict.keys())[0]]['ms'][0] or 'FDCHP' in r: sname = '-'.join((sname, 'hourlyavg')) df = pd.DataFrame({'dfx': x_nonan_nofv_nE_nogr, 'dfy': y_nonan_nofv_nE_nogr}) dfr = df.resample('H', on='dfx').mean() # Plot all data fig, ax = pf.plot_timeseries_all(dfr.index, dfr['dfy'], sv, sv_units, stdev=None) ax.set_title((r + '\nDeployments: ' + str(plt_deploy) + '\n' + t0 + ' - ' + t1), fontsize=8) # if plotting a specific time range, plot deployment lines only for those deployments if type(start_time) == dt.datetime: for e in list(np.unique(vinfo['deployments'])): etime = dend_times[int(e) - 1] ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) else: for etime in dend_times: ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) pf.save_fig(save_dir, sname) else: # Plot all data fig, ax = pf.plot_timeseries_all(x_nonan_nofv, y_nonan_nofv, sv, sv_units, stdev=None) ax.set_title((r + '\nDeployments: ' + str(plt_deploy) + '\n' + t0 + ' - ' + t1), fontsize=8) # if plotting a specific time range, plot deployment lines only for those deployments if type(start_time) == dt.datetime: # for e in list(np.unique(vinfo['deployments'])): # etime = dend_times[int(e) - 1] # ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) etime = dend_times[int(list(np.unique(vinfo['deployments']))[0]) - 1] ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) else: for etime in dend_times: ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) # if not any(e is None for e in [global_min, global_max]): # ax.axhline(y=global_min, color='r', linestyle='--', linewidth=.6) # ax.axhline(y=global_max, color='r', linestyle='--', linewidth=.6) # else: # maxpoint = x[np.argmax(y_nonan_nofv)], max(y_nonan_nofv) # ax.annotate('No Global Ranges', size=8, # xy=maxpoint, xytext=(5, 5), textcoords='offset points') pf.save_fig(save_dir, sname) # Plot data with outliers removed fig, ax = pf.plot_timeseries_all(x_nonan_nofv_nE_nogr, y_nonan_nofv_nE_nogr, sv, sv_units, stdev=5) ax.set_title((r + '\nDeployments: ' + str(plt_deploy) + '\n' + t0 + ' - ' + t1), fontsize=8) # if plotting a specific time range, plot deployment lines only for those deployments if type(start_time) == dt.datetime: # for e in list(np.unique(vinfo['deployments'])): # etime = dend_times[int(e) - 1] # ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) etime = dend_times[int(list(np.unique(vinfo['deployments']))[0]) - 1] ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) else: for etime in dend_times: ax.axvline(x=etime, color='b', linestyle='--', linewidth=.6) # if not any(e is None for e in [global_min, global_max]): # ax.axhline(y=global_min, color='r', linestyle='--', linewidth=.6) # ax.axhline(y=global_max, color='r', linestyle='--', linewidth=.6) # else: # maxpoint = x[np.argmax(y_nonan_nofv_nE_nogr)], max(y_nonan_nofv_nE_nogr) # ax.annotate('No Global Ranges', size=8, # xy=maxpoint, xytext=(5, 5), textcoords='offset points') sfile = '_'.join((sname, 'rmoutliers')) pf.save_fig(save_dir, sfile)
def main(sDir, url_list, start_time, end_time): # get summary lists of reference designators and delivery methods rd_list = [] rdm_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) rdm = '-'.join((rd, elements[5])) if rd not in rd_list: rd_list.append(rd) if rdm not in rdm_list: rdm_list.append(rdm) for r in rd_list: rdm_filtered = [k for k in rdm_list if r in k] dinfo = {} if len(rdm_filtered) == 1: print('Only one delivery method provided - no comparison.') continue elif len(rdm_filtered) > 1 & len(rdm_filtered) <= 3: print('\nComparing data from different methods for: {}'.format(r)) for i in range(len(rdm_filtered)): urls = [x for x in url_list if rdm_filtered[i] in x] for u in urls: splitter = u.split('/')[-2].split('-') catalog_rms = '-'.join((r, splitter[-2], splitter[-1])) udatasets = cf.get_nc_urls([u]) deployments = [ str(k.split('/')[-1][0:14]) for k in udatasets ] udeploy = np.unique(deployments).tolist() for ud in udeploy: rdatasets = [s for s in udatasets if ud in s] datasets = [] for dss in rdatasets: # filter out collocated data files if catalog_rms == dss.split('/')[-1].split( '_20')[0][15:]: datasets.append(dss) if len(datasets) == 0: print('no data for ', ud) else: file_ms_lst = [] for dataset in datasets: splt = dataset.split('/')[-1].split( '_20')[0].split('-') file_ms_lst.append('-'.join( (splt[-2], splt[-1]))) file_ms = np.unique(file_ms_lst).tolist()[0] try: dinfo[file_ms] except KeyError: dinfo[file_ms] = {} dinfo[file_ms].update({ud: datasets}) else: print( 'More than 3 methods provided. Please provide fewer datasets for analysis.' ) continue dinfo_df = pd.DataFrame(dinfo) umethods = [] ustreams = [] for k in dinfo.keys(): umethods.append(k.split('-')[0]) ustreams.append(k.split('-')[1]) if len(np.unique(ustreams)) > len( np.unique(umethods) ): # if there is more than 1 stream per delivery method method_stream_df = cf.stream_word_check(dinfo) streamlst = (np.unique( method_stream_df['stream_name_compare'])).tolist() for cs in streamlst: print('Common stream_name: {}'.format(cs)) method_stream_list = [] for row in method_stream_df.itertuples(): index, method, stream_name, stream_name_compare = row if stream_name_compare == cs: method_stream_list.append('-'.join( (method, stream_name))) dinfo_df_filtered = dinfo_df[method_stream_list] compare_plot_datasets(dinfo_df_filtered, r, start_time, end_time, sDir, cs) else: compare_plot_datasets(dinfo_df, r, start_time, end_time, sDir)
def main(sDir, url_list, start_time, end_time, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'OPTAA' in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) for ud in udatasets: # filter out collocated data files if 'OPTAA' in ud.split('/')[-1]: datasets.append(ud) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets fdatasets = np.unique(fdatasets).tolist() for fd in fdatasets: ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(fd) #sci_vars = cf.return_science_vars(stream) sci_vars = ['optical_absorption', 'beam_attenuation'] print('\nPlotting {} {}'.format(r, deployment)) array = subsite[0:2] filename = '_'.join(fname.split('_')[:-1]) save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_plots') cf.create_dir(save_dir) tm = ds['time'].values t0 = pd.to_datetime(tm.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tm.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) # # add chl-a data from the collocated fluorometer # flor_url = [s for s in url_list if r.split('-')[0] in s and 'FLOR' in s] # if len(flor_url) == 1: # flor_datasets = cf.get_nc_urls(flor_url) # # filter out collocated datasets # flor_dataset = [j for j in flor_datasets if ('FLOR' in j.split('/')[-1] and deployment in j.split('/')[-1])] # if len(flor_dataset) > 0: # ds_flor = xr.open_dataset(flor_dataset[0], mask_and_scale=False) # ds_flor = ds_flor.swap_dims({'obs': 'time'}) # flor_t0 = dt.datetime.strptime(t0, '%Y-%m-%dT%H:%M:%S') # flor_t1 = dt.datetime.strptime(t1, '%Y-%m-%dT%H:%M:%S') # ds_flor = ds_flor.sel(time=slice(flor_t0, flor_t1)) # t_flor = ds_flor['time'].values # flor_sci_vars = cf.return_science_vars(ds_flor.stream) # for fsv in flor_sci_vars: # if ds_flor[fsv].long_name == 'Chlorophyll-a Concentration': # chla = ds_flor[fsv] for var in sci_vars: print(var) if var == 'optical_absorption': wv = ds['wavelength_a'].values else: wv = ds['wavelength_c'].values vv = ds[var] fv = vv._FillValue fig1, ax1 = plt.subplots() fig2, ax2 = plt.subplots() plotting = [] # keep track if anything is plotted wavelengths = [] iwavelengths = [] for i in range(len(wv)): if (wv[i] > 671.) and (wv[i] < 679.): wavelengths.append(wv[i]) iwavelengths.append(i) colors = ['purple', 'green', 'orange'] for iw in range(len(iwavelengths)): v = vv.sel(wavelength=iwavelengths[iw]).values n_all = len(v) n_nan = np.sum(np.isnan(v)) # convert fill values to nans v[v == fv] = np.nan n_fv = np.sum(np.isnan(v)) - n_nan if n_nan + n_fv < n_all: # plot before global ranges are removed #fig, ax = pf.plot_optaa(tm, v, vv.name, vv.units) plotting.append('yes') ax1.scatter(tm, v, c=colors[iw], label='{} nm'.format(wavelengths[iw]), marker='.', s=1) # reject data outside of global ranges [g_min, g_max] = cf.get_global_ranges(r, var) if g_min is not None and g_max is not None: v[v < g_min] = np.nan v[v > g_max] = np.nan n_grange = np.sum(np.isnan(v)) - n_fv - n_nan else: n_grange = 'no global ranges' # plot after global ranges are removed ax2.scatter(tm, v, c=colors[iw], label='{} nm: rm {} GR'.format(wavelengths[iw], n_grange), marker='.', s=1) # if iw == len(wavelengths) - 1: # ax2a = ax2.twinx() # ax2a.scatter(t_flor, chla.values, c='lime', marker='.', s=1) # ax2a.set_ylabel('Fluorometric Chl-a ({})'.format(chla.units)) if len(plotting) > 0: ax1.grid() pf.format_date_axis(ax1, fig1) ax1.legend(loc='best', fontsize=7) ax1.set_ylabel((var + " (" + vv.units + ")"), fontsize=9) ax1.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, var, t0[:10])) save_file = os.path.join(save_dir, sfile) fig1.savefig(str(save_file), dpi=150) ax2.grid() pf.format_date_axis(ax2, fig2) ax2.legend(loc='best', fontsize=7) ax2.set_ylabel((var + " (" + vv.units + ")"), fontsize=9) title_gr = 'GR: global ranges' ax2.set_title((title + '\n' + t0 + ' - ' + t1 + '\n' + title_gr), fontsize=9) sfile2 = '-'.join((filename, var, t0[:10], 'rmgr')) save_file2 = os.path.join(save_dir, sfile2) fig2.savefig(str(save_file2), dpi=150) plt.close('all')
def main(sDir, url_list): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] ps_df, n_streams = cf.get_preferred_stream_info(r) # get end times of deployments dr_data = cf.refdes_datareview_json(r) deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = get_deployment_information(dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append(pd.to_datetime(deploy_info['stop_date'])) # filter datasets datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) main_sensor = r.split('-')[-1] fdatasets = cf.filter_collocated_instruments(main_sensor, datasets) methodstream = [] for f in fdatasets: methodstream.append('-'.join((f.split('/')[-2].split('-')[-2], f.split('/')[-2].split('-')[-1]))) for ms in np.unique(methodstream): fdatasets_sel = [x for x in fdatasets if ms in x] save_dir = os.path.join(sDir, array, subsite, r, 'timeseries_plots_all', ms.split('-')[0]) cf.create_dir(save_dir) stream_sci_vars_dict = dict() for x in dr_data['instrument']['data_streams']: dr_ms = '-'.join((x['method'], x['stream_name'])) if ms == dr_ms: stream_sci_vars_dict[dr_ms] = dict(vars=dict()) sci_vars = dict() for y in x['stream']['parameters']: if y['data_product_type'] == 'Science Data': sci_vars.update( {y['name']: dict(db_units=y['unit'])}) if len(sci_vars) > 0: stream_sci_vars_dict[dr_ms]['vars'] = sci_vars sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict, ms) print('\nAppending data from files: {}'.format(ms)) for fd in fdatasets_sel: ds = xr.open_dataset(fd, mask_and_scale=False) for var in list(sci_vars_dict[ms]['vars'].keys()): sh = sci_vars_dict[ms]['vars'][var] if ds[var].units == sh['db_units']: if ds[var]._FillValue not in sh['fv']: sh['fv'].append(ds[var]._FillValue) if ds[var].units not in sh['units']: sh['units'].append(ds[var].units) tD = ds['time'].values varD = ds[var].values sh['t'] = np.append(sh['t'], tD) sh['values'] = np.append(sh['values'], varD) print('\nPlotting data') for m, n in sci_vars_dict.items(): for sv, vinfo in n['vars'].items(): print(sv) if len(vinfo['t']) < 1: print('no variable data to plot') else: sv_units = vinfo['units'][0] t0 = pd.to_datetime(min( vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(max( vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') x = vinfo['t'] y = vinfo['values'] # reject NaNs nan_ind = ~np.isnan(y) x_nonan = x[nan_ind] y_nonan = y[nan_ind] # reject fill values fv_ind = y_nonan != vinfo['fv'][0] x_nonan_nofv = x_nonan[fv_ind] y_nonan_nofv = y_nonan[fv_ind] # reject extreme values Ev_ind = cf.reject_extreme_values(y_nonan_nofv) y_nonan_nofv_nE = y_nonan_nofv[Ev_ind] x_nonan_nofv_nE = x_nonan_nofv[Ev_ind] # reject values outside global ranges: global_min, global_max = cf.get_global_ranges(r, sv) if global_min is not None and global_max is not None: gr_ind = cf.reject_global_ranges( y_nonan_nofv_nE, global_min, global_max) y_nonan_nofv_nE_nogr = y_nonan_nofv_nE[gr_ind] x_nonan_nofv_nE_nogr = x_nonan_nofv_nE[gr_ind] else: y_nonan_nofv_nE_nogr = y_nonan_nofv_nE x_nonan_nofv_nE_nogr = x_nonan_nofv_nE title = ' '.join((r, ms.split('-')[0])) if len(y_nonan_nofv) > 0: if m == 'common_stream_placeholder': sname = '-'.join((r, sv)) else: sname = '-'.join((r, m, sv)) # Plot all data fig, ax = pf.plot_timeseries_all(x_nonan_nofv, y_nonan_nofv, sv, sv_units, stdev=None) ax.set_title((title + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='b', linestyle='--', linewidth=.6) if global_min is not None and global_max is not None: ax.axhline(y=global_min, color='r', linestyle='--', linewidth=.6) ax.axhline(y=global_max, color='r', linestyle='--', linewidth=.6) pf.save_fig(save_dir, sname) # Plot data with extreme values, data outside global ranges and outliers removed fig, ax = pf.plot_timeseries_all( x_nonan_nofv_nE_nogr, y_nonan_nofv_nE_nogr, sv, sv_units, stdev=5) ax.set_title((title + '\nDeployments: ' + str(sorted(deployments)) + '\n' + t0 + ' - ' + t1), fontsize=8) for etimes in end_times: ax.axvline(x=etimes, color='b', linestyle='--', linewidth=.6) if global_min is not None and global_max is not None: ax.axhline(y=global_min, color='r', linestyle='--', linewidth=.6) ax.axhline(y=global_max, color='r', linestyle='--', linewidth=.6) sfile = '_'.join((sname, 'rmoutliers')) pf.save_fig(save_dir, sfile)
def main(url_list, sDir, plot_type, deployment_num, start_time, end_time, preferred_only, glider, zdbar, n_std, inpercentile, zcell_size): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'ENG' not in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments(main_sensor, fdatasets) for fd in fdatasets_sel: part_d = fd.split('/')[-1] print(part_d) ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(fd) array = subsite[0:2] sci_vars = cf.return_science_vars(stream) if 'CE05MOAS' in r or 'CP05MOAS' in r: # for coastal gliders, get m_water_depth for bathymetry eng = '-'.join((r.split('-')[0], r.split('-')[1], '00-ENG000000', method, 'glider_eng')) eng_url = [s for s in url_list if eng in s] if len(eng_url) == 1: eng_datasets = cf.get_nc_urls(eng_url) # filter out collocated datasets eng_dataset = [j for j in eng_datasets if (eng in j.split('/')[-1] and deployment in j.split('/')[-1])] if len(eng_dataset) > 0: ds_eng = xr.open_dataset(eng_dataset[0], mask_and_scale=False) t_eng = ds_eng['time'].values m_water_depth = ds_eng['m_water_depth'].values # m_altimeter_status = 0 means a good reading (not nan or -1) eng_ind = ds_eng['m_altimeter_status'].values == 0 m_water_depth = m_water_depth[eng_ind] t_eng = t_eng[eng_ind] else: print('No engineering file for deployment {}'.format(deployment)) if deployment_num is not None: if int(deployment.split('0')[-1]) is not deployment_num: print(type(int(deployment.split('0')[-1])), type(deployment_num)) continue if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue stime = start_time.strftime('%Y-%m-%d') etime = end_time.strftime('%Y-%m-%d') ext = stime + 'to' + etime # .join((ds0_method, ds1_method save_dir = os.path.join(sDir, array, subsite, refdes, plot_type, deployment, ext) else: save_dir = os.path.join(sDir, array, subsite, refdes, plot_type, deployment) cf.create_dir(save_dir) tm = ds['time'].values # get pressure variable ds_vars = list(ds.data_vars.keys()) + [x for x in ds.coords.keys() if 'pressure' in x] y, y_units, press = cf.add_pressure_to_dictionary_of_sci_vars(ds) print(y_units, press) # press = pf.pressure_var(ds, ds_vars) # print(press) # y = ds[press].values # y_units = ds[press].units for sv in sci_vars: print(sv) if 'sci_water_pressure' not in sv: z = ds[sv].values fv = ds[sv]._FillValue z_units = ds[sv].units # Check if the array is all NaNs if sum(np.isnan(z)) == len(z): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z[z != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: """ clean up data """ # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max = \ cf.reject_erroneous_data(r, sv, tm, y, z, fv) # get rid of 0.0 data if 'CTD' in r: ind = zpressure > 0.0 else: ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = dtime[ind] zpressure = zpressure[ind] ndata = ndata[ind] # creating data groups columns = ['tsec', 'dbar', str(sv)] min_r = int(round(min(zpressure) - zcell_size)) max_r = int(round(max(zpressure) + zcell_size)) ranges = list(range(min_r, max_r, zcell_size)) groups, d_groups = gt.group_by_depth_range(dtime, zpressure, ndata, columns, ranges) # rejecting timestamps from percentile analysis y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr, time_ex = cf.reject_timestamps_in_groups( groups, d_groups, n_std, inpercentile) t_nospct, z_nospct, y_nospct = cf.reject_suspect_data(dtime, zpressure, ndata, time_ex) print('removed {} data points using {} percentile of data grouped in {} dbar segments'.format( len(zpressure) - len(z_nospct), inpercentile, zcell_size)) # reject time range from data portal file export t_portal, z_portal, y_portal = cf.reject_timestamps_dataportal(subsite, r, t_nospct, y_nospct, z_nospct) print('removed {} data points using visual inspection of data'.format(len(z_nospct) - len(z_portal))) # reject data in a depth range if zdbar: y_ind = y_portal < zdbar n_zdbar = np.sum(~y_ind) t_array = t_portal[y_ind] y_array = y_portal[y_ind] z_array = z_portal[y_ind] else: n_zdbar = 0 t_array = t_portal y_array = y_portal z_array = z_portal print('{} in water depth > {} dbar'.format(n_zdbar, zdbar)) """ Plot data """ if len(dtime) > 0: sname = '-'.join((r, method, sv)) clabel = sv + " (" + z_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" if glider == 'no': t_eng = None m_water_depth = None # plot non-erroneous data fig, ax, bar = pf.plot_xsection(subsite, dtime, zpressure, ndata, clabel, ylabel, t_eng, m_water_depth, inpercentile, stdev=None) t0 = pd.to_datetime(dtime.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(dtime.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) + '\n' + t0 + ' to ' + t1 ax.set_title(title, fontsize=9) leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} zeros'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() sfile = '_'.join(('rm_erroneous_data', sname)) pf.save_fig(save_dir, sfile) # plots removing all suspect data if len(t_array) > 0: if len(t_array) != len(dtime): # plot bathymetry only within data time ranges if glider == 'yes': eng_ind = (t_eng >= np.min(t_array)) & (t_eng <= np.max(t_array)) t_eng = t_eng[eng_ind] m_water_depth = m_water_depth[eng_ind] fig, ax, bar = pf.plot_xsection(subsite, t_array, y_array, z_array, clabel, ylabel, t_eng, m_water_depth, inpercentile, stdev=None) t0 = pd.to_datetime(t_array.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(t_array.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) + '\n' + t0 + ' to ' + t1 ax.set_title(title, fontsize=9) if zdbar: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} zeros'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nremoved {} in the upper and lower {}th percentile of data grouped in {} dbar segments'.format( len(zpressure) - len(z_nospct), inpercentile, zcell_size) + '\nexcluded {} suspect data points when inspected visually'.format( len(z_nospct) - len(z_portal)) + '\nexcluded {} suspect data in water depth greater than {} dbar'.format(n_zdbar, zdbar), ) else: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} zeros'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nremoved {} in the upper and lower {}th percentile of data grouped in {} dbar segments'.format( len(zpressure) - len(z_nospct), inpercentile, zcell_size) + '\nexcluded {} suspect data points when inspected visually'.format( len(z_nospct) - len(z_portal)), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() sfile = '_'.join(('rm_suspect_data', sname)) pf.save_fig(save_dir, sfile)
def main(url_list, sDir, mDir, zcell_size, zdbar, start_time, end_time, inpercentile): """"" URL : path to instrument data by methods sDir : path to the directory on your machine to save plots mDir : path to the directory on your machine to save data ranges zcell_size : depth cell size to group data zdbar : define depth where suspect data are identified start_time : select start date to slice timeseries end_time : select end date to slice timeseries """"" rd_list = [] ms_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = uu.split(rd + '-')[1].split('/')[0] if rd not in rd_list: rd_list.append(rd) if ms not in ms_list: ms_list.append(ms) for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] main_sensor = r.split('-')[-1] # read in the analysis file dr_data = cf.refdes_datareview_json(r) # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) # get science variable long names from the Data Review Database stream_sci_vars = cd.sci_var_long_names(r) # check if the science variable long names are the same for each stream and initialize empty arrays sci_vars_dict0 = cd.sci_var_long_names_check(stream_sci_vars) # get the list of data files and filter out collocated instruments and other streams datasets = [] for u in url_list: print(u) splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = cf.filter_collocated_instruments(main_sensor, datasets) fdatasets = cf.filter_other_streams(r, ms_list, fdatasets) # select the list of data files from the preferred dataset for each deployment fdatasets_final = [] for ii in range(len(ps_df)): for x in fdatasets: if ps_df['deployment'][ii] in x and ps_df[0][ii] in x: fdatasets_final.append(x) # build dictionary of science data from the preferred dataset for each deployment print('\nAppending data from files') sci_vars_dict, y_unit, y_name, l0 = cd.append_evaluated_science_data( sDir, ps_df, n_streams, r, fdatasets_final, sci_vars_dict0, zdbar, start_time, end_time) # get end times of deployments deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = cf.get_deployment_information(dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append(pd.to_datetime(deploy_info['stop_date'])) # create data range output folders save_dir_stat = os.path.join(mDir, array, subsite) cf.create_dir(save_dir_stat) # create plots output folder save_fdir = os.path.join(sDir, array, subsite, r, 'data_range') cf.create_dir(save_fdir) stat_df = pd.DataFrame() """ create data ranges csv file and figures """ for m, n in sci_vars_dict.items(): for sv, vinfo in n['vars'].items(): print('\n' + vinfo['var_name']) if len(vinfo['t']) < 1: print('no variable data to plot') continue else: sv_units = vinfo['units'][0] fv = vinfo['fv'][0] t = vinfo['t'] z = vinfo['values'] y = vinfo['pressure'] # Check if the array is all NaNs if sum(np.isnan(z)) == len(z): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z[z != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: if len(y) > 0: if m == 'common_stream_placeholder': sname = '-'.join((vinfo['var_name'], r)) else: sname = '-'.join((vinfo['var_name'], r, m)) """ create data ranges for non - pressure data only """ if 'pressure' in vinfo['var_name']: pass else: columns = ['tsec', 'dbar', str(vinfo['var_name'])] # create depth ranges min_r = int(round(min(y) - zcell_size)) max_r = int(round(max(y) + zcell_size)) ranges = list(range(min_r, max_r, zcell_size)) # group data by depth groups, d_groups = gt.group_by_depth_range(t, y, z, columns, ranges) print('writing data ranges for {}'.format(vinfo['var_name'])) stat_data = groups.describe()[vinfo['var_name']] stat_data.insert(loc=0, column='parameter', value=sv, allow_duplicates=False) t_deploy = deployments[0] for i in range(len(deployments))[1:len(deployments)]: t_deploy = '{}, {}'.format(t_deploy, deployments[i]) stat_data.insert(loc=1, column='deployments', value=t_deploy, allow_duplicates=False) stat_df = stat_df.append(stat_data, ignore_index=False) """ plot full time range free from errors and suspect data """ clabel = sv + " (" + sv_units + ")" ylabel = (y_name[0][0] + " (" + y_unit[0][0] + ")") t_eng = None m_water_depth = None # plot non-erroneous -suspect data fig, ax, bar = pf.plot_xsection(subsite, t, y, z, clabel, ylabel, t_eng, m_water_depth, inpercentile, stdev=None) title0 = 'Data colored using the upper and lower {} percentile.'.format(inpercentile) ax.set_title(r+'\n'+title0, fontsize=9) leg_text = ('{} % erroneous values removed after Human In the Loop review'.format( (len(t)/l0) * 100),) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) for ii in range(len(end_times)): ax.axvline(x=end_times[ii], color='b', linestyle='--', linewidth=.8) ax.text(end_times[ii], min(y)-5, 'End' + str(deployments[ii]), fontsize=6, style='italic', bbox=dict(boxstyle='round', ec=(0., 0.5, 0.5), fc=(1., 1., 1.), )) # fig.tight_layout() sfile = '_'.join(('data_range', sname)) pf.save_fig(save_fdir, sfile) # write stat file stat_df.to_csv('{}/{}_data_ranges.csv'.format(save_dir_stat, r), index=True, float_format='%11.6f')
ctd_pressure = np.squeeze(np.array(df['PRES'])) except KeyError: print('No pressure variable found in the cruise CTD file') ctd_pressure = [] CTDloc = [ctd_lat, ctd_lon] # CTD cast location for url in urls: splitter = url.split('/')[-2].split('-') refdes = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if CTDfile_platform in refdes: # if the file is mapped to this reference designator print(refdes) catalog_rms = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4], splitter[5], splitter[6])) ud = cf.get_nc_urls([url]) datasets = [] for u in ud: spl = u.split('/')[-1].split('_') file_rms = '_'.join(spl[1:-1]) if catalog_rms == file_rms and deployment[-1] in spl[0]: datasets.append(u) if len(datasets) == 1: with xr.open_dataset(datasets[0], mask_and_scale=False) as ds: ds = ds.swap_dims({'obs': 'time'}) # select data within +/- 1 day of the CTD cast dstart = cast_start - uframe_window dend = cast_start + uframe_window ds = ds.sel(time=slice(dstart, dend))
def main(sDir, url_list, start_time, end_time, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): rms = '-'.join((r, row[ii])) for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets for fd in fdatasets: with xr.open_dataset(fd, mask_and_scale=False) as ds: ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(fd) print('\nPlotting {} {}'.format(r, deployment)) array = subsite[0:2] save_dir = os.path.join(sDir, array, subsite, refdes, 'ts_plots') cf.create_dir(save_dir) tme = ds['time'].values t0 = pd.to_datetime(tme.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tme.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) filename = '-'.join(('_'.join(fname.split('_')[:-1]), 'ts', t0[:10])) ds_vars = list(ds.data_vars.keys()) raw_vars = cf.return_raw_vars(ds_vars) xvar = return_var(ds, raw_vars, 'salinity', 'Practical Salinity') sal = ds[xvar].values sal_fv = ds[xvar]._FillValue yvar = return_var(ds, raw_vars, 'temp', 'Seawater Temperature') temp = ds[yvar].values temp_fv = ds[yvar]._FillValue press = pf.pressure_var(ds, list(ds.coords.keys())) if press is None: press = pf.pressure_var(ds, list(ds.data_vars.keys())) p = ds[press].values # get rid of nans, 0.0s, fill values sind1 = (~np.isnan(sal)) & (sal != 0.0) & (sal != sal_fv) sal = sal[sind1] temp = temp[sind1] tme = tme[sind1] p = p[sind1] tind1 = (~np.isnan(temp)) & (temp != 0.0) & (temp != temp_fv) sal = sal[tind1] temp = temp[tind1] tme = tme[tind1] p = p[tind1] # reject values outside global ranges: global_min, global_max = cf.get_global_ranges(r, xvar) if any(e is None for e in [global_min, global_max]): sal = sal temp = temp tme = tme p = p else: sgr_ind = cf.reject_global_ranges(sal, global_min, global_max) sal = sal[sgr_ind] temp = temp[sgr_ind] tme = tme[sgr_ind] p = p[sgr_ind] global_min, global_max = cf.get_global_ranges(r, yvar) if any(e is None for e in [global_min, global_max]): sal = sal temp = temp tme = tme p = p else: tgr_ind = cf.reject_global_ranges(temp, global_min, global_max) sal = sal[tgr_ind] temp = temp[tgr_ind] tme = tme[tgr_ind] p = p[tgr_ind] # get rid of outliers soind = cf.reject_outliers(sal, 5) sal = sal[soind] temp = temp[soind] tme = tme[soind] p = p[soind] toind = cf.reject_outliers(temp, 5) sal = sal[toind] temp = temp[toind] tme = tme[toind] p = p[toind] if len(sal) > 0: # if there are any data to plot colors = cm.rainbow(np.linspace(0, 1, len(tme))) # Figure out boundaries (mins and maxes) #smin = sal.min() - (0.01 * sal.min()) #smax = sal.max() + (0.01 * sal.max()) if sal.max() - sal.min() < 0.2: smin = sal.min() - (0.0005 * sal.min()) smax = sal.max() + (0.0005 * sal.max()) else: smin = sal.min() - (0.001 * sal.min()) smax = sal.max() + (0.001 * sal.max()) if temp.max() - temp.min() <= 1: tmin = temp.min() - (0.01 * temp.min()) tmax = temp.max() + (0.01 * temp.max()) elif 1 < temp.max() - temp.min() < 1.5: tmin = temp.min() - (0.05 * temp.min()) tmax = temp.max() + (0.05 * temp.max()) else: tmin = temp.min() - (0.1 * temp.min()) tmax = temp.max() + (0.1 * temp.max()) # Calculate how many gridcells are needed in the x and y directions and # Create temp and sal vectors of appropriate dimensions xdim = int(round((smax-smin)/0.1 + 1, 0)) if xdim == 1: xdim = 2 si = np.linspace(0, xdim - 1, xdim) * 0.1 + smin if 1.1 <= temp.max() - temp.min() < 1.7: # if the diff between min and max temp is small ydim = int(round((tmax-tmin)/0.75 + 1, 0)) ti = np.linspace(0, ydim - 1, ydim) * 0.75 + tmin elif temp.max() - temp.min() < 1.1: ydim = int(round((tmax - tmin) / 0.1 + 1, 0)) ti = np.linspace(0, ydim - 1, ydim) * 0.1 + tmin else: ydim = int(round((tmax - tmin) + 1, 0)) ti = np.linspace(0, ydim - 1, ydim) + tmin # Create empty grid of zeros mdens = np.zeros((ydim, xdim)) # Loop to fill in grid with densities for j in range(0, ydim): for i in range(0, xdim): mdens[j, i] = gsw.density.rho(si[i], ti[j], np.median(p)) # calculate density using median pressure value fig, ax = pf.plot_ts(si, ti, mdens, sal, temp, colors) ax.set_title((title + '\n' + t0 + ' - ' + t1 + '\ncolors = time (cooler: earlier)'), fontsize=9) leg_text = ('Removed {} values (SD=5)'.format(len(ds[xvar].values) - len(sal)),) ax.legend(leg_text, loc='best', fontsize=6) pf.save_fig(save_dir, filename)
def main(url_list, sDir, deployment_num, start_time, end_time, preferred_only, zdbar, n_std, inpercentile, zcell_size): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'ENG' not in rd and 'ADCP' not in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments( main_sensor, fdatasets) for fd in fdatasets_sel: part_d = fd.split('/')[-1] print('\n{}'.format(part_d)) ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd) array = subsite[0:2] sci_vars = cf.return_science_vars(stream) # if 'CE05MOAS' in r or 'CP05MOAS' in r: # for coastal gliders, get m_water_depth for bathymetry # eng = '-'.join((r.split('-')[0], r.split('-')[1], '00-ENG000000', method, 'glider_eng')) # eng_url = [s for s in url_list if eng in s] # if len(eng_url) == 1: # eng_datasets = cf.get_nc_urls(eng_url) # # filter out collocated datasets # eng_dataset = [j for j in eng_datasets if (eng in j.split('/')[-1] and deployment in j.split('/')[-1])] # if len(eng_dataset) > 0: # ds_eng = xr.open_dataset(eng_dataset[0], mask_and_scale=False) # t_eng = ds_eng['time'].values # m_water_depth = ds_eng['m_water_depth'].values # # # m_altimeter_status = 0 means a good reading (not nan or -1) # try: # eng_ind = ds_eng['m_altimeter_status'].values == 0 # except KeyError: # eng_ind = (~np.isnan(m_water_depth)) & (m_water_depth >= 0) # # m_water_depth = m_water_depth[eng_ind] # t_eng = t_eng[eng_ind] # # # get rid of any remaining nans or fill values # eng_ind2 = (~np.isnan(m_water_depth)) & (m_water_depth >= 0) # m_water_depth = m_water_depth[eng_ind2] # t_eng = t_eng[eng_ind2] # else: # print('No engineering file for deployment {}'.format(deployment)) # m_water_depth = None # t_eng = None # else: # m_water_depth = None # t_eng = None # else: # m_water_depth = None # t_eng = None if deployment_num is not None: if int(int(deployment[-4:])) is not deployment_num: print(type(int(deployment[-4:])), type(deployment_num)) continue if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue stime = start_time.strftime('%Y-%m-%d') etime = end_time.strftime('%Y-%m-%d') ext = stime + 'to' + etime # .join((ds0_method, ds1_method save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment, ext) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment, ext) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment, ext) else: save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment) texclude_dir = os.path.join(sDir, array, subsite, refdes, 'time_to_exclude') cf.create_dir(texclude_dir) time1 = ds['time'].values try: ds_lat1 = ds['lat'].values except KeyError: ds_lat1 = None print('No latitude variable in file') try: ds_lon1 = ds['lon'].values except KeyError: ds_lon1 = None print('No longitude variable in file') # get pressure variable pvarname, y1, y_units, press, y_fillvalue = cf.add_pressure_to_dictionary_of_sci_vars( ds) # prepare file to list timestamps with suspect data for each data parameter stat_data = pd.DataFrame( columns=['deployments', 'time_to_exclude']) file_exclude = '{}/{}_{}_{}_excluded_timestamps.csv'.format( texclude_dir, deployment, refdes, method) stat_data.to_csv(file_exclude, index=True) # loop through sensor-data parameters for sv in sci_vars: print(sv) if 'pressure' not in sv: z1 = ds[sv].values fv = ds[sv]._FillValue sv_units = ds[sv].units # Check if the array is all NaNs if sum(np.isnan(z1)) == len(z1): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z1[z1 != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: # remove unreasonable pressure data (e.g. for surface piercing profilers) if zdbar: po_ind = (0 < y1) & (y1 < zdbar) n_zdbar = np.sum(~po_ind) tm = time1[po_ind] y = y1[po_ind] z = z1[po_ind] ds_lat = ds_lat1[po_ind] ds_lon = ds_lon1[po_ind] print('{} in water depth > {} dbar'.format( n_zdbar, zdbar)) else: tm = time1 y = y1 z = z1 ds_lat = ds_lat1 ds_lon = ds_lon1 # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max, lat, lon = \ cf.reject_erroneous_data(r, sv, tm, y, z, fv, ds_lat, ds_lon) # get rid of 0.0 data if sv == 'salinity': ind = ndata > 30 elif sv == 'density': ind = ndata > 1022.5 elif sv == 'conductivity': ind = ndata > 3.45 else: ind = ndata > 0 # if sv == 'sci_flbbcd_chlor_units': # ind = ndata < 7.5 # elif sv == 'sci_flbbcd_cdom_units': # ind = ndata < 25 # else: # ind = ndata > 0.0 # if 'CTD' in r: # ind = zpressure > 0.0 # else: # ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = dtime[ind] zpressure = zpressure[ind] ndata = ndata[ind] if ds_lat is not None and ds_lon is not None: lat = lat[ind] lon = lon[ind] else: lat = None lon = None if len(dtime) > 0: # reject time range from data portal file export t_portal, z_portal, y_portal, lat_portal, lon_portal = \ cf.reject_timestamps_dataportal(subsite, r, dtime, zpressure, ndata, lat, lon) print( 'removed {} data points using visual inspection of data' .format(len(ndata) - len(z_portal))) # create data groups if len(y_portal) > 0: columns = ['tsec', 'dbar', str(sv)] min_r = int(round(min(y_portal) - zcell_size)) max_r = int(round(max(y_portal) + zcell_size)) ranges = list(range(min_r, max_r, zcell_size)) groups, d_groups = gt.group_by_depth_range( t_portal, y_portal, z_portal, columns, ranges) if 'scatter' in sv: n_std = None # to use percentile else: n_std = n_std # identifying timestamps from percentile analysis y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr, time_ex = cf.reject_timestamps_in_groups( groups, d_groups, n_std, inpercentile) """ writing timestamps to .csv file to use with data_range.py script """ if len(time_ex) != 0: t_exclude = time_ex[0] for i in range( len(time_ex))[1:len(time_ex)]: t_exclude = '{}, {}'.format( t_exclude, time_ex[i]) stat_data = pd.DataFrame( { 'deployments': deployment, 'time_to_exclude': t_exclude }, index=[sv]) stat_data.to_csv(file_exclude, index=True, mode='a', header=False) # rejecting timestamps from percentile analysis if len(time_ex) > 0: t_nospct, z_nospct, y_nospct = cf.reject_suspect_data( t_portal, y_portal, z_portal, time_ex) else: t_nospct = t_portal z_nospct = z_portal y_nospct = y_portal """ Plot data """ if len(t_nospct) > 0: if len(t_nospct) != len(dtime): cf.create_dir(save_dir_profile) cf.create_dir(save_dir_xsection) sname = '-'.join((r, method, sv)) sfile = '_'.join( ('rm_suspect_data', sname, pd.to_datetime( t_nospct.min()).strftime( '%Y%m%d'))) t0 = pd.to_datetime( t_nospct.min()).strftime( '%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime( t_nospct.max()).strftime( '%Y-%m-%dT%H:%M:%S') title = ' '.join( (deployment, refdes, method)) + '\n' + t0 + ' to ' + t1 if zdbar: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges ' '[{} - {}], {} unreasonable values' .format( lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nremoved {} in the upper and lower {} percentile of data grouped in {} ' 'dbar segments'.format( len(z_portal) - len(z_nospct), inpercentile, zcell_size) + '\nexcluded {} suspect data points when inspected visually' .format( len(ndata) - len(z_portal)) + '\nexcluded {} suspect data in water depth greater than {} dbar' .format(n_zdbar, zdbar), ) elif n_std: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} unreasonable values'. format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nremoved {} data points +/- {} SD of data grouped in {} dbar segments' .format( len(z_portal) - len(z_nospct), n_std, zcell_size) + '\nexcluded {} suspect data points when inspected visually' .format( len(ndata) - len(z_portal)), ) else: leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} unreasonable values'. format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nremoved {} in the upper and lower {} percentile of data grouped in {} dbar segments' .format( len(z_portal) - len(z_nospct), inpercentile, zcell_size) + '\nexcluded {} suspect data points when inspected visually' .format( len(ndata) - len(z_portal)), ) ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[ 0] + ")" clabel = 'Time' # plot non-erroneous data print('plotting profile') fig, ax = pf.plot_profiles(z_nospct, y_nospct, t_nospct, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) ax.plot(n_avg, y_avg, '-k') #ax.fill_betweenx(y_avg, n0_std, n1_std, color='m', alpha=0.2) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_profile, sfile) ''' xsection plot ''' print('plotting xsection') clabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[ 0] + ")" # plot bathymetry only within data time ranges # if t_eng is not None: # eng_ind = (t_eng >= np.nanmin(t_array)) & (t_eng <= np.nanmax(t_array)) # t_eng = t_eng[eng_ind] # m_water_depth = m_water_depth[eng_ind] # plot non-erroneous data fig, ax, bar = pf.plot_xsection( subsite, t_nospct, y_nospct, z_nospct, clabel, ylabel, t_eng=None, m_water_depth=None, inpercentile=inpercentile, stdev=None) ax.set_title(title, fontsize=9) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_xsection, sfile)
def main(sDir, url_list, start_time, end_time, deployment_num): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'OPTAA' in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] deployments = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) for ud in udatasets: # filter out collocated data files if 'OPTAA' in ud.split('/')[-1]: datasets.append(ud) if ud.split('/')[-1].split('_')[0] not in deployments: deployments.append(ud.split('/')[-1].split('_')[0]) deployments.sort() fdatasets = np.unique(datasets).tolist() for deploy in deployments: if deployment_num is not None: if int(deploy[-4:]) is not deployment_num: print('\nskipping {}'.format(deploy)) continue rdatasets = [s for s in fdatasets if deploy in s] if len(rdatasets) > 0: sci_vars_dict = {'optical_absorption': dict(atts=dict(fv=[], units=[])), 'beam_attenuation': dict(atts=dict(fv=[], units=[]))} for i in range(len(rdatasets)): #for i in range(0, 2): ##### for testing ds = xr.open_dataset(rdatasets[i], mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue if i == 0: fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(rdatasets[0]) array = subsite[0:2] filename = '_'.join(fname.split('_')[:-1]) save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_plots', deployment) cf.create_dir(save_dir) for k in sci_vars_dict.keys(): print('\nAppending data from {}: {}'.format(deploy, k)) vv = ds[k] fv = vv._FillValue vvunits = vv.units if fv not in sci_vars_dict[k]['atts']['fv']: sci_vars_dict[k]['atts']['fv'].append(fv) if vvunits not in sci_vars_dict[k]['atts']['units']: sci_vars_dict[k]['atts']['units'].append(vvunits) if k == 'optical_absorption': wavelengths = ds['wavelength_a'].values elif k == 'beam_attenuation': wavelengths = ds['wavelength_c'].values for j in range(len(wavelengths)): if (wavelengths[j] > 671.) and (wavelengths[j] < 679.): wv = str(wavelengths[j]) try: sci_vars_dict[k][wv] except KeyError: sci_vars_dict[k].update({wv: dict(values=np.array([]), time=np.array([], dtype=np.datetime64))}) v = vv.sel(wavelength=j).values sci_vars_dict[k][wv]['values'] = np.append(sci_vars_dict[k][wv]['values'], v) sci_vars_dict[k][wv]['time'] = np.append(sci_vars_dict[k][wv]['time'], ds['time'].values) title = ' '.join((deployment, refdes, method)) colors = ['purple', 'green', 'orange'] t0_array = np.array([], dtype=np.datetime64) t1_array = np.array([], dtype=np.datetime64) for var in sci_vars_dict.keys(): print('Plotting {}'.format(var)) plotting = [] # keep track if anything is plotted fig1, ax1 = plt.subplots() fig2, ax2 = plt.subplots() [g_min, g_max] = cf.get_global_ranges(r, var) for idk, dk in enumerate(sci_vars_dict[var]): if dk != 'atts': v = sci_vars_dict[var][dk]['values'] n_all = len(sci_vars_dict[var][dk]['values']) n_nan = np.sum(np.isnan(v)) # convert fill values to nans v[v == sci_vars_dict[var]['atts']['fv'][0]] = np.nan n_fv = np.sum(np.isnan(v)) - n_nan if n_nan + n_fv < n_all: # plot before global ranges are removed plotting.append('yes') tm = sci_vars_dict[var][dk]['time'] t0_array = np.append(t0_array, tm.min()) t1_array = np.append(t1_array, tm.max()) ax1.scatter(tm, v, c=colors[idk - 1], label='{} nm'.format(dk), marker='.', s=1) # reject data outside of global ranges if g_min is not None and g_max is not None: v[v < g_min] = np.nan v[v > g_max] = np.nan n_grange = np.sum(np.isnan(v)) - n_fv - n_nan else: n_grange = 'no global ranges' # plot after global ranges are removed ax2.scatter(tm, v, c=colors[idk - 1], label='{} nm: rm {} GR'.format(dk, n_grange), marker='.', s=1) if len(plotting) > 0: t0 = pd.to_datetime(t0_array.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(t1_array.max()).strftime('%Y-%m-%dT%H:%M:%S') ax1.grid() pf.format_date_axis(ax1, fig1) ax1.legend(loc='best', fontsize=7) ax1.set_ylabel((var + " (" + sci_vars_dict[var]['atts']['units'][0] + ")"), fontsize=9) ax1.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, var, t0[:10])) save_file = os.path.join(save_dir, sfile) fig1.savefig(str(save_file), dpi=150) ax2.grid() pf.format_date_axis(ax2, fig2) ax2.legend(loc='best', fontsize=7) ax2.set_ylabel((var + " (" + vv.units + ")"), fontsize=9) title_gr = 'GR: global ranges' ax2.set_title((title + '\n' + t0 + ' - ' + t1 + '\n' + title_gr), fontsize=9) sfile2 = '-'.join((filename, var, t0[:10], 'rmgr')) save_file2 = os.path.join(save_dir, sfile2) fig2.savefig(str(save_file2), dpi=150) plt.close('all')
def main(url_list, sDir, mDir, zcell_size, zdbar, start_time, end_time): """"" URL : path to instrument data by methods sDir : path to the directory on your machine to save files plot_type: folder name for a plot type """ "" rd_list = [] ms_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = uu.split(rd + '-')[1].split('/')[0] if rd not in rd_list: rd_list.append(rd) if ms not in ms_list: ms_list.append(ms) ''' separate different instruments ''' for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] main_sensor = r.split('-')[-1] # read in the analysis file dr_data = cf.refdes_datareview_json(r) # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) # get science variable long names from the Data Review Database stream_sci_vars = cd.sci_var_long_names(r) #stream_vars = cd.var_long_names(r) # check if the science variable long names are the same for each stream and initialize empty arrays sci_vars_dict0 = cd.sci_var_long_names_check(stream_sci_vars) # get the list of data files and filter out collocated instruments and other streams datasets = [] for u in url_list: print(u) splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = cf.filter_collocated_instruments(main_sensor, datasets) fdatasets = cf.filter_other_streams(r, ms_list, fdatasets) # select the list of data files from the preferred dataset for each deployment fdatasets_final = [] for ii in range(len(ps_df)): for x in fdatasets: if ps_df['deployment'][ii] in x and ps_df[0][ii] in x: fdatasets_final.append(x) # build dictionary of science data from the preferred dataset for each deployment print('\nAppending data from files') et = [] sci_vars_dict, y_unit, y_name = cd.append_evaluated_science_data( sDir, ps_df, n_streams, r, fdatasets_final, sci_vars_dict0, et, start_time, end_time) # get end times of deployments deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = cf.get_deployment_information( dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append(pd.to_datetime(deploy_info['stop_date'])) """ create a data-ranges table and figure for full data time range """ # create a folder to save data ranges save_dir_stat = os.path.join(mDir, array, subsite) cf.create_dir(save_dir_stat) save_fdir = os.path.join(sDir, array, subsite, r, 'data_range') cf.create_dir(save_fdir) stat_df = pd.DataFrame() for m, n in sci_vars_dict.items(): for sv, vinfo in n['vars'].items(): print(vinfo['var_name']) if len(vinfo['t']) < 1: print('no variable data to plot') continue else: sv_units = vinfo['units'][0] fv = vinfo['fv'][0] t = vinfo['t'] z = vinfo['values'] y = vinfo['pressure'] # Check if the array is all NaNs if sum(np.isnan(z)) == len(z): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z[z != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: """ clean up data """ # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max = \ cf.reject_erroneous_data(r, sv, t, y, z, fv) # reject timestamps from stat analysis Dpath = '{}/{}/{}/{}/{}'.format(sDir, array, subsite, r, 'time_to_exclude') onlyfiles = [] for item in os.listdir(Dpath): if not item.startswith('.') and os.path.isfile( os.path.join(Dpath, item)): onlyfiles.append(join(Dpath, item)) dre = pd.DataFrame() for nn in onlyfiles: dr = pd.read_csv(nn) dre = dre.append(dr, ignore_index=True) drn = dre.loc[dre['Unnamed: 0'] == vinfo['var_name']] list_time = [] for itime in drn.time_to_exclude: ntime = itime.split(', ') list_time.extend(ntime) u_time_list = np.unique(list_time) if len(u_time_list) != 0: t_nospct, z_nospct, y_nospct = cf.reject_suspect_data( dtime, zpressure, ndata, u_time_list) print( '{} using {} percentile of data grouped in {} dbar segments' .format( len(zpressure) - len(z_nospct), inpercentile, zcell_size)) # reject time range from data portal file export t_portal, z_portal, y_portal = cf.reject_timestamps_dataportal( subsite, r, t_nospct, y_nospct, z_nospct) print('{} using visual inspection of data'.format( len(z_nospct) - len(z_portal), inpercentile, zcell_size)) # reject data in a depth range if zdbar is not None: y_ind = y_portal < zdbar t_array = t_portal[y_ind] y_array = y_portal[y_ind] z_array = z_portal[y_ind] else: y_ind = [] t_array = t_portal y_array = y_portal z_array = z_portal print('{} in water depth > {} dbar'.format( len(y_ind), zdbar)) if len(y_array) > 0: if m == 'common_stream_placeholder': sname = '-'.join((vinfo['var_name'], r)) else: sname = '-'.join((vinfo['var_name'], r, m)) """ create data ranges for non - pressure data only """ if 'pressure' in vinfo['var_name']: pass else: columns = ['tsec', 'dbar', str(vinfo['var_name'])] # create depth ranges min_r = int(round(min(y_array) - zcell_size)) max_r = int(round(max(y_array) + zcell_size)) ranges = list(range(min_r, max_r, zcell_size)) # group data by depth groups, d_groups = gt.group_by_depth_range( t_array, y_array, z_array, columns, ranges) print('writing data ranges for {}'.format( vinfo['var_name'])) stat_data = groups.describe()[vinfo['var_name']] stat_data.insert(loc=0, column='parameter', value=sv, allow_duplicates=False) t_deploy = deployments[0] for i in range( len(deployments))[1:len(deployments)]: t_deploy = '{}, {}'.format( t_deploy, deployments[i]) stat_data.insert(loc=1, column='deployments', value=t_deploy, allow_duplicates=False) stat_df = stat_df.append(stat_data, ignore_index=True) """ plot full time range free from errors and suspect data """ clabel = sv + " (" + sv_units + ")" ylabel = (y_name[0][0] + " (" + y_unit[0][0] + ")") title = ' '.join((r, m)) # plot non-erroneous -suspect data fig, ax, bar = pf.plot_xsection(subsite, t_array, y_array, z_array, clabel, ylabel, inpercentile=None, stdev=None) ax.set_title(title, fontsize=9) leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}]' .format( len(z) - lenfv, len(z) - lennan, len(z) - lenev, lengr, global_min, global_max) + '\n' + ('removed {} in the upper and lower {} percentile of data grouped in {} dbar segments' .format( len(zpressure) - len(z_nospct), inpercentile, zcell_size)), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) for ii in range(len(end_times)): ax.axvline(x=end_times[ii], color='b', linestyle='--', linewidth=.8) ax.text(end_times[ii], min(y_array) - 5, 'End' + str(deployments[ii]), fontsize=6, style='italic', bbox=dict( boxstyle='round', ec=(0., 0.5, 0.5), fc=(1., 1., 1.), )) fig.tight_layout() sfile = '_'.join(('data_range', sname)) pf.save_fig(save_fdir, sfile) # write stat file stat_df.to_csv('{}/{}_data_ranges.csv'.format(save_dir_stat, r), index=True, float_format='%11.6f')
def main(url_list, sDir, plot_type, start_time, end_time, deployment_num, bfiles): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) for r in rd_list: if 'ENG' not in r: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: if 'bottom_track_earth' not in splitter[-1]: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join((spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments(main_sensor, fdatasets) subsite = r.split('-')[0] array = subsite[0:2] save_dir = os.path.join(sDir, array, subsite, r, plot_type) cf.create_dir(save_dir) sname = '_'.join((r, plot_type)) sh = pd.DataFrame() deployments = [] for ii, d in enumerate(fdatasets_sel): print('\nDataset {} of {}: {}'.format(ii + 1, len(fdatasets_sel), d.split('/')[-1])) deploy = d.split('/')[-1].split('_')[0] if deployment_num: if int(deploy[-4:]) is not deployment_num: continue ds = xr.open_dataset(d, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print('No data to plot for specified time range: ({} to {})'.format(start_time, end_time)) continue try: ds_lat = ds['lat'].values except KeyError: ds_lat = None print('No latitude variable in file') try: ds_lon = ds['lon'].values except KeyError: ds_lon = None print('No longitude variable in file') if ds_lat is not None and ds_lon is not None: data = {'lat': ds_lat, 'lon': ds_lon} new_r = pd.DataFrame(data, columns=['lat', 'lon'], index=ds['time'].values) sh = sh.append(new_r) # append the deployments that are actually plotted if int(deploy[-4:]) not in deployments: deployments.append(int(deploy[-4:])) # plot data by deployment sfile = '-'.join((deploy, sname)) if array == 'CE': ttl = 'Glider Track - ' + r + ' - ' + deploy + '\nx: Mooring Locations' else: ttl = 'Glider Track - ' + r + ' - ' + deploy + '\nx: Mooring Locations' + '\n blue box: Glider Sampling Area' #fig, ax = pf.plot_profiles(ds_lon, ds_lat, ds['time'].values, ylabel, xlabel, clabel, stdev=None) plot_map(save_dir, sfile, ttl, ds_lon, ds_lat, ds['time'].values, array, bfiles, plot_type) sh = sh.resample('H').median() # resample hourly xD = sh.lon.values yD = sh.lat.values tD = sh.index.values title = 'Glider Track - ' + r + '\nDeployments: ' + str(deployments) + ' x: Mooring Locations' + '\n blue box: Glider Sampling Area' save_dir_main = os.path.join(sDir, array, subsite, r) plot_map(save_dir_main, sname, title, xD, yD, tD, array, bfiles, plot_type, add_box='yes')
def main(sDir, url_list): reviewlist = pd.read_csv( 'https://raw.githubusercontent.com/ooi-data-lab/data-review-prep/master/review_list/data_review_list.csv' ) rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) json_file_list = [] for r in rd_list: dependencies = [] print('\n{}'.format(r)) data = OrderedDict(deployments=OrderedDict()) save_dir = os.path.join(sDir, r.split('-')[0], r) cf.create_dir(save_dir) # Deployment location test deploy_loc_test = cf.deploy_location_check(r) data['location_comparison'] = deploy_loc_test for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) catalog_rms = '-'.join((r, splitter[-2], splitter[-1])) # complete the analysis by reference designator if rd_check == r: udatasets = cf.get_nc_urls([u]) # check for the OOI 1.0 datasets for review rl_filtered = reviewlist.loc[ (reviewlist['Reference Designator'] == r) & (reviewlist['status'] == 'for review')] review_deployments = rl_filtered['deploymentNumber'].tolist() review_deployments_int = [ 'deployment%04d' % int(x) for x in review_deployments ] for rev_dep in review_deployments_int: rdatasets = [s for s in udatasets if rev_dep in s] if len(rdatasets) > 0: datasets = [] for dss in rdatasets: # filter out collocated data files if catalog_rms == dss.split('/')[-1].split( '_20')[0][15:]: datasets.append(dss) else: drd = dss.split('/')[-1].split('_20')[0][15:42] if drd not in dependencies and drd != r: dependencies.append(drd) notes = [] time_ascending = '' if len(datasets) == 1: try: ds = xr.open_dataset(datasets[0], mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) fname, subsite, refdes, method, data_stream, deployment = cf.nc_attributes( datasets[0]) except OSError: print('OSError - skipping file {}'.format( datasets[0])) continue elif len(datasets) > 1: ds = xr.open_mfdataset(datasets, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) #ds = ds.chunk({'time': 100}) fname, subsite, refdes, method, data_stream, deployment = cf.nc_attributes( datasets[0]) fname = fname.split('_20')[0] notes.append('multiple deployment .nc files') # when opening multiple datasets, don't check that the timestamps are in ascending order time_ascending = 'not_tested' else: continue print('\nAnalyzing file: {}'.format(fname)) # Get info from the data review database dr_data = cf.refdes_datareview_json(refdes) stream_vars = cf.return_stream_vars(data_stream) sci_vars = cf.return_science_vars(data_stream) node = refdes.split('-')[1] if 'cspp' in data_stream or 'WFP' in node: sci_vars.append('int_ctd_pressure') # if 'FDCHP' in refdes: # remove_vars = ['fdchp_wind_x', 'fdchp_wind_y', 'fdchp_wind_z', 'fdchp_speed_of_sound_sonic', # 'fdchp_x_accel_g', 'fdchp_y_accel_g', 'fdchp_z_accel_g'] # rv_regex = re.compile('|'.join(remove_vars)) # rv_sci_vars = [nn for nn in sci_vars if not rv_regex.search(nn)] # sci_vars = rv_sci_vars deploy_info = get_deployment_information( dr_data, int(deployment[-4:])) # Grab deployment Variables deploy_start = str(deploy_info['start_date']) deploy_stop = str(deploy_info['stop_date']) deploy_lon = deploy_info['longitude'] deploy_lat = deploy_info['latitude'] deploy_depth = deploy_info['deployment_depth'] # Calculate days deployed if deploy_stop != 'None': r_deploy_start = pd.to_datetime( deploy_start).replace(hour=0, minute=0, second=0) if deploy_stop.split('T')[1] == '00:00:00': r_deploy_stop = pd.to_datetime(deploy_stop) else: r_deploy_stop = (pd.to_datetime(deploy_stop) + timedelta(days=1)).replace( hour=0, minute=0, second=0) n_days_deployed = (r_deploy_stop - r_deploy_start).days else: n_days_deployed = None # Add reference designator to dictionary try: data['refdes'] except KeyError: data['refdes'] = refdes deployments = data['deployments'].keys() data_start = pd.to_datetime(min( ds['time'].values)).strftime('%Y-%m-%dT%H:%M:%S') data_stop = pd.to_datetime(max( ds['time'].values)).strftime('%Y-%m-%dT%H:%M:%S') # Add deployment and info to dictionary and initialize delivery method sub-dictionary if deployment not in deployments: data['deployments'][deployment] = OrderedDict( deploy_start=deploy_start, deploy_stop=deploy_stop, n_days_deployed=n_days_deployed, lon=deploy_lon, lat=deploy_lat, deploy_depth=deploy_depth, method=OrderedDict()) # Add delivery methods to dictionary and initialize stream sub-dictionary methods = data['deployments'][deployment][ 'method'].keys() if method not in methods: data['deployments'][deployment]['method'][ method] = OrderedDict(stream=OrderedDict()) # Add streams to dictionary and initialize file sub-dictionary streams = data['deployments'][deployment]['method'][ method]['stream'].keys() if data_stream not in streams: data['deployments'][deployment]['method'][method][ 'stream'][data_stream] = OrderedDict( file=OrderedDict()) # Get a list of data gaps >1 day time_df = pd.DataFrame(ds['time'].values, columns=['time']) gap_list = cf.timestamp_gap_test(time_df) # Calculate the sampling rate to the nearest second time_df['diff'] = time_df['time'].diff().astype( 'timedelta64[s]') rates_df = time_df.groupby(['diff']).agg(['count']) n_diff_calc = len(time_df) - 1 rates = dict(n_unique_rates=len(rates_df), common_sampling_rates=dict()) for i, row in rates_df.iterrows(): percent = (float(row['time']['count']) / float(n_diff_calc)) if percent > 0.1: rates['common_sampling_rates'].update( {int(i): '{:.2%}'.format(percent)}) sampling_rt_sec = None for k, v in rates['common_sampling_rates'].items(): if float(v.strip('%')) > 50.00: sampling_rt_sec = k if not sampling_rt_sec: sampling_rt_sec = 'no consistent sampling rate: {}'.format( rates['common_sampling_rates']) # Check that the timestamps in the file are unique time = ds['time'] len_time = time.__len__() len_time_unique = np.unique(time).__len__() if len_time == len_time_unique: time_test = 'pass' else: time_test = 'fail' # Check that the timestamps in the file are in ascending order if time_ascending != 'not_tested': # convert time to number time_in = [ dt.datetime.utcfromtimestamp( np.datetime64(x).astype('O') / 1e9) for x in ds['time'].values ] time_data = nc.date2num( time_in, 'seconds since 1900-01-01') # Create a list of True or False by iterating through the array of time and checking # if every time stamp is increasing result = [(time_data[k + 1] - time_data[k]) > 0 for k in range(len(time_data) - 1)] # Print outcome of the iteration with the list of indices when time is not increasing if result.count(True) == len(time) - 1: time_ascending = 'pass' else: ind_fail = { k: time_in[k] for k, v in enumerate(result) if v is False } time_ascending = 'fail: {}'.format(ind_fail) # Count the number of days for which there is at least 1 timestamp n_days = len( np.unique(time.values.astype('datetime64[D]'))) # Compare variables in file to variables in Data Review Database ds_variables = list(ds.data_vars.keys()) + list( ds.coords.keys()) #ds_variables = [k for k in ds] ds_variables = eliminate_common_variables(ds_variables) ds_variables = [ x for x in ds_variables if 'qc' not in x ] [_, unmatch1] = compare_lists(stream_vars, ds_variables) [_, unmatch2] = compare_lists(ds_variables, stream_vars) # Check deployment pressure from asset management against pressure variable in file press = pf.pressure_var(ds, list(ds.coords.keys())) if press is None: press = pf.pressure_var(ds, list(ds.data_vars.keys())) # calculate mean pressure from data, excluding outliers +/- 3 SD try: pressure = ds[press] num_dims = len(pressure.dims) if len(pressure) > 1: # if the pressure variable is an array of all zeros (as in the case of pressure_depth # for OPTAAs on surface piercing profilers if (len(np.unique(pressure)) == 1) & ( np.unique(pressure)[0] == 0.0): try: pressure = ds['int_ctd_pressure'] press = 'int_ctd_pressure' except KeyError: pressure = pressure # reject NaNs p_nonan = pressure.values[~np.isnan(pressure. values)] # reject fill values p_nonan_nofv = p_nonan[ p_nonan != pressure._FillValue] # reject data outside of global ranges [pg_min, pg_max] = cf.get_global_ranges(r, press) if pg_min is not None and pg_max is not None: pgr_ind = cf.reject_global_ranges( p_nonan_nofv, pg_min, pg_max) p_nonan_nofv_gr = p_nonan_nofv[pgr_ind] else: p_nonan_nofv_gr = p_nonan_nofv if (len(p_nonan_nofv_gr) > 0) and (num_dims == 1): [ press_outliers, pressure_mean, _, pressure_max, _, _ ] = cf.variable_statistics( p_nonan_nofv_gr, 3) pressure_mean = round(pressure_mean, 2) pressure_max = round(pressure_max, 2) elif (len(p_nonan_nofv_gr) > 0) and (num_dims > 1): print('variable has more than 1 dimension') press_outliers = 'not calculated: variable has more than 1 dimension' pressure_mean = round( np.nanmean(p_nonan_nofv_gr), 2) pressure_max = round( np.nanmax(p_nonan_nofv_gr), 2) else: press_outliers = None pressure_mean = None pressure_max = None if len(pressure) > 0 and len(p_nonan) == 0: notes.append( 'Pressure variable all NaNs') elif len(pressure) > 0 and len( p_nonan) > 0 and len( p_nonan_nofv) == 0: notes.append( 'Pressure variable all fill values' ) elif len(pressure) > 0 and len( p_nonan) > 0 and len( p_nonan_nofv) > 0 and len( p_nonan_nofv_gr) == 0: notes.append( 'Pressure variable outside of global ranges' ) else: # if there is only 1 data point press_outliers = 0 pressure_mean = round( ds[press].values.tolist()[0], 2) pressure_max = round( ds[press].values.tolist()[0], 2) try: pressure_units = pressure.units except AttributeError: pressure_units = 'no units attribute for pressure' if pressure_mean: if ('WFP' in node) or ('MOAS' in subsite) or ( 'SP' in node): pressure_compare = int(round(pressure_max)) else: pressure_compare = int( round(pressure_mean)) if pressure_units == '0.001 dbar': pressure_max = round((pressure_max / 1000), 2) pressure_mean = round( (pressure_mean / 1000), 2) pressure_compare = round( (pressure_compare / 1000), 2) notes.append( 'Pressure converted from 0.001 dbar to dbar for pressure comparison' ) elif pressure_units == 'daPa': pressure_max = round((pressure_max / 1000), 2) pressure_mean = round( (pressure_mean / 1000), 2) pressure_compare = round( (pressure_compare / 1000), 2) notes.append( 'Pressure converted from daPa to dbar for pressure comparison' ) else: pressure_compare = None if (not deploy_depth) or (not pressure_mean): pressure_diff = None else: pressure_diff = pressure_compare - deploy_depth except KeyError: press = 'no seawater pressure in file' pressure_diff = None pressure_mean = None pressure_max = None pressure_compare = None press_outliers = None pressure_units = None # Add files and info to dictionary filenames = data['deployments'][deployment]['method'][ method]['stream'][data_stream]['file'].keys() if fname not in filenames: data['deployments'][deployment]['method'][method][ 'stream'][data_stream]['file'][ fname] = OrderedDict( file_downloaded=pd.to_datetime( splitter[0][0:15]).strftime( '%Y-%m-%dT%H:%M:%S'), file_coordinates=list( ds.coords.keys()), sampling_rate_seconds=sampling_rt_sec, sampling_rate_details=rates, data_start=data_start, data_stop=data_stop, time_gaps=gap_list, unique_timestamps=time_test, n_timestamps=len_time, n_days=n_days, notes=notes, ascending_timestamps=time_ascending, pressure_comparison=dict( pressure_mean=pressure_mean, units=pressure_units, num_outliers=press_outliers, diff=pressure_diff, pressure_max=pressure_max, variable=press, pressure_compare=pressure_compare), vars_in_file=ds_variables, vars_not_in_file=[ x for x in unmatch1 if 'time' not in x ], vars_not_in_db=unmatch2, sci_var_stats=OrderedDict()) # calculate statistics for science variables, excluding outliers +/- 5 SD for sv in sci_vars: if sv != 't_max': # for ADCP if sv != 'wavss_a_buoymotion_time': print(sv) try: var = ds[sv] # need to round SPKIR values to 1 decimal place to match the global ranges. # otherwise, values that round to zero (e.g. 1.55294e-05) will be excluded by # the global range test # if 'spkir' in sv: # vD = np.round(var.values, 1) # else: # vD = var.values vD = var.values if 'timedelta' not in str( var.values.dtype): # for OPTAA wavelengths: when multiple files are opened with xr.open_mfdataset # xarray automatically forces all variables to have the same number of # dimensions. So in this case wavelength_a and wavelength_c have 1 dimension # in the individual files, so I'm forcing the analysis to treat them like # they have 1 dimension (when there are multiple files for 1 deployment) if sv == 'wavelength_a' or sv == 'wavelength_c': [g_min, g_max] = cf.get_global_ranges( r, sv) vnum_dims = len(var.dims) if vnum_dims == 1: n_all = len(var) mean = list(vD) else: vnum_dims = 1 n_all = len(vD[0]) mean = list(vD[0]) num_outliers = None vmin = None vmax = None sd = None n_stats = 'not calculated' var_units = var.units n_nan = None n_fv = None n_grange = 'no global ranges' fv = var._FillValue else: vnum_dims = len(var.dims) if vnum_dims > 2: print( 'variable has more than 2 dimensions' ) num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 'variable has more than 2 dimensions' var_units = var.units n_nan = None n_fv = None n_grange = None fv = None n_all = None else: if vnum_dims > 1: n_all = [ len(vD), len(vD.flatten()) ] else: n_all = len(vD) n_nan = int( np.sum(np.isnan(vD))) fv = var._FillValue var_nofv = var.where( var != fv) n_fv = int( np.sum( np.isnan( var_nofv.values ))) - n_nan try: var_units = var.units except AttributeError: var_units = 'no_units' [g_min, g_max ] = cf.get_global_ranges( r, sv) if list( np.unique( np.isnan( var_nofv)) ) != [True]: # reject data outside of global ranges if g_min is not None and g_max is not None: var_gr = var_nofv.where( (var_nofv >= g_min) & (var_nofv <= g_max)) n_grange = int( np.sum( np.isnan( var_gr) ) - n_fv - n_nan) else: n_grange = 'no global ranges' var_gr = var_nofv if list( np.unique( np.isnan( var_gr) )) != [True]: if sv == 'spkir_abj_cspp_downwelling_vector': # don't remove outliers from dataset [ num_outliers, mean, vmin, vmax, sd, n_stats ] = cf.variable_statistics_spkir( var_gr) else: if vnum_dims > 1: var_gr = var_gr.values.flatten( ) # drop nans before calculating stats var_gr = var_gr[ ~np.isnan( var_gr )] [ num_outliers, mean, vmin, vmax, sd, n_stats ] = cf.variable_statistics( var_gr, 5) else: num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 0 n_grange = None else: num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 0 n_grange = None except KeyError: if sv == 'int_ctd_pressure': continue else: num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 'variable not found in file' var_units = None n_nan = None n_fv = None fv = None n_grange = None n_all = None if vnum_dims > 1: sv = '{} (dims: {})'.format( sv, list(var.dims)) else: sv = sv if 'timedelta' not in str( var.values.dtype): data['deployments'][deployment][ 'method'][method]['stream'][ data_stream]['file'][fname][ 'sci_var_stats'][sv] = dict( n_outliers=num_outliers, mean=mean, min=vmin, max=vmax, stdev=sd, n_stats=n_stats, units=var_units, n_nans=n_nan, n_fillvalues=n_fv, fill_value=str(fv), global_ranges=[ g_min, g_max ], n_grange=n_grange, n_all=n_all) sfile = os.path.join(save_dir, '{}-file_analysis.json'.format(r)) with open(sfile, 'w') as outfile: json.dump(data, outfile) depfile = os.path.join(save_dir, '{}-dependencies.txt'.format(r)) with open(depfile, 'w') as depf: depf.write(str(dependencies)) json_file_list.append(str(sfile)) return json_file_list
def main(sDir, url_list, start_time, end_time, preferred_only): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'PRESF' in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) for ud in udatasets: # filter out collocated data files if 'PRESF' in ud.split('/')[-1]: datasets.append(ud) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets fdatasets = np.unique(fdatasets).tolist() for fd in fdatasets: ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd) sci_vars = cf.return_science_vars(stream) print('\nPlotting {} {}'.format(r, deployment)) array = subsite[0:2] filename = '_'.join(fname.split('_')[:-1]) save_dir = os.path.join(sDir, array, subsite, refdes, 'timeseries_plots', deployment) cf.create_dir(save_dir) tm = ds['time'].values t0 = pd.to_datetime(tm.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(tm.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) for var in sci_vars: print(var) if var != 'id': #if var == 'presf_wave_burst_pressure': y = ds[var] fv = y._FillValue if len(y.dims) == 1: # Check if the array is all NaNs if sum(np.isnan(y.values)) == len(y.values): print('Array of all NaNs - skipping plot.') # Check if the array is all fill values elif len(y[y != fv]) == 0: print('Array of all fill values - skipping plot.') else: # reject fill values ind = y.values != fv t = tm[ind] y = y[ind] # Plot all data fig, ax = pf.plot_timeseries(t, y, y.name, stdev=None) ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, y.name, t0[:10])) pf.save_fig(save_dir, sfile) # Plot data with outliers removed fig, ax = pf.plot_timeseries(t, y, y.name, stdev=5) ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join( (filename, y.name, t0[:10])) + '_rmoutliers' pf.save_fig(save_dir, sfile) else: v = y.values.T n_nan = np.sum(np.isnan(v)) # convert fill values to nans try: v[v == fv] = np.nan except ValueError: v = v.astype(float) v[v == fv] = np.nan n_fv = np.sum(np.isnan(v)) - n_nan # plot before global ranges are removed fig, ax = pf.plot_presf_2d(tm, v, y.name, y.units) ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9) sfile = '-'.join((filename, var, t0[:10])) pf.save_fig(save_dir, sfile) # reject data outside of global ranges [g_min, g_max] = cf.get_global_ranges(r, var) if g_min is not None and g_max is not None: v[v < g_min] = np.nan v[v > g_max] = np.nan n_grange = np.sum(np.isnan(v)) - n_fv - n_nan if n_grange > 0: # don't plot if the array is all nans if len(np.unique( np.isnan(v))) == 1 and np.unique( np.isnan(v))[0] == True: continue else: # plot after global ranges are removed fig, ax = pf.plot_presf_2d( tm, v, y.name, y.units) title2 = 'removed: {} global ranges [{}, {}]'.format( n_grange, g_min, g_max) ax.set_title((title + '\n' + t0 + ' - ' + t1 + '\n' + title2), fontsize=9) sfile = '-'.join( (filename, var, t0[:10], 'rmgr')) pf.save_fig(save_dir, sfile)
def main(sDir, url_list): # get summary lists of reference designators and delivery methods rd_list = [] rdm_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) rdm = '-'.join((rd, elements[5])) if rd not in rd_list: rd_list.append(rd) if rdm not in rdm_list: rdm_list.append(rdm) json_file_list = [] for r in rd_list: rdm_filtered = [k for k in rdm_list if r in k] dinfo = {} save_dir = os.path.join(sDir, r.split('-')[0], r) cf.create_dir(save_dir) sfile = os.path.join(save_dir, '{}-method_comparison.json'.format(r)) if len(rdm_filtered) == 1: print('Only one delivery method provided - no comparison.') dinfo['note'] = 'no comparison - only one delivery method provided' with open(sfile, 'w') as outfile: json.dump(dinfo, outfile) json_file_list.append(str(sfile)) continue elif len(rdm_filtered) > 1 & len(rdm_filtered) <= 3: print('\nComparing data from different methods for: {}'.format(r)) for i in range(len(rdm_filtered)): urls = [x for x in url_list if rdm_filtered[i] in x] for u in urls: splitter = u.split('/')[-2].split('-') catalog_rms = '-'.join((r, splitter[-2], splitter[-1])) udatasets = cf.get_nc_urls([u]) idatasets = [] for dss in udatasets: # filter out collocated data files if catalog_rms == dss.split('/')[-1].split( '_20')[0][15:]: idatasets.append(dss) deployments = [ str(k.split('/')[-1][0:14]) for k in idatasets ] udeploy = np.unique(deployments).tolist() for ud in udeploy: rdatasets = [s for s in idatasets if ud in s] file_ms_lst = [] for dataset in rdatasets: splt = dataset.split('/')[-1].split( '_20')[0].split('-') file_ms_lst.append('-'.join((splt[-2], splt[-1]))) file_ms = np.unique(file_ms_lst).tolist()[0] try: dinfo[file_ms] except KeyError: dinfo[file_ms] = {} dinfo[file_ms].update({ud: rdatasets}) else: print( 'More than 3 methods provided. Please provide fewer datasets for analysis.' ) continue dinfo_df = pd.DataFrame(dinfo) umethods = [] ustreams = [] for k in dinfo.keys(): umethods.append(k.split('-')[0]) ustreams.append(k.split('-')[1]) if len(np.unique(ustreams)) > len( np.unique(umethods) ): # if there is more than 1 stream per delivery method mdict = dict() method_stream_df = cf.stream_word_check(dinfo) for cs in (np.unique( method_stream_df['stream_name_compare'])).tolist(): print('Common stream_name: {}'.format(cs)) method_stream_list = [] for row in method_stream_df.itertuples(): index, method, stream_name, stream_name_compare = row if stream_name_compare == cs: method_stream_list.append('-'.join( (method, stream_name))) dinfo_df_filtered = dinfo_df[method_stream_list] summary_dict = compare_data(dinfo_df_filtered) # merge dictionaries for all streams for one reference designator mdict = merge_two_dicts(mdict, summary_dict) with open(sfile, 'w') as outfile: json.dump(mdict, outfile) else: summary_dict = compare_data(dinfo_df) with open(sfile, 'w') as outfile: json.dump(summary_dict, outfile) json_file_list.append(str(sfile)) return json_file_list
def main(url_list, sDir, deployment_num, start_time, end_time, preferred_only, n_std, surface_params, depth_params): rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list and 'ENG' not in rd: rd_list.append(rd) for r in rd_list: print('\n{}'.format(r)) datasets = [] for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets_sel = cf.filter_collocated_instruments( main_sensor, fdatasets) for fd in fdatasets_sel: part_d = fd.split('/')[-1] print('\n{}'.format(part_d)) ds = xr.open_dataset(fd, mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd) array = subsite[0:2] sci_vars = cf.return_science_vars(stream) if 'CE05MOAS' in r or 'CP05MOAS' in r: # for coastal gliders, get m_water_depth for bathymetry eng = '-'.join((r.split('-')[0], r.split('-')[1], '00-ENG000000', method, 'glider_eng')) eng_url = [s for s in url_list if eng in s] if len(eng_url) == 1: eng_datasets = cf.get_nc_urls(eng_url) # filter out collocated datasets eng_dataset = [ j for j in eng_datasets if (eng in j.split('/')[-1] and deployment in j.split('/')[-1]) ] if len(eng_dataset) > 0: ds_eng = xr.open_dataset(eng_dataset[0], mask_and_scale=False) t_eng = ds_eng['time'].values m_water_depth = ds_eng['m_water_depth'].values # m_altimeter_status = 0 means a good reading (not nan or -1) eng_ind = ds_eng['m_altimeter_status'].values == 0 m_water_depth = m_water_depth[eng_ind] t_eng = t_eng[eng_ind] else: print('No engineering file for deployment {}'.format( deployment)) m_water_depth = None t_eng = None else: m_water_depth = None t_eng = None else: m_water_depth = None t_eng = None if deployment_num is not None: if int(deployment.split('0')[-1]) is not deployment_num: print(type(int(deployment.split('0')[-1])), type(deployment_num)) continue if start_time is not None and end_time is not None: ds = ds.sel(time=slice(start_time, end_time)) if len(ds['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue stime = start_time.strftime('%Y-%m-%d') etime = end_time.strftime('%Y-%m-%d') ext = stime + 'to' + etime # .join((ds0_method, ds1_method save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment, ext) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment, ext) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment, ext) else: save_dir_profile = os.path.join(sDir, array, subsite, refdes, 'profile_plots', deployment) save_dir_xsection = os.path.join(sDir, array, subsite, refdes, 'xsection_plots', deployment) save_dir_4d = os.path.join(sDir, array, subsite, refdes, 'xsection_plots_4d', deployment) tm = ds['time'].values try: ds_lat = ds['lat'].values except KeyError: ds_lat = None print('No latitude variable in file') try: ds_lon = ds['lon'].values except KeyError: ds_lon = None print('No longitude variable in file') # get pressure variable y, y_units, press = cf.add_pressure_to_dictionary_of_sci_vars(ds) for sv in sci_vars: print(sv) if 'pressure' not in sv: z = ds[sv].values fv = ds[sv]._FillValue sv_units = ds[sv].units # Check if the array is all NaNs if sum(np.isnan(z)) == len(z): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z[z != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: # reject erroneous data dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max, lat, lon = \ cf.reject_erroneous_data(r, sv, tm, y, z, fv, ds_lat, ds_lon) # get rid of 0.0 data if 'CTD' in r: ind = zpressure > 0.0 else: ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = dtime[ind] zpressure = zpressure[ind] ndata = ndata[ind] if ds_lat is not None and ds_lon is not None: lat = lat[ind] lon = lon[ind] else: lat = None lon = None t0 = pd.to_datetime( dtime.min()).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime( dtime.max()).strftime('%Y-%m-%dT%H:%M:%S') title = ' '.join((deployment, refdes, method)) + '\n' + t0 + ' to ' + t1 # reject time range from data portal file export t_portal, z_portal, y_portal, lat_portal, lon_portal = \ cf.reject_timestamps_dataportal(subsite, r, dtime, zpressure, ndata, lat, lon) print( 'removed {} data points using visual inspection of data' .format(len(ndata) - len(z_portal))) # create data groups columns = ['tsec', 'dbar', str(sv)] # min_r = int(round(min(y_portal) - zcell_size)) # max_r = int(round(max(y_portal) + zcell_size)) # ranges = list(range(min_r, max_r, zcell_size)) #ranges = [0, 10, 20, 30, 40, 50, 60, 70, 80, 200] range1 = list( range(surface_params[0], surface_params[1], surface_params[2])) range2 = list( range(depth_params[0], depth_params[1] + depth_params[2], depth_params[2])) ranges = range1 + range2 groups, d_groups = gt.group_by_depth_range( t_portal, y_portal, z_portal, columns, ranges) if 'scatter' in sv: n_std = None # to use percentile else: n_std = n_std # get percentile analysis for printing on the profile plot inpercentile = [surface_params[3]] * len( range1) + [depth_params[3]] * len(range2) n_std = [surface_params[3]] * len( range1) + [depth_params[3]] * len(range2) y_plt, n_med, n_min, n_max, n0_std, n1_std, l_arr, time_ex = reject_timestamps_in_groups( groups, d_groups, n_std, inpercentile) """ Plot all data """ if len(tm) > 0: cf.create_dir(save_dir_profile) cf.create_dir(save_dir_xsection) sname = '-'.join((r, method, sv)) sfileall = '_'.join(('all_data', sname)) ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" clabel = 'Time' fig, ax = pf.plot_profiles(z, y, tm, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_profile, sfileall) ''' xsection plot ''' clabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" fig, ax, bar = pf.plot_xsection(subsite, tm, y, z, clabel, ylabel, t_eng, m_water_depth, inpercentile=None, stdev=None) ax.set_title(title, fontsize=9) fig.tight_layout() pf.save_fig(save_dir_xsection, sfileall) """ Plot cleaned-up data """ if len(dtime) > 0: sfile = '_'.join(('rm_erroneous_data', sname)) ''' profile plot ''' xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" clabel = 'Time' fig, ax = pf.plot_profiles(z_portal, y_portal, t_portal, ylabel, xlabel, clabel, stdev=None) ax.set_title(title, fontsize=9) ax.plot(n_med, y_plt, '.k') ax.fill_betweenx(y_plt, n0_std, n1_std, color='m', alpha=0.2) leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} zeros'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nexcluded {} suspect data points when inspected visually' .format(len(ndata) - len(z_portal)) + '\n(black) data median in {} dbar segments (break at {} dbar)' .format([surface_params[2], depth_params[2]], depth_params[0]) + '\n(magenta) upper and lower {} percentile envelope in {} dbar segments' .format( [surface_params[3], depth_params[3]], [surface_params[2], depth_params[2]]), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_profile, sfile) ''' xsection plot ''' clabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" # plot non-erroneous data fig, ax, bar = pf.plot_xsection(subsite, t_portal, y_portal, z_portal, clabel, ylabel, t_eng, m_water_depth, inpercentile=None, stdev=None) ax.set_title(title, fontsize=9) leg_text = ( 'removed {} fill values, {} NaNs, {} Extreme Values (1e7), {} Global ranges [{} - {}], ' '{} zeros'.format(lenfv, lennan, lenev, lengr, global_min, global_max, lenzero) + '\nexcluded {} suspect data points when inspected visually' .format(len(ndata) - len(z_portal)), ) ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6) fig.tight_layout() pf.save_fig(save_dir_xsection, sfile) ''' 4D plot for gliders only ''' if 'MOAS' in r: if ds_lat is not None and ds_lon is not None: cf.create_dir(save_dir_4d) clabel = sv + " (" + sv_units + ")" zlabel = press[0] + " (" + y_units[0] + ")" fig = plt.figure() ax = fig.add_subplot(111, projection='3d') sct = ax.scatter(lon_portal, lat_portal, y_portal, c=z_portal, s=2) cbar = plt.colorbar(sct, label=clabel, extend='both') cbar.ax.tick_params(labelsize=8) ax.invert_zaxis() ax.view_init(25, 32) ax.invert_xaxis() ax.invert_yaxis() ax.set_zlabel(zlabel, fontsize=9) ax.set_ylabel('Latitude', fontsize=9) ax.set_xlabel('Longitude', fontsize=9) ax.set_title(title, fontsize=9) pf.save_fig(save_dir_4d, sfile)
def main(url_list, sDir, stime, etime): if len(url_list) != 2: print('Please provide 2 reference designators for plotting') else: uu0 = url_list[0] uu1 = url_list[1] rd0 = uu0.split('/')[-2][20:47] rd1 = uu1.split('/')[-2][20:47] array = rd0[0:2] inst = rd0.split('-')[-1] datasets0 = [] datasets1 = [] for i in range(len(url_list)): udatasets = cf.get_nc_urls([url_list[i]]) if i == 0: datasets0.append(udatasets) else: datasets1.append(udatasets) datasets0 = list(itertools.chain(*datasets0)) datasets1 = list(itertools.chain(*datasets1)) main_sensor0 = rd0.split('-')[-1] main_sensor1 = rd1.split('-')[-1] fdatasets0_sel = cf.filter_collocated_instruments( main_sensor0, datasets0) fdatasets1_sel = cf.filter_collocated_instruments( main_sensor1, datasets1) deployments = [ dd.split('/')[-1].split('_')[0] for dd in fdatasets0_sel ] for d in deployments: fd0 = [x for x in fdatasets0_sel if d in x] fd1 = [x for x in fdatasets1_sel if d in x] ds0 = xr.open_dataset(fd0[0], mask_and_scale=False) ds0 = ds0.swap_dims({'obs': 'time'}) ds1 = xr.open_dataset(fd1[0], mask_and_scale=False) ds1 = ds1.swap_dims({'obs': 'time'}) if stime is not None and etime is not None: ds0 = ds0.sel(time=slice(stime, etime)) ds1 = ds1.sel(time=slice(stime, etime)) if len(ds0['time'].values) == 0: print( 'No data to plot for specified time range: ({} to {})'. format(start_time, end_time)) continue fname, subsite, refdes, method, stream, deployment = cf.nc_attributes( fd0[0]) sci_vars = cf.return_science_vars(stream) save_dir_profile = os.path.join(sDir, array, subsite, inst, 'profile_plots', deployment) cf.create_dir(save_dir_profile) # get pressure variable pvarname, y1, y_units, press, y_fillvalue = cf.add_pressure_to_dictionary_of_sci_vars( ds0) for sv in sci_vars: print('') print(sv) if 'pressure' not in sv: fig, ax = plt.subplots() plt.margins(y=.08, x=.02) plt.grid() title = ' '.join((deployment, subsite, inst, method)) sname = '-'.join((subsite, inst, method, sv)) for i in range(len(url_list)): if i == 0: ds = ds0 else: ds = ds1 t = ds['time'].values zpressure = ds[pvarname].values z1 = ds[sv].values fv = ds[sv]._FillValue sv_units = ds[sv].units # Check if the array is all NaNs if sum(np.isnan(z1)) == len(z1): print('Array of all NaNs - skipping plot.') continue # Check if the array is all fill values elif len(z1[z1 != fv]) == 0: print('Array of all fill values - skipping plot.') continue else: # get rid of 0.0 data if sv == 'salinity': ind = z1 > 1 elif sv == 'density': ind = z1 > 1000 elif sv == 'conductivity': ind = z1 > 0.1 elif sv == 'dissolved_oxygen': ind = z1 > 160 elif sv == 'estimated_oxygen_concentration': ind = z1 > 200 else: ind = z1 > 0 # if sv == 'sci_flbbcd_chlor_units': # ind = ndata < 7.5 # elif sv == 'sci_flbbcd_cdom_units': # ind = ndata < 25 # else: # ind = ndata > 0.0 # if 'CTD' in r: # ind = zpressure > 0.0 # else: # ind = ndata > 0.0 lenzero = np.sum(~ind) dtime = t[ind] zpressure = zpressure[ind] zdata = z1[ind] if len(dtime) > 0: ax.scatter(zdata, zpressure, s=2, edgecolor='None') xlabel = sv + " (" + sv_units + ")" ylabel = press[0] + " (" + y_units[0] + ")" ax.invert_yaxis() # plt.xlim([-0.5, 0.5]) ax.set_xlabel(xlabel, fontsize=9) ax.set_ylabel(ylabel, fontsize=9) ax.set_title(title + '\nWFP02 (blue) & WFP03 (orange)', fontsize=9) fig.tight_layout() pf.save_fig(save_dir_profile, sname)
def main(sDir, url_list, preferred_only): rd_list = [] ms_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) ms = uu.split(rd + '-')[1].split('/')[0] if rd not in rd_list: rd_list.append(rd) if ms not in ms_list: ms_list.append(ms) for r in rd_list: print('\n{}'.format(r)) subsite = r.split('-')[0] array = subsite[0:2] # filter datasets datasets = [] for u in url_list: print(u) splitter = u.split('/')[-2].split('-') rd_check = '-'.join( (splitter[1], splitter[2], splitter[3], splitter[4])) if rd_check == r: udatasets = cf.get_nc_urls([u]) datasets.append(udatasets) datasets = list(itertools.chain(*datasets)) fdatasets = [] if preferred_only == 'yes': # get the preferred stream information ps_df, n_streams = cf.get_preferred_stream_info(r) for index, row in ps_df.iterrows(): for ii in range(n_streams): try: rms = '-'.join((r, row[ii])) except TypeError: continue for dd in datasets: spl = dd.split('/')[-2].split('-') catalog_rms = '-'.join( (spl[1], spl[2], spl[3], spl[4], spl[5], spl[6])) fdeploy = dd.split('/')[-1].split('_')[0] if rms == catalog_rms and fdeploy == row['deployment']: fdatasets.append(dd) else: fdatasets = datasets main_sensor = r.split('-')[-1] fdatasets = cf.filter_collocated_instruments(main_sensor, fdatasets) # ps_df, n_streams = cf.get_preferred_stream_info(r) # get end times of deployments dr_data = cf.refdes_datareview_json(r) deployments = [] end_times = [] for index, row in ps_df.iterrows(): deploy = row['deployment'] deploy_info = get_deployment_information(dr_data, int(deploy[-4:])) deployments.append(int(deploy[-4:])) end_times.append(pd.to_datetime(deploy_info['stop_date'])) # # filter datasets # datasets = [] # for u in url_list: # print(u) # splitter = u.split('/')[-2].split('-') # rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) # if rd_check == r: # udatasets = cf.get_nc_urls([u]) # datasets.append(udatasets) # datasets = list(itertools.chain(*datasets)) # main_sensor = r.split('-')[-1] # fdatasets = cf.filter_collocated_instruments(main_sensor, datasets) # fdatasets = cf.filter_other_streams(r, ms_list, fdatasets) methodstream = [] for f in fdatasets: methodstream.append('-'.join((f.split('/')[-2].split('-')[-2], f.split('/')[-2].split('-')[-1]))) ms_dict = save_dir_path(ms_list) for ms in np.unique(methodstream): fdatasets_sel = [x for x in fdatasets if ms in x] check_ms = ms.split('-')[1] if 'recovered' in check_ms: check_ms = check_ms.split('_recovered')[0] if ms_dict['ms_count'][ms_dict['ms_unique'] == ms.split('-') [0]] == 1: save_dir = os.path.join(sDir, array, subsite, r, 'timeseries_yearly_plot', ms.split('-')[0]) else: save_dir = os.path.join(sDir, array, subsite, r, 'timeseries_yearly_plot', ms.split('-')[0], check_ms) cf.create_dir(save_dir) stream_sci_vars_dict = dict() for x in dr_data['instrument']['data_streams']: dr_ms = '-'.join((x['method'], x['stream_name'])) if ms == dr_ms: stream_sci_vars_dict[dr_ms] = dict(vars=dict()) sci_vars = dict() for y in x['stream']['parameters']: if y['data_product_type'] == 'Science Data': sci_vars.update( {y['name']: dict(db_units=y['unit'])}) if len(sci_vars) > 0: stream_sci_vars_dict[dr_ms]['vars'] = sci_vars sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict, ms) print('\nAppending data from files: {}'.format(ms)) for fd in fdatasets_sel: ds = xr.open_dataset(fd, mask_and_scale=False) print(fd) for var in list(sci_vars_dict[ms]['vars'].keys()): sh = sci_vars_dict[ms]['vars'][var] try: ds[var] print(var) deployment_num = np.unique(ds['deployment'].values)[0] sh['deployments'] = np.append(sh['deployments'], deployment_num) if ds[var].units == sh['db_units']: if ds[var]._FillValue not in sh['fv']: sh['fv'].append(ds[var]._FillValue) if ds[var].units not in sh['units']: sh['units'].append(ds[var].units) tD = ds['time'].values varD = ds[var].values sh['t'] = np.append(sh['t'], tD) sh['values'] = np.append(sh['values'], varD) except KeyError: print('KeyError: ', var) print('\nPlotting data') for m, n in sci_vars_dict.items(): for sv, vinfo in n['vars'].items(): print(sv) if len(vinfo['t']) < 1: print('no variable data to plot') else: sv_units = vinfo['units'][0] deployments_num = vinfo['deployments'] fv = vinfo['fv'][0] t0 = pd.to_datetime(min( vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') t1 = pd.to_datetime(max( vinfo['t'])).strftime('%Y-%m-%dT%H:%M:%S') x = vinfo['t'] y = vinfo['values'] # reject NaNs nan_ind = ~np.isnan(y) x_nonan = x[nan_ind] y_nonan = y[nan_ind] # reject fill values fv_ind = y_nonan != vinfo['fv'][0] x_nonan_nofv = x_nonan[fv_ind] y_nonan_nofv = y_nonan[fv_ind] # reject extreme values Ev_ind = cf.reject_extreme_values(y_nonan_nofv) y_nonan_nofv_nE = y_nonan_nofv[Ev_ind] x_nonan_nofv_nE = x_nonan_nofv[Ev_ind] # reject values outside global ranges: global_min, global_max = cf.get_global_ranges(r, sv) print('global ranges: ', global_min, global_max) if global_min and global_max: gr_ind = cf.reject_global_ranges( y_nonan_nofv_nE, global_min, global_max) y_nonan_nofv_nE_nogr = y_nonan_nofv_nE[gr_ind] x_nonan_nofv_nE_nogr = x_nonan_nofv_nE[gr_ind] else: y_nonan_nofv_nE_nogr = y_nonan_nofv_nE x_nonan_nofv_nE_nogr = x_nonan_nofv_nE # check array length if len(y_nonan_nofv_nE_nogr) > 0: if m == 'common_stream_placeholder': sname = '-'.join((r, sv)) print(var, 'empty array') else: sname = '-'.join((r, m, sv)) # group data by year groups, g_data = gt.group_by_time_range( x_nonan_nofv_nE_nogr, y_nonan_nofv_nE_nogr, 'A') # create bins # groups_min = min(groups.describe()['DO']['min']) # lower_bound = int(round(groups_min)) # groups_max = max(groups.describe()['DO']['max']) # if groups_max < 1: # upper_bound = 1 # step_bound = 1 # else: # upper_bound = int(round(groups_max + (groups_max / 50))) # step_bound = int(round((groups_max - groups_min) / 10)) # # if step_bound == 0: # step_bound += 1 # # if (upper_bound - lower_bound) == step_bound: # lower_bound -= 1 # upper_bound += 1 # if (upper_bound - lower_bound) < step_bound: # print('<') # step_bound = int(round(step_bound / 10)) # print(lower_bound, upper_bound, step_bound) # bin_range = list(range(lower_bound, upper_bound, step_bound)) # print(bin_range) # preparing color palette colors = color_names[:len(groups)] # colors = [color['color'] for color in # list(pyplot.rcParams['axes.prop_cycle'][:len(groups)])] fig0, ax0 = pyplot.subplots(nrows=2, ncols=1) # subplot for histogram and basic statistics table ax0[1].axis('off') ax0[1].axis('tight') the_table = ax0[1].table( cellText=groups.describe().round(2).values, rowLabels=groups.describe().index.year, rowColours=colors, colLabels=groups.describe().columns.levels[1], loc='center') the_table.set_fontsize(5) # subplot for data fig, ax = pyplot.subplots(nrows=len(groups), ncols=1, sharey=True) if len(groups) == 1: ax = [ax] t = 1 for ny in range(len(groups)): # prepare data for plotting y_data = g_data[ny + (t + 1)].dropna(axis=0) x_time = g_data[ny + t].dropna(axis=0) t += 1 if len(y_data) != 0 and len(x_time) != 0: n_year = x_time[0].year col_name = str(n_year) serie_n = pd.DataFrame(columns=[col_name], index=x_time) serie_n[col_name] = list(y_data[:]) # plot histogram # serie_n.plot.hist(ax=ax0[0], bins=bin_range, # histtype='bar', color=colors[ny], stacked=True) if len(serie_n) != 1: serie_n.plot.kde(ax=ax0[0], color=colors[ny]) ax0[0].legend(fontsize=8, bbox_to_anchor=(0., 1.12, 1., .102), loc=3, ncol=len(groups), mode="expand", borderaxespad=0.) # ax0[0].set_xticks(bin_range) ax0[0].set_xlabel('Observation Ranges', fontsize=8) ax0[0].set_ylabel( 'Density', fontsize=8 ) #'Number of Observations' ax0[0].set_title( ms.split('-')[0] + ' (' + sv + ', ' + sv_units + ')' + ' Kernel Density Estimates', fontsize=8) # plot data serie_n.plot(ax=ax[ny], linestyle='None', marker='.', markersize=0.5, color=colors[ny]) ax[ny].legend().set_visible(False) # plot Mean and Standard deviation ma = serie_n.rolling('86400s').mean() mstd = serie_n.rolling('86400s').std() ax[ny].plot(ma.index, ma[col_name].values, 'k', linewidth=0.15) ax[ny].fill_between( mstd.index, ma[col_name].values - 2 * mstd[col_name].values, ma[col_name].values + 2 * mstd[col_name].values, color='b', alpha=0.2) # prepare the time axis parameters datemin = datetime.date(n_year, 1, 1) datemax = datetime.date(n_year, 12, 31) ax[ny].set_xlim(datemin, datemax) xlocator = mdates.MonthLocator( ) # every month myFmt = mdates.DateFormatter('%m') ax[ny].xaxis.set_minor_locator( xlocator) ax[ny].xaxis.set_major_formatter(myFmt) # prepare the time axis parameters # ax[ny].set_yticks(bin_range) ylocator = MaxNLocator(prune='both', nbins=3) ax[ny].yaxis.set_major_locator( ylocator) # format figure ax[ny].tick_params(axis='both', color='r', labelsize=7, labelcolor='m') if ny < len(groups) - 1: ax[ny].tick_params( which='both', pad=0.1, length=1, labelbottom=False) ax[ny].set_xlabel(' ') else: ax[ny].tick_params(which='both', color='r', labelsize=7, labelcolor='m', pad=0.1, length=1, rotation=0) ax[ny].set_xlabel('Months', rotation=0, fontsize=8, color='b') ax[ny].set_ylabel(n_year, rotation=0, fontsize=8, color='b', labelpad=20) ax[ny].yaxis.set_label_position( "right") if ny == 0: if global_min and global_max: ax[ny].set_title( sv + '( ' + sv_units + ') -- Global Range: [' + str(int(global_min)) + ',' + str(int(global_max)) + '] \n' 'Plotted: Data, Mean and 2STD (Method: One day rolling window calculations) \n', fontsize=8) else: ax[ny].set_title( sv + '( ' + sv_units + ') -- Global Range: [] \n' 'Plotted: Data, Mean and 2STD (Method: One day rolling window calculations) \n', fontsize=8) # plot global ranges # ax[ny].axhline(y=global_min, color='r', linestyle='--', linewidth=.6) # ax[ny].axhline(y=global_max, color='r', linestyle='--', linewidth=.6) # mark deployment end times on figure ymin, ymax = ax[ny].get_ylim() #dep = 1 for etimes in range(len(end_times)): if end_times[ etimes].year == n_year: ax[ny].axvline( x=end_times[etimes], color='b', linestyle='--', linewidth=.6) ax[ny].text( end_times[etimes], ymin, 'End' + str(deployments_num[etimes] ), fontsize=6, style='italic', bbox=dict(boxstyle='round', ec=(0., 0.5, 0.5), fc=(1., 1., 1.))) # dep += 1 # ax[ny].set_ylim(5, 12) # save figure to a file sfile = '_'.join(('all', sname)) save_file = os.path.join(save_dir, sfile) fig.savefig(str(save_file), dpi=150) sfile = '_'.join(('Statistics', sname)) save_file = os.path.join(save_dir, sfile) fig0.savefig(str(save_file), dpi=150) pyplot.close()
def main(sDir, url_list, deployment_num): reviewlist = pd.read_csv( 'https://raw.githubusercontent.com/ooi-data-lab/data-review-prep/master/review_list/data_review_list.csv') rd_list = [] for uu in url_list: elements = uu.split('/')[-2].split('-') rd = '-'.join((elements[1], elements[2], elements[3], elements[4])) if rd not in rd_list: rd_list.append(rd) json_file_list = [] for r in rd_list: dependencies = [] print('\n{}'.format(r)) data = OrderedDict(deployments=OrderedDict()) save_dir = os.path.join(sDir, r.split('-')[0], r) cf.create_dir(save_dir) # Deployment location test deploy_loc_test = cf.deploy_location_check(r) data['location_comparison'] = deploy_loc_test for u in url_list: splitter = u.split('/')[-2].split('-') rd_check = '-'.join((splitter[1], splitter[2], splitter[3], splitter[4])) catalog_rms = '-'.join((r, splitter[-2], splitter[-1])) # complete the analysis by reference designator if rd_check == r: udatasets = cf.get_nc_urls([u]) # check for the OOI 1.0 datasets for review rl_filtered = reviewlist.loc[ (reviewlist['Reference Designator'] == r) & (reviewlist['status'] == 'for review')] review_deployments = rl_filtered['deploymentNumber'].tolist() review_deployments_int = ['deployment%04d' % int(x) for x in review_deployments] for rev_dep in review_deployments_int: if deployment_num is not None: if int(rev_dep[-4:]) is not deployment_num: print('\nskipping {}'.format(rev_dep)) continue rdatasets = [s for s in udatasets if rev_dep in s] rdatasets.sort() if len(rdatasets) > 0: datasets = [] for dss in rdatasets: # filter out collocated data files if catalog_rms == dss.split('/')[-1].split('_20')[0][15:]: datasets.append(dss) else: drd = dss.split('/')[-1].split('_20')[0][15:42] if drd not in dependencies and drd != r: dependencies.append(drd) notes = [] time_ascending = '' sci_vars_dict = {} #datasets = datasets[0:2] #### for testing for i in range(len(datasets)): ds = xr.open_dataset(datasets[i], mask_and_scale=False) ds = ds.swap_dims({'obs': 'time'}) print('\nAppending data from {}: file {} of {}'.format(rev_dep, i+1, len(datasets))) # when opening multiple datasets, don't check that the timestamps are in ascending order time_ascending = 'not_tested' if i == 0: fname, subsite, refdes, method, data_stream, deployment = cf.nc_attributes(datasets[0]) fname = fname.split('_20')[0] # Get info from the data review database dr_data = cf.refdes_datareview_json(refdes) stream_vars = cf.return_stream_vars(data_stream) sci_vars = cf.return_science_vars(data_stream) node = refdes.split('-')[1] if 'cspp' in data_stream or 'WFP' in node: sci_vars.append('int_ctd_pressure') # Add pressure to the list of science variables press = pf.pressure_var(ds, list(ds.coords.keys())) if press is None: press = pf.pressure_var(ds, list(ds.data_vars.keys())) if press is not None: sci_vars.append(press) sci_vars.append('time') sci_vars = list(np.unique(sci_vars)) if 'ADCP' in r: sci_vars = [x for x in sci_vars if 'beam' not in x] for sci_var in sci_vars: if sci_var == 'time': sci_vars_dict.update( {sci_var: dict(values=np.array([], dtype=np.datetime64), units=[], fv=[])}) else: sci_vars_dict.update({sci_var: dict(values=np.array([]), units=[], fv=[])}) deploy_info = get_deployment_information(dr_data, int(deployment[-4:])) # Grab deployment Variables deploy_start = str(deploy_info['start_date']) deploy_stop = str(deploy_info['stop_date']) deploy_lon = deploy_info['longitude'] deploy_lat = deploy_info['latitude'] deploy_depth = deploy_info['deployment_depth'] # Calculate days deployed if deploy_stop != 'None': r_deploy_start = pd.to_datetime(deploy_start).replace(hour=0, minute=0, second=0) if deploy_stop.split('T')[1] == '00:00:00': r_deploy_stop = pd.to_datetime(deploy_stop) else: r_deploy_stop = (pd.to_datetime(deploy_stop) + timedelta(days=1)).replace(hour=0, minute=0, second=0) n_days_deployed = (r_deploy_stop - r_deploy_start).days else: n_days_deployed = None # Add reference designator to dictionary try: data['refdes'] except KeyError: data['refdes'] = refdes # append data for the deployment into a dictionary for s_v in sci_vars_dict.keys(): vv = ds[s_v] try: if vv.units not in sci_vars_dict[s_v]['units']: sci_vars_dict[s_v]['units'].append(vv.units) except AttributeError: print('') try: if vv._FillValue not in sci_vars_dict[s_v]['fv']: sci_vars_dict[s_v]['fv'].append(vv._FillValue) except AttributeError: print('') if len(vv.dims) == 1: if s_v in ['wavelength_a', 'wavelength_c']: # if the array is not same as the array that was already appended for these # two OPTAA variables, append. if it's already there, don't append if np.sum(vv.values == sci_vars_dict[s_v]['values']) != len(vv.values): sci_vars_dict[s_v]['values'] = np.append(sci_vars_dict[s_v]['values'], vv.values) else: sci_vars_dict[s_v]['values'] = np.append(sci_vars_dict[s_v]['values'], vv.values) elif len(vv.dims) == 2: # appending 2D datasets vD = vv.values.T if len(sci_vars_dict[s_v]['values']) == 0: sci_vars_dict[s_v]['values'] = vD else: sci_vars_dict[s_v]['values'] = np.concatenate((sci_vars_dict[s_v]['values'], vD), axis=1) deployments = data['deployments'].keys() data_start = pd.to_datetime(min(sci_vars_dict['time']['values'])).strftime('%Y-%m-%dT%H:%M:%S') data_stop = pd.to_datetime(max(sci_vars_dict['time']['values'])).strftime('%Y-%m-%dT%H:%M:%S') # Add deployment and info to dictionary and initialize delivery method sub-dictionary if deployment not in deployments: data['deployments'][deployment] = OrderedDict(deploy_start=deploy_start, deploy_stop=deploy_stop, n_days_deployed=n_days_deployed, lon=deploy_lon, lat=deploy_lat, deploy_depth=deploy_depth, method=OrderedDict()) # Add delivery methods to dictionary and initialize stream sub-dictionary methods = data['deployments'][deployment]['method'].keys() if method not in methods: data['deployments'][deployment]['method'][method] = OrderedDict( stream=OrderedDict()) # Add streams to dictionary and initialize file sub-dictionary streams = data['deployments'][deployment]['method'][method]['stream'].keys() if data_stream not in streams: data['deployments'][deployment]['method'][method]['stream'][ data_stream] = OrderedDict(file=OrderedDict()) # Get a list of data gaps >1 day time_df = pd.DataFrame(sci_vars_dict['time']['values'], columns=['time']) time_df = time_df.sort_values(by=['time']) gap_list = cf.timestamp_gap_test(time_df) # Calculate the sampling rate to the nearest second time_df['diff'] = time_df['time'].diff().astype('timedelta64[s]') rates_df = time_df.groupby(['diff']).agg(['count']) n_diff_calc = len(time_df) - 1 rates = dict(n_unique_rates=len(rates_df), common_sampling_rates=dict()) for i, row in rates_df.iterrows(): percent = (float(row['time']['count']) / float(n_diff_calc)) if percent > 0.1: rates['common_sampling_rates'].update({int(i): '{:.2%}'.format(percent)}) sampling_rt_sec = None for k, v in rates['common_sampling_rates'].items(): if float(v.strip('%')) > 50.00: sampling_rt_sec = k if not sampling_rt_sec: sampling_rt_sec = 'no consistent sampling rate: {}'.format(rates['common_sampling_rates']) # Don't do : Check that the timestamps in the file are unique time_test = '' # Count the number of days for which there is at least 1 timestamp n_days = len(np.unique(sci_vars_dict['time']['values'].astype('datetime64[D]'))) # Compare variables in file to variables in Data Review Database ds_variables = list(ds.data_vars.keys()) + list(ds.coords.keys()) ds_variables = eliminate_common_variables(ds_variables) ds_variables = [x for x in ds_variables if 'qc' not in x] [_, unmatch1] = compare_lists(stream_vars, ds_variables) [_, unmatch2] = compare_lists(ds_variables, stream_vars) # calculate mean pressure from data, excluding outliers +/- 3 SD try: pressure = sci_vars_dict[press] if len(pressure) > 1: # reject NaNs p_nonan = pressure['values'][~np.isnan(pressure['values'])] # reject fill values p_nonan_nofv = p_nonan[p_nonan != pressure['fv'][0]] # reject data outside of global ranges [pg_min, pg_max] = cf.get_global_ranges(r, press) if pg_min is not None and pg_max is not None: pgr_ind = cf.reject_global_ranges(p_nonan_nofv, pg_min, pg_max) p_nonan_nofv_gr = p_nonan_nofv[pgr_ind] else: p_nonan_nofv_gr = p_nonan_nofv if (len(p_nonan_nofv_gr) > 0): [press_outliers, pressure_mean, _, pressure_max, _, _] = cf.variable_statistics(p_nonan_nofv_gr, 3) pressure_mean = round(pressure_mean, 2) pressure_max = round(pressure_max, 2) else: press_outliers = None pressure_mean = None pressure_max = None if len(pressure) > 0 and len(p_nonan) == 0: notes.append('Pressure variable all NaNs') elif len(pressure) > 0 and len(p_nonan) > 0 and len(p_nonan_nofv) == 0: notes.append('Pressure variable all fill values') elif len(pressure) > 0 and len(p_nonan) > 0 and len(p_nonan_nofv) > 0 and len(p_nonan_nofv_gr) == 0: notes.append('Pressure variable outside of global ranges') else: # if there is only 1 data point press_outliers = 0 pressure_mean = round(ds[press].values.tolist()[0], 2) pressure_max = round(ds[press].values.tolist()[0], 2) try: pressure_units = pressure['units'][0] except AttributeError: pressure_units = 'no units attribute for pressure' if pressure_mean: if 'SF' in node: pressure_compare = int(round(pressure_max)) else: pressure_compare = int(round(pressure_mean)) if pressure_units == '0.001 dbar': pressure_max = round((pressure_max / 1000), 2) pressure_mean = round((pressure_mean / 1000), 2) pressure_compare = round((pressure_compare / 1000), 2) notes.append('Pressure converted from 0.001 dbar to dbar for pressure comparison') elif pressure_units == 'daPa': pressure_max = round((pressure_max / 1000), 2) pressure_mean = round((pressure_mean / 1000), 2) pressure_compare = round((pressure_compare / 1000), 2) notes.append('Pressure converted from daPa to dbar for pressure comparison') else: pressure_compare = None if (not deploy_depth) or (not pressure_mean): pressure_diff = None else: pressure_diff = pressure_compare - deploy_depth except KeyError: press = 'no seawater pressure in file' pressure_diff = None pressure_mean = None pressure_max = None pressure_compare = None press_outliers = None pressure_units = None # Add files and info to dictionary filenames = data['deployments'][deployment]['method'][method]['stream'][data_stream][ 'file'].keys() if fname not in filenames: data['deployments'][deployment]['method'][method]['stream'][data_stream]['file'][ fname] = OrderedDict( file_downloaded=pd.to_datetime(splitter[0][0:15]).strftime('%Y-%m-%dT%H:%M:%S'), file_coordinates=list(ds.coords.keys()), sampling_rate_seconds=sampling_rt_sec, sampling_rate_details=rates, data_start=data_start, data_stop=data_stop, time_gaps=gap_list, unique_timestamps=time_test, n_timestamps=len(sci_vars_dict['time']['values']), n_days=n_days, notes=notes, ascending_timestamps=time_ascending, pressure_comparison=dict(pressure_mean=pressure_mean, units=pressure_units, num_outliers=press_outliers, diff=pressure_diff, pressure_max=pressure_max, variable=press, pressure_compare=pressure_compare), vars_in_file=ds_variables, vars_not_in_file=[x for x in unmatch1 if 'time' not in x], vars_not_in_db=unmatch2, sci_var_stats=OrderedDict()) # calculate statistics for science variables, excluding outliers +/- 5 SD for sv in sci_vars_dict.keys(): if sv != 't_max': # for ADCP if sv != 'time': print(sv) var = sci_vars_dict[sv] vD = var['values'] var_units = var['units'] #if 'timedelta' not in str(vD.dtype): vnum_dims = len(np.shape(vD)) # for OPTAA wavelengths, print the array if sv == 'wavelength_a' or sv == 'wavelength_c': [g_min, g_max] = cf.get_global_ranges(r, sv) n_all = len(var) mean = list(vD) num_outliers = None vmin = None vmax = None sd = None n_stats = 'not calculated' n_nan = None n_fv = None n_grange = 'no global ranges' fv = var['fv'][0] else: if vnum_dims > 2: print('variable has more than 2 dimensions') num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 'variable has more than 2 dimensions' n_nan = None n_fv = None n_grange = None fv = None n_all = None else: if vnum_dims > 1: n_all = [len(vD), len(vD.flatten())] else: n_all = len(vD) n_nan = int(np.sum(np.isnan(vD))) fv = var['fv'][0] vD[vD == fv] = np.nan # turn fill values to nans n_fv = int(np.sum(np.isnan(vD))) - n_nan [g_min, g_max] = cf.get_global_ranges(r, sv) if list(np.unique(np.isnan(vD))) != [True]: # reject data outside of global ranges if g_min is not None and g_max is not None: # turn data outside of global ranges to nans #var_gr = var_nofv.where((var_nofv >= g_min) & (var_nofv <= g_max)) vD[vD < g_min] = np.nan vD[vD > g_max] = np.nan n_grange = int(np.sum(np.isnan(vD)) - n_fv - n_nan) else: n_grange = 'no global ranges' if list(np.unique(np.isnan(vD))) != [True]: if sv == 'spkir_abj_cspp_downwelling_vector': # don't remove outliers from dataset [num_outliers, mean, vmin, vmax, sd, n_stats] = cf.variable_statistics_spkir(vD) else: if vnum_dims > 1: var_gr = vD.flatten() else: var_gr = vD # drop nans before calculating stats var_gr = var_gr[~np.isnan(var_gr)] [num_outliers, mean, vmin, vmax, sd, n_stats] = cf.variable_statistics(var_gr, 5) else: num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 0 n_grange = None else: num_outliers = None mean = None vmin = None vmax = None sd = None n_stats = 0 n_grange = None if vnum_dims > 1: sv = '{} (dims: {})'.format(sv, list(np.shape(var['values']))) else: sv = sv #if 'timedelta' not in str(var.values.dtype): data['deployments'][deployment]['method'][method]['stream'][data_stream]['file'][ fname]['sci_var_stats'][sv] = dict(n_outliers=num_outliers, mean=mean, min=vmin, max=vmax, stdev=sd, n_stats=n_stats, units=var_units, n_nans=n_nan, n_fillvalues=n_fv, fill_value=str(fv), global_ranges=[g_min, g_max], n_grange=n_grange, n_all=n_all) sfile = os.path.join(save_dir, '{}-{}-file_analysis.json'.format(rev_dep, r)) with open(sfile, 'w') as outfile: json.dump(data, outfile) json_file_list.append(str(sfile)) depfile = os.path.join(save_dir, '{}-dependencies.txt'.format(r)) with open(depfile, 'w') as depf: depf.write(str(dependencies)) return json_file_list