def main(sDir, ncdir):
rd_list = [ncdir.split('/')[-2]]
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
fdatasets = []
for root, dirs, files in os.walk(ncdir):
for f in files:
if f.endswith('.nc'):
fdatasets.append(f)
# 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:
strm = '_'.join((f.split('-')[-2].split('_')[0], f.split('-')[-2].split('_')[1]))
methodstream.append('-'.join((f.split('-')[-3], strm)))
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')
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(os.path.join(ncdir, 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(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(url_list, sDir, plot_type):
"""""
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]
ps_df, n_streams = cf.get_preferred_stream_info(r)
# read in the analysis file
dr_data = cf.refdes_datareview_json(r)
# get end times of deployments
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']))
# get the list of data files and filter out collocated instruments and other streams chat
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)
'''
separate the data files by methods
'''
for ms in ms_list: # np.unique(methodstream)
fdatasets_sel = [x for x in fdatasets if ms in x]
# create a folder to save figures
save_dir = os.path.join(sDir, array, subsite, r, plot_type,
ms.split('-')[0])
cf.create_dir(save_dir)
# create a dictionary for science variables from analysis file
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
# initialize an empty data array for science variables in dictionary
sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict,
ms)
y_unit = []
y_name = []
for fd in fdatasets_sel:
ds = xr.open_dataset(fd, mask_and_scale=False)
print('\nAppending data file: {}'.format(fd.split('/')[-1]))
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)
# time
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')
# sci variable
z = ds[var].values
sh['t'] = np.append(sh['t'], t)
sh['values'] = np.append(sh['values'], z)
# add pressure to dictionary of sci vars
if 'MOAS' in subsite:
if 'CTD' in main_sensor: # for glider CTDs, pressure is a coordinate
pressure = 'sci_water_pressure_dbar'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = 'int_ctd_pressure'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = pf.pressure_var(ds, ds.data_vars.keys())
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
sh['pressure'] = np.append(sh['pressure'], y)
if len(y_unit) != 1:
print('pressure unit varies!')
else:
y_unit = y_unit[0]
if len(y_name) != 1:
print('pressure long name varies!')
else:
y_name = y_name[0]
for m, n in sci_vars_dict.items():
for sv, vinfo in n['vars'].items():
print('\nWorking on variable: {}'.format(sv))
if len(vinfo['t']) < 1:
print('no variable data to plot')
else:
sv_units = vinfo['units'][0]
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')
t = vinfo['t']
x = vinfo['values']
y = vinfo['pressure']
# Check if the array is all NaNs
if sum(np.isnan(x)) == len(x):
print('Array of all NaNs - skipping plot.')
continue
# Check if the array is all fill values
elif len(x[x != fv]) == 0:
print('Array of all fill values - skipping plot.')
continue
else:
# reject fill values
fv_ind = x != fv
y_nofv = y[fv_ind]
t_nofv = t[fv_ind]
c_nofv = cm.rainbow(np.linspace(0, 1, len(t[fv_ind])))
x_nofv = x[fv_ind]
print(len(x) - len(fv_ind), ' fill values')
# reject NaNs
nan_ind = ~np.isnan(x)
t_nofv_nonan = t_nofv[nan_ind]
c_nofv_nonan = c_nofv[nan_ind]
y_nofv_nonan = y_nofv[nan_ind]
x_nofv_nonan = x_nofv[nan_ind]
print(len(x) - len(nan_ind), ' NaNs')
# reject extreme values
ev_ind = cf.reject_extreme_values(x_nofv_nonan)
t_nofv_nonan_noev = t_nofv_nonan[ev_ind]
c_nofv_nonan_noev = c_nofv_nonan[ev_ind]
y_nofv_nonan_noev = y_nofv_nonan[ev_ind]
x_nofv_nonan_noev = x_nofv_nonan[ev_ind]
print(len(z) - len(ev_ind), ' Extreme Values', '|1e7|')
# reject values outside global ranges:
global_min, global_max = cf.get_global_ranges(r, sv)
# platform not in qc-table (parad_k_par)
# global_min = 0
# global_max = 2500
print('global ranges for : {}-{} {} - {}'.format(
r, sv, global_min, global_max))
if isinstance(global_min, (int, float)) and isinstance(
global_max, (int, float)):
gr_ind = cf.reject_global_ranges(
x_nofv_nonan_noev, global_min, global_max)
t_nofv_nonan_noev_nogr = t_nofv_nonan_noev[gr_ind]
y_nofv_nonan_noev_nogr = y_nofv_nonan_noev[gr_ind]
x_nofv_nonan_noev_nogr = x_nofv_nonan_noev[gr_ind]
else:
t_nofv_nonan_noev_nogr = t_nofv_nonan_noev
y_nofv_nonan_noev_nogr = y_nofv_nonan_noev
x_nofv_nonan_noev_nogr = x_nofv_nonan_noev
if len(x_nofv_nonan_noev) > 0:
if m == 'common_stream_placeholder':
sname = '-'.join((r, sv))
else:
sname = '-'.join((r, m, sv))
if sv != 'pressure':
columns = ['tsec', 'dbar', str(sv)]
bin_size = 10
min_r = int(round(min(y_nofv_nonan_noev) - bin_size))
max_r = int(round(max(y_nofv_nonan_noev) + bin_size))
ranges = list(range(min_r, max_r, bin_size))
groups, d_groups = gt.group_by_depth_range(
t_nofv_nonan_noev_nogr, y_nofv_nonan_noev_nogr,
x_nofv_nonan_noev_nogr, columns, ranges)
y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr = [], [], [], [], [], [], []
tm = 1
for ii in range(len(groups)):
nan_ind = d_groups[ii + tm].notnull()
xtime = d_groups[ii + tm][nan_ind]
colors = cm.rainbow(np.linspace(0, 1, len(xtime)))
ypres = d_groups[ii + tm + 1][nan_ind]
nval = d_groups[ii + tm + 2][nan_ind]
tm += 2
l_arr.append(len(
nval)) # count of data to filter out small groups
y_avg.append(ypres.mean())
n_avg.append(nval.mean())
n_min.append(nval.min())
n_max.append(nval.max())
n_std = 3
n0_std.append(nval.mean() + n_std * nval.std())
n1_std.append(nval.mean() - n_std * nval.std())
# Plot all data
ylabel = y_name + " (" + y_unit + ")"
xlabel = sv + " (" + sv_units + ")"
clabel = 'Time'
fig, ax = pf.plot_profiles(x_nofv_nonan_noev_nogr,
y_nofv_nonan_noev_nogr,
t_nofv_nonan_noev_nogr,
ylabel,
xlabel,
clabel,
end_times,
deployments,
stdev=None)
title_text = ' '.join((r, ms.split('-')[-1])) + '\n' \
+ t0 + ' - ' + t1 + '\n' + str(bin_size) +\
' m average and ' + str(n_std) + ' std shown'
ax.set_title(title_text, fontsize=9)
ax.plot(n_avg, y_avg, '-k')
ax.fill_betweenx(y_avg,
n0_std,
n1_std,
color='m',
alpha=0.2)
pf.save_fig(save_dir, sname)
# Plot data with outliers removed
fig, ax = pf.plot_profiles(x_nofv_nonan_noev_nogr,
y_nofv_nonan_noev_nogr,
t_nofv_nonan_noev_nogr,
ylabel,
xlabel,
clabel,
end_times,
deployments,
stdev=5)
ax.set_title(' '.join((r, ms.split('-')[-1])) + '\n' \
+ t0 + ' - ' + t1, fontsize=9)
sfile = '_'.join((sname, 'rmoutliers'))
pf.save_fig(save_dir, sfile)
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]
check_ms = ms.split('-')[1]
if 'recovered' in check_ms:
check_ms = check_ms.split('_recovered')
save_dir = os.path.join(sDir, array, subsite, r, 'timeseries_monthly_plot',
check_ms[0], 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)
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]
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))
# 1st group by year
ygroups, gy_data = gt.group_by_timerange(x_nonan_nofv_nE_nogr, y_nonan_nofv_nE_nogr, 'A')
tn = 1
for n in range(len(ygroups)):
x_time = gy_data[n+tn].dropna(axis=0)
y_data = gy_data[n+(tn+1)].dropna(axis=0)
y_data = y_data.astype(float)
# 2nd group by month
mgroups, gm_data = gt.group_by_timerange(x_time.values, y_data.values, 'M')
x_year = x_time[0].year
print(x_year)
#
# create bins for histogram
mgroups_min = min(mgroups.describe()['DO']['min'])
mgroups_max = max(mgroups.describe()['DO']['max'])
lower_bound = int(round(mgroups_min))
upper_bound = int(round(mgroups_max + (mgroups_max / 50)))
step_bound = int(round((mgroups_max - mgroups_min) / 10))
lower_bound = int(round(global_min))
upper_bound = int(round(global_max + (global_max / 50)))
step_bound = int(round((global_max - global_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:
step_bound = int(round(step_bound / 10))
bin_range = list(range(lower_bound, upper_bound, step_bound))
print(bin_range)
# create color palette
colors = color_names[:len(mgroups)]
print('1--- ', len(colors))
print(colors)
fig0, ax0 = pyplot.subplots(nrows=2, ncols=1)
# # subplot for histogram and basic statistics table
ax0[0].axis('off')
ax0[0].axis('tight')
the_table = ax0[0].table(cellText=mgroups.describe().round(2).values,
rowLabels=mgroups.describe().index.month,
rowColours=colors,
colLabels=mgroups.describe().columns.levels[1], loc='center')
the_table.set_fontsize(5)
fig, ax = pyplot.subplots(nrows=12, ncols=1, sharey=True)
for kk in list(range(0, 12)):
ax[kk].tick_params(axis='both', which='both', color='r', labelsize=7,
labelcolor='m', rotation=0, pad=0.1, length=1)
month_name = calendar.month_abbr[kk + 1]
ax[kk].set_ylabel(month_name, rotation=0, fontsize=8, color='b', labelpad=20)
if kk == 0:
ax[kk].set_title(str(x_year) + '\n ' + sv + " (" + sv_units + ")" +
' Global Range: [' + str(int(global_min)) + ',' + str(int(global_max)) + ']' +
'\n End of deployments are marked with a vertical line \n ' +
'Plotted: Data, Mean and STD (Method: 1 day' +
' rolling window calculations)',
fontsize=8)
if kk < 11:
ax[kk].tick_params(labelbottom=False)
if kk == 11:
ax[kk].set_xlabel('Days', rotation=0, fontsize=8, color='b')
tm = 1
for mt in range(len(mgroups)):
x_time = gm_data[mt+tm].dropna(axis=0)
y_data = gm_data[mt+(tm+1)].dropna(axis=0)
if len(x_time) == 0:
# ax[plt_index].tick_params(which='both', labelbottom=False, labelleft=False,
# pad=0.1, length=1)
continue
x_month = x_time[0].month
col_name = str(x_month)
series_m = pd.DataFrame(columns=[col_name], index=x_time)
series_m[col_name] = list(y_data[:])
# serie_n.plot.hist(ax=ax0[0], bins=bin_range,
# histtype='bar', color=colors[ny], stacked=True)
series_m.plot.kde(ax=ax0[0], color=colors[mt])
ax0[0].legend(fontsize=8, bbox_to_anchor=(0., 1.12, 1., .102), loc=3,
ncol=len(mgroups), mode="expand", borderaxespad=0.)
# ax0[0].set_xticks(bin_range)
ax0[0].set_xlabel('Observation Ranges' + ' (' + sv + ', ' + sv_units + ')', fontsize=8)
ax0[0].set_ylabel('Density', fontsize=8) # 'Number of Observations'
ax0[0].set_title('Kernel Density Estimates', fontsize=8)
ax0[0].tick_params(which='both', labelsize=7, pad=0.1, length=1, rotation=0)
plt_index = x_month - 1
# Plot data
series_m.plot(ax=ax[plt_index], linestyle='None', marker='.', markersize=1)
ax[plt_index].legend().set_visible(False)
ma = series_m.rolling('86400s').mean()
mstd = series_m.rolling('86400s').std()
ax[plt_index].plot(ma.index, ma[col_name].values, 'b')
ax[plt_index].fill_between(mstd.index, ma[col_name].values-3*mstd[col_name].values,
ma[col_name].values+3*mstd[col_name].values,
color='b', alpha=0.2)
# prepare the time axis parameters
mm, nod = monthrange(x_year, x_month)
datemin = datetime.date(x_year, x_month, 1)
datemax = datetime.date(x_year, x_month, nod)
ax[plt_index].set_xlim(datemin, datemax)
xlocator = mdates.DayLocator() # every day
myFmt = mdates.DateFormatter('%d')
ax[plt_index].xaxis.set_major_locator(xlocator)
ax[plt_index].xaxis.set_major_formatter(myFmt)
ax[plt_index].xaxis.set_minor_locator(pyplot.NullLocator())
ax[plt_index].xaxis.set_minor_formatter(pyplot.NullFormatter())
# data_min = min(ma.DO_n.dropna(axis=0) - 5 * mstd.DO_n.dropna(axis=0))
# 0data_max = max(ma.DO_n.dropna(axis=0) + 5 * mstd.DO_n.dropna(axis=0))
# ax[plt_index].set_ylim([data_min, data_max])
ylocator = MaxNLocator(prune='both', nbins=3)
ax[plt_index].yaxis.set_major_locator(ylocator)
if x_month != 12:
ax[plt_index].tick_params(which='both', labelbottom=False, pad=0.1, length=1)
ax[plt_index].set_xlabel(' ')
else:
ax[plt_index].tick_params(which='both', color='r', labelsize=7, labelcolor='m',
pad=0.1, length=1, rotation=0)
ax[plt_index].set_xlabel('Days', rotation=0, fontsize=8, color='b')
dep = 1
for etimes in end_times:
ax[plt_index].axvline(x=etimes, color='b', linestyle='--', linewidth=.8)
if ma[col_name].values.any():
ax[plt_index].text(etimes, max(ma[col_name].dropna(axis=0)), 'End' + str(dep),
fontsize=6, style='italic',
bbox=dict(boxstyle='round',
ec=(0., 0.5, 0.5),
fc=(1., 1., 1.),
))
else:
ax[plt_index].text(etimes, min(series_m['DO_n']), 'End' + str(dep),
fontsize=6, style='italic',
bbox=dict(boxstyle='round',
ec=(0., 0.5, 0.5),
fc=(1., 1., 1.),
))
dep += 1
tm += 1
tn += 1
# pyplot.show()
sfile = '_'.join((str(x_year), sname))
save_file = os.path.join(save_dir, sfile)
fig.savefig(str(save_file), dpi=150)
sfile = '_'.join(('Statistics', str(x_year), sname))
save_file = os.path.join(save_dir, sfile)
fig0.savefig(str(save_file), dpi=150)
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:
# 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])))
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_yearly_plot', 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 'light' in y['name']:
sci_vars.update({y['name']: dict(db_units=y['unit'])})
# 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))
fcount = 0
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) # put deployments time series together
if fcount == 0:
if varD.ndim > 1:
sh['values'] = np.zeros(shape=[varD.shape[0], varD.shape[1]])
sh['values'][:] = varD
else:
sh['values'] = np.append(sh['values'], varD)
else:
if varD.ndim > 1:
sh['values'] = np.vstack([sh['values'], varD])
else:
sh['values'] = np.append(sh['values'], varD)
print(fcount, var, sh['values'].shape, sh['t'].shape)
fcount += 1
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']
if len(y) > 0:
if m == 'common_stream_placeholder':
sname = '-'.join((r, sv))
else:
sname = '-'.join((r, m, sv))
if y.ndim == 1:
num_col = 1
else:
num_col = y.shape[1]
col = [str(x) for x in list(range(1, num_col + 1))]
col.insert(0, 'time')
groups, d_groups = gt.group_by_time_frequency(x, y, col, 'A')
if len(d_groups.columns) == len(col):
time_ind = [1]
data_ind0 = [2]
data_ind1 = [len(col)]
else:
time_ind = list(range(1, len(d_groups.columns), len(col)))
data_ind0 = list(range(2, len(d_groups.columns), len(col)))
if data_ind0[-1] == d_groups.columns.values[-(len(col)+1)]:
data_ind0.insert(len(groups) - 1, len(d_groups.columns))
data_ind1 = list(range(len(col), len(d_groups.columns), len(col)))
data_ind1.insert(len(groups)-1, len(d_groups.columns))
save_file = os.path.join(save_dir, sname)
print('\ncreating images')
fig, ax = pyplot.subplots(nrows=len(groups), ncols=1)
if len(groups) == 1:
ax = [ax]
colors = color_names[:len(groups)]
images = []
for group in range(len(groups)):
nan_ind = d_groups[time_ind[group]].notnull()
xtime = d_groups[time_ind[group]][nan_ind]
ycol = list(range(data_ind0[group], data_ind1[group] + 1))
ydata = d_groups[ycol][nan_ind]
if len(xtime) != 0 and len(ydata) != 0:
n_year = xtime[0].year
print(n_year)
ydata = ydata.set_index(xtime)
if len(ydata.columns) > 1:
print('more than one col: ', len(ydata.columns))
b = fsplt.split_by_timegap(ydata, 86400)
if b:
print('gaps exist, splitting data')
for ib in (range(len(b))):
iydata = b[ib][b[ib].columns.values[0:-2]]
Y = iydata.columns.values
X = iydata.index.values
Z = iydata.values
if Z.shape[0] == 1:
X = np.repeat(X[0], len(Y), axis=0)
df = pd.DataFrame(dict(a=list(X), b=list(Y), c=list(Z[0])))
images.append(ax[group].scatter(df['a'].values, df['b'].values, c=df['c'].values, cmap='Blues', s=1))
else:
Z = Z.T
x, y = np.meshgrid(X, Y)
images.append(ax[group].contourf(x, y, Z, alpha=0.7, cmap='Blues'))
else:
print('no gaps exist, not splitting data')
iydata = ydata[ydata.columns.values[0:-2]]
Y = iydata.columns.values
X = iydata.index.values
Z = iydata.values
if Z.shape[0] == 1:
X = np.repeat(X[0], len(Y), axis=0)
df = pd.DataFrame(dict(a=list(X), b=list(Y), c=list(Z[0])))
images.append(
ax[group].scatter(df['a'].values, df['b'].values, c=df['c'].values,
cmap='Blues', s=1))
elif Z.shape[1] < 2:
Y = np.repeat(Y[0], len(X), axis=1)
df = pd.DataFrame(dict(a=list(X), b=list(Y), c=list(Z[0])))
images.append(
ax[group].scatter(df['a'].values, df['b'].values, c=df['c'].values,
cmap='Blues', s=1))
else:
Z = Z.T
x, y = np.meshgrid(X, Y)
im = ax[group].contourf(x, y, Z, alpha=0.7, cmap='Blues') #pyplot.cm.jet
images.append(ax[group].contourf(x, y, Z, alpha=0.7, cmap='Blues'))
else:
print('with one column:', len(ydata.columns))
ax[group].contourf(x, y, Z, alpha=0.7, cmap='Blues')(ydata.plot(ax=ax[group],
linestyle='None',
marker='.',
markersize=0.5,
color=colors[group]))
ax[group].legend().set_visible(False)
# plot Mean and Standard deviation
ma = ydata.rolling('86400s').mean()
mstd = ydata.rolling('86400s').std()
m_mstd_min = ma[ycol].values - 2 * mstd[ycol].values
m_mstd_max = ma[ycol].values + 2 * mstd[ycol].values
ax[group].plot(ma.index.values, ma[ycol].values, 'k', linewidth=0.15)
ax[group].fill_between(mstd.index.values, m_mstd_min, m_mstd_max, color='b', alpha=0.2)
# flag deployments end-time for reference
ymin, ymax = ax[group].get_ylim()
dep = 1
for etimes in end_times:
if etimes.year == n_year:
ax[group].axvline(x=etimes, color='b', linestyle='--', linewidth=.6)
ax[group].text(etimes, ymin, 'End' + str(dep), fontsize=6, style='italic',
bbox=dict(boxstyle='round', ec=(0., 0.5, 0.5), fc=(1., 1., 1.)))
dep += 1
# prepare the time axis parameters
datemin = datetime.date(n_year, 1, 1)
datemax = datetime.date(n_year, 12, 31)
ax[group].set_xlim(datemin, datemax)
xlocator = mdates.MonthLocator() # every month
myFmt = mdates.DateFormatter('%m')
ax[group].xaxis.set_minor_locator(xlocator)
ax[group].xaxis.set_major_formatter(myFmt)
# prepare the y axis parameters
ax[group].set_ylabel(n_year, rotation=0, fontsize=8, color='b', labelpad=20)
ax[group].yaxis.set_label_position("right")
ylocator = MaxNLocator(prune='both', nbins=3)
ax[group].yaxis.set_major_locator(ylocator)
ax[group].yaxis.set_ticklabels([]) #range(1, len(col), 1)
# format figure
ax[group].tick_params(axis='both', color='r', labelsize=7, labelcolor='m')
if group == 0:
ax[group].set_title(sv + '( ' + sv_units + ')', fontsize=8)
if group < len(groups) - 1:
ax[group].tick_params(which='both', pad=0.1, length=1, labelbottom=False)
ax[group].set_xlabel(' ')
else:
ax[group].tick_params(which='both', color='r', labelsize=7, labelcolor='m',
pad=0.1, length=1, rotation=0)
ax[group].set_xlabel('Months', rotation=0, fontsize=8, color='b')
vmin = min(image.get_array().min() for image in images)
vmax = max(image.get_array().max() for image in images)
norm = mcolors.Normalize(vmin=vmin, vmax=vmax)
for im in images:
im.set_norm(norm)
fig.colorbar(images[0], ax=ax, orientation='horizontal', fraction=.1, spacing='proportional')
fig.savefig(str(save_file), dpi=150)
pyplot.close()
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_daily_plots',
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)
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))
# 1st group by year
ygroups, gy_data = gt.group_by_timerange(
x_nonan_nofv_nE_nogr, y_nonan_nofv_nE_nogr,
'A')
tn = 1
for n in range(len(ygroups)):
x_time = gy_data[n + tn].dropna(axis=0)
y_data = gy_data[n + (tn + 1)].dropna(axis=0)
# 2nd group by month
mgroups, gm_data = gt.group_by_timerange(
x_time.values, y_data.values, 'M')
if len(x_time) == 0:
continue
td = 1
for jj in range(len(mgroups)):
x_time = gm_data[jj + td].dropna(axis=0)
y_data = gm_data[jj +
(td + 1)].dropna(axis=0)
if len(x_time) == 0:
continue
# 3rd group by day
dgroups, gd_data = gt.group_by_timerange(
x_time.values, y_data.values, 'D')
x_year = x_time[0].year
x_month = x_time[0].month
month_name = calendar.month_abbr[x_month]
print(x_year, x_month)
sfile = '_'.join(
(str(x_year), str(x_month), sname))
# prepare plot layout
fig, ax = pyplot.subplots(nrows=7,
ncols=5,
sharey=True)
title_in = month_name + '-' + str(x_year) + \
' calendar days \n Parameter: ' + \
sv + " (" + sv_units + ")"
ax[0][2].text(0.5,
1.5,
title_in,
horizontalalignment='center',
fontsize=8,
transform=ax[0][2].transAxes)
num_i = 0
day_i = {}
for kk in list(range(0, 7)):
for ff in list(range(0, 5)):
num_i += 1
day_i[num_i] = [kk, ff]
ax[kk][ff].tick_params(
axis='both',
which='both',
color='r',
labelsize=7,
labelcolor='m',
rotation=0)
ax[kk][ff].text(
0.1,
0.75,
str(num_i),
horizontalalignment='center',
fontsize=7,
transform=ax[kk][ff].transAxes,
bbox=dict(
boxstyle="round",
ec=(0., 0.5, 0.5),
fc=(1., 1., 1.),
))
if kk is not 6:
ax[kk][ff].tick_params(
labelbottom=False)
if ff is not 0:
ax[kk][ff].tick_params(
labelright=False)
if kk is 6 and ff is 0:
ax[kk][ff].set_xlabel(
'Hours',
rotation=0,
fontsize=8,
color='b')
if kk is 6 and ff in list(
range(1, 5)):
fig.delaxes(ax[kk][ff])
tm = 1
for mt in range(len(dgroups)):
x_time = gd_data[mt +
tm].dropna(axis=0)
y_DO = gd_data[mt +
(tm + 1)].dropna(axis=0)
series_m = pd.DataFrame(
columns=['DO_n'], index=x_time)
series_m['DO_n'] = list(y_DO[:])
if len(x_time) == 0:
continue
x_day = x_time[0].day
print(x_time[0].year, x_time[0].month,
x_day)
i0 = day_i[x_day][0]
i1 = day_i[x_day][1]
# Plot data
series_m.plot(ax=ax[i0][i1],
linestyle='None',
marker='.',
markersize=1)
ax[i0][i1].legend().set_visible(False)
ma = series_m.rolling('3600s').mean()
mstd = series_m.rolling('3600s').std()
ax[i0][i1].plot(ma.index,
ma.DO_n,
'b',
linewidth=0.25)
ax[i0][i1].fill_between(
mstd.index,
ma.DO_n - 3 * mstd.DO_n,
ma.DO_n + 3 * mstd.DO_n,
color='b',
alpha=0.2)
# prepare the time axis parameters
datemin = datetime.datetime(
x_year, x_month, x_day, 0)
datemax = datetime.datetime(
x_year, x_month, x_day, 23)
ax[i0][i1].set_xlim(datemin, datemax)
xLocator = mdates.HourLocator(
interval=4) # every hour
myFmt = mdates.DateFormatter('%H')
ax[i0][i1].xaxis.set_minor_locator(
xLocator)
ax[i0][i1].xaxis.set_minor_formatter(
myFmt)
ax[i0][i1].xaxis.set_major_locator(
pyplot.NullLocator())
ax[i0][i1].xaxis.set_major_formatter(
pyplot.NullFormatter())
yLocator = MaxNLocator(prune='both',
nbins=3)
ax[i0][i1].yaxis.set_major_locator(
yLocator)
if x_day is not 31:
ax[i0][i1].tick_params(
labelbottom=False)
ax[i0][i1].set_xlabel(' ')
else:
ax[i0][i1].tick_params(
which='both',
color='r',
labelsize=7,
labelcolor='m',
length=0.1,
pad=0.1)
ax[i0][i1].set_xlabel('Hours',
rotation=0,
fontsize=8,
color='b')
ymin, ymax = ax[i0][i1].get_ylim()
dep = 1
for etimes in end_times:
ax[i0][i1].axvline(x=etimes,
color='b',
linestyle='--',
linewidth=.6)
ax[i0][i1].text(
etimes,
ymin + 50,
str(dep),
fontsize=6,
style='italic',
bbox=dict(
boxstyle="round",
ec=(0., 0.5, 0.5),
fc=(1., 1., 1.),
))
dep += 1
tm += 1
td += 1
pf.save_fig(save_dir, sfile)
tn += 1
def main(url_list, sDir, plot_type):
"""""
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]
ps_df, n_streams = cf.get_preferred_stream_info(r)
# read in the analysis file
dr_data = cf.refdes_datareview_json(r)
# get preferred stream
ps_df, n_streams = cf.get_preferred_stream_info(r)
# 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']))
# 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)
'''
separate data files by methods
'''
for ms in ms_list:
fdatasets_sel = [x for x in fdatasets if ms in x]
# create a folder to save figures
save_dir = os.path.join(sDir, array, subsite, r, plot_type,
ms.split('-')[0])
cf.create_dir(save_dir)
# create a dictionary for science variables from analysis file
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
# initialize an empty data array for science variables in dictionary
sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict,
ms)
print('\nAppending data from files: {}'.format(ms))
y_unit = []
y_name = []
for fd in fdatasets_sel:
ds = xr.open_dataset(fd, mask_and_scale=False)
print('\nAppending data file: {}'.format(fd.split('/')[-1]))
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)
# time
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')
# sci variable
z = ds[var].values
sh['t'] = np.append(sh['t'], t)
sh['values'] = np.append(sh['values'], z)
# add pressure to dictionary of sci vars
if 'MOAS' in subsite:
if 'CTD' in main_sensor: # for glider CTDs, pressure is a coordinate
pressure = 'sci_water_pressure_dbar'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = 'int_ctd_pressure'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = pf.pressure_var(ds, ds.data_vars.keys())
y = ds[pressure].values
sh['pressure'] = np.append(sh['pressure'], y)
try:
ds[pressure].units
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
except AttributeError:
print('pressure attributes missing units')
if 'pressure unit missing' not in y_unit:
y_unit.append('pressure unit missing')
try:
ds[pressure].long_name
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
except AttributeError:
print('pressure attributes missing long_name')
if 'pressure long name missing' not in y_name:
y_name.append('pressure long name missing')
# create a csv file with diagnostic results:
if len(y_unit) != 1:
print('pressure unit varies')
if 'dbar' in y_unit:
y_unit = 'dbar'
print(y_unit)
else:
y_unit = y_unit[0]
if len(y_name) != 1:
print('pressure long name varies')
if 'Seawater Pressure' in y_name:
y_name = 'Seawater Pressure'
print(y_name)
else:
y_name = y_name[0]
# create a folder to save variables statistics
mDir = '/Users/leila/Documents/NSFEduSupport/github/data-review-tools/data_review/final_stats'
save_dir_stat = os.path.join(mDir, array, subsite)
cf.create_dir(save_dir_stat)
stat_df = pd.DataFrame()
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]
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')
t = vinfo['t']
z = vinfo['values']
y = vinfo['pressure']
title = ' '.join((r, ms))
# 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 fill values
fv_ind = z != fv
y_nofv = y[fv_ind]
t_nofv = t[fv_ind]
z_nofv = z[fv_ind]
print(len(z) - len(fv_ind), ' fill values')
# reject NaNs
nan_ind = ~np.isnan(z_nofv)
t_nofv_nonan = t_nofv[nan_ind]
y_nofv_nonan = y_nofv[nan_ind]
z_nofv_nonan = z_nofv[nan_ind]
print(len(z) - len(nan_ind), ' NaNs')
# reject extreme values
ev_ind = cf.reject_extreme_values(z_nofv_nonan)
t_nofv_nonan_noev = t_nofv_nonan[ev_ind]
y_nofv_nonan_noev = y_nofv_nonan[ev_ind]
z_nofv_nonan_noev = z_nofv_nonan[ev_ind]
print(
len(z) - len(ev_ind), ' Extreme Values',
'|1e7|')
# reject values outside global ranges:
global_min, global_max = cf.get_global_ranges(
r, sv)
# platform not in qc-table (parad_k_par)
# global_min = 0
# global_max = 2500
print('global ranges for : {}-{} {} - {}'.format(
r, sv, global_min, global_max))
if isinstance(global_min,
(int, float)) and isinstance(
global_max, (int, float)):
gr_ind = cf.reject_global_ranges(
z_nofv_nonan_noev, global_min, global_max)
t_nofv_nonan_noev_nogr = t_nofv_nonan_noev[
gr_ind]
y_nofv_nonan_noev_nogr = y_nofv_nonan_noev[
gr_ind]
z_nofv_nonan_noev_nogr = z_nofv_nonan_noev[
gr_ind]
else:
t_nofv_nonan_noev_nogr = t_nofv_nonan_noev
y_nofv_nonan_noev_nogr = y_nofv_nonan_noev
z_nofv_nonan_noev_nogr = z_nofv_nonan_noev
if len(z_nofv_nonan_noev) > 0:
if m == 'common_stream_placeholder':
sname = '-'.join((r, sv))
else:
sname = '-'.join((r, m, sv))
# group by depth range
sname = '_'.join((sname, sv_units))
# if sv != 'pressure':
# columns = ['tsec', 'dbar', str(sv)]
#
# # select depth bin size for the data group function
# bin_size = 10
# min_r = int(round(min(y_nofv_nonan_noev) - bin_size))
# max_r = int(round(max(y_nofv_nonan_noev) + bin_size))
# ranges = list(range(min_r, max_r, bin_size))
# groups, d_groups = gt.group_by_depth_range(t_nofv_nonan_noev_nogr, y_nofv_nonan_noev_nogr,
# z_nofv_nonan_noev_nogr, columns, ranges)
#
# if (ms.split('-')[0]) == (ps_df[0].values[0].split('-')[0]):
# if 'pressure' not in sv:
# print('final_stats_{}-{}-{}-{}'.format(r,
# ms.split('-')[0],
# ps_df[0].values[0].split('-')[0],
# sv))
# stat_data = groups.describe()[sv]
# stat_data.insert(loc=0, column='parameter', value=sv, allow_duplicates=False)
# stat_df = stat_df.append(stat_data)
# if sv == 'optical_backscatter':
# less_ind = z_nofv_nonan_noev < 0.0004
# print(sv, ' < 0.0004', len(less_ind))
# more_ind = z_nofv_nonan_noev > 0.01
# print(sv, ' > 0.01', len(more_ind))
# Plot all data
clabel = sv + " (" + sv_units + ")"
ylabel = y_name + " (" + y_unit + ")"
fig, ax = pf.plot_xsection(subsite,
t_nofv_nonan_noev,
y_nofv_nonan_noev,
z_nofv_nonan_noev,
clabel,
ylabel,
stdev=None)
ax.set_title((title + '\n' + t0 + ' - ' + t1),
fontsize=9)
pf.save_fig(save_dir, sname)
# Plot data with outliers removed
fig, ax = pf.plot_xsection(subsite,
t_nofv_nonan_noev_nogr,
y_nofv_nonan_noev_nogr,
z_nofv_nonan_noev_nogr,
clabel,
ylabel,
stdev=5)
ax.set_title((title + '\n' + t0 + ' - ' + t1),
fontsize=9)
sfile = '_'.join((sname, 'rmoutliers'))
pf.save_fig(save_dir, sfile)
# plot data with excluded time range removed
dr = pd.read_csv(
'https://datareview.marine.rutgers.edu/notes/export'
)
drn = dr.loc[dr.type == 'exclusion']
if len(drn) != 0:
subsite_node = '-'.join((subsite, r.split('-')[1]))
drne = drn.loc[drn.reference_designator.isin(
[subsite, subsite_node, r])]
t_ex = t_nofv_nonan_noev_nogr
y_ex = y_nofv_nonan_noev_nogr
z_ex = z_nofv_nonan_noev_nogr
for i, row in drne.iterrows():
sdate = cf.format_dates(row.start_date)
edate = cf.format_dates(row.end_date)
ts = np.datetime64(sdate)
te = np.datetime64(edate)
ind = np.where((t_ex < ts) | (t_ex > te), True,
False)
if len(ind) != 0:
t_ex = t_ex[ind]
z_ex = z_ex[ind]
y_ex = y_ex[ind]
fig, ax = pf.plot_xsection(subsite,
t_ex,
y_ex,
z_ex,
clabel,
ylabel,
stdev=None)
ax.set_title((title + '\n' + t0 + ' - ' + t1),
fontsize=9)
sfile = '_'.join((sname, 'rmsuspectdata'))
pf.save_fig(save_dir, sfile)
def main(url_list, sDir, plot_type, deployment_num, start_time, end_time, method_num, zdbar, n_std, inpercentile, zcell_size):
for i, u in enumerate(url_list):
print('\nUrl {} of {}: {}'.format(i + 1, len(url_list), u))
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]
# read URL to get data
datasets = cf.get_nc_urls([u])
datasets_sel = cf.filter_collocated_instruments(main_sensor, datasets)
# get sci data review list
dr_data = cf.refdes_datareview_json(r)
ps_df, n_streams = cf.get_preferred_stream_info(r)
# 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 dictionary for science variables from analysis file
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
for ii, d in enumerate(datasets_sel):
part_d = d.split('/')[-1]
print('\nDataset {} of {}: {}'.format(ii + 1, len(datasets_sel), part_d))
with xr.open_dataset(d, mask_and_scale=False) as ds:
ds = ds.swap_dims({'obs': 'time'})
fname, subsite, refdes, method, stream, deployment = cf.nc_attributes(d)
if method_num is not None:
if method != method_num:
print(method_num, method)
continue
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, ms.split('-')[0], deployment, ext)
else:
save_dir = os.path.join(sDir, array, subsite, refdes, plot_type, ms.split('-')[0], deployment)
cf.create_dir(save_dir)
texclude_dir = os.path.join(sDir, array, subsite, refdes, 'time_to_exclude')
cf.create_dir(texclude_dir)
# initialize an empty data array for science variables in dictionary
sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict, ms)
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)
sh['t'] = np.append(sh['t'], ds['time'].values) # t = ds['time'].values
sh['values'] = np.append(sh['values'], ds[var].values) # z = ds[var].values
y, y_unit, y_name = cf.add_pressure_to_dictionary_of_sci_vars(ds)
sh['pressure'] = np.append(sh['pressure'], y)
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)
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]
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')
colors = cm.rainbow(np.linspace(0, 1, len(vinfo['t'])))
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:
# reject erroneous data
dtime, zpressure, ndata, lenfv, lennan, lenev, lengr, global_min, global_max = \
cf.reject_erroneous_data(r, sv, t, y, z, fv)
# create 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)
# ... excluding timestamps
if 'scatter' in sv:
n_std = None #to use percentile
else:
n_std = n_std
# rejecting timestamps from percentile analysis
y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr, time_ex, \
t_nospct, z_nospct, y_nospct = cf.reject_timestamps_in_groups(groups, d_groups, n_std,
dtime, zpressure, ndata,
inpercentile)
print('{} using {} percentile of data grouped in {} dbar segments'.format(
len(zpressure) - len(z_nospct), inpercentile, zcell_size))
"""
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)
# reject time range from data portal file export
t_portal, z_portal, y_portal = cf.reject_timestamps_dataportal(subsite, r,
t_nospct, z_nospct, y_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))
"""
Plot data
"""
if len(t_array) > 0:
if m == 'common_stream_placeholder':
sname = '-'.join((sv, r))
else:
sname = '-'.join((sv, r, m))
xlabel = sv + " (" + sv_units + ")"
ylabel = y_name[0] + " (" + y_unit[0] + ")"
clabel = 'Time'
title = ' '.join((deployment, r, m))
# plot non-erroneous data
fig, ax = pf.plot_profiles(ndata, zpressure, dtime,
ylabel, xlabel, clabel, end_times, deployments, 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)
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' +
('(black) data average in {} dbar segments'.format(zcell_size)) + '\n' +
('(magenta) upper and lower {} percentile envelope in {} dbar segments'.format(
inpercentile, zcell_size)),)
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)
# plot excluding time ranges for suspect data
if len(z_nospct) != len(zpressure):
fig, ax = pf.plot_profiles(z_nospct, y_nospct, t_nospct,
ylabel, xlabel, clabel, end_times, deployments, stdev=None)
ax.set_title(title, fontsize=9)
leg_text = (
'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)
fig.tight_layout()
sfile = '_'.join(('rm_suspect_data', sname))
pf.save_fig(save_dir, sfile)
# plot excluding time ranges from data portal export
if len(z_nospct) - len(z_portal):
fig, ax = pf.plot_profiles(z_portal, y_portal, t_portal,
ylabel, xlabel, clabel, end_times, deployments, stdev=None)
ax.set_title(title, fontsize=9)
leg_text = ('excluded {} suspect data 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_v_suspect_data', sname))
pf.save_fig(save_dir, sfile)
# Plot excluding a selected depth value
if len(z_array) != len(z_array):
fig, ax = pf.plot_profiles(z_array, y_array, t_array,
ylabel, xlabel, clabel, end_times, deployments, stdev=None)
ax.set_title(title, fontsize=9)
leg_text = ('excluded {} suspect data in water depth greater than {} dbar'.format(len(y_ind), zdbar),)
ax.legend(leg_text, loc='upper center', bbox_to_anchor=(0.5, -0.17), fontsize=6)
fig.tight_layout()
sfile = '_'.join(('rm_depth_range', sname))
pf.save_fig(save_dir, sfile)
def main(url_list, sDir, plot_type, deployment_num, 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]
ps_df, n_streams = cf.get_preferred_stream_info(r)
# read in the analysis file
dr_data = cf.refdes_datareview_json(r)
# get end times of deployments
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']))
# get the list of data files and filter out collocated instruments and other streams chat
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)
'''
separate the data files by methods
'''
for ms in ms_list:
fdatasets_sel = [x for x in fdatasets if ms in x]
# create a dictionary for science variables from analysis file
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
# initialize an empty data array for science variables in dictionary
sci_vars_dict = cd.initialize_empty_arrays(stream_sci_vars_dict,
ms)
print('\nAppending data from files: {}'.format(ms))
y_unit = []
y_name = []
for fd in fdatasets_sel:
ds = xr.open_dataset(fd, mask_and_scale=False)
print(fd)
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)
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
save_dir = os.path.join(sDir, array, subsite, refdes,
plot_type,
ms.split('-')[0], deployment)
cf.create_dir(save_dir)
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)
# time
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')
# sci variable
z = ds[var].values
sh['t'] = np.append(sh['t'], t)
sh['values'] = np.append(sh['values'], z)
# add pressure to dictionary of sci vars
if 'MOAS' in subsite:
if 'CTD' in main_sensor: # for glider CTDs, pressure is a coordinate
pressure = 'sci_water_pressure_dbar'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = 'int_ctd_pressure'
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
else:
pressure = pf.pressure_var(ds, ds.data_vars.keys())
y = ds[pressure].values
if ds[pressure].units not in y_unit:
y_unit.append(ds[pressure].units)
if ds[pressure].long_name not in y_name:
y_name.append(ds[pressure].long_name)
sh['pressure'] = np.append(sh['pressure'], y)
if len(y_unit) != 1:
print('pressure unit varies UHHHHHHHHH')
else:
y_unit = y_unit[0]
if len(y_name) != 1:
print('pressure long name varies UHHHHHHHHH')
else:
y_name = y_name[0]
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]
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')
t = vinfo['t']
z = vinfo['values']
y = vinfo['pressure']
title = ' '.join((r, ms.split('-')[1]))
# Check if the array is all NaNs
if sum(np.isnan(z)) == len(z):
print('Array of all NaNs - skipping plot.')
# Check if the array is all fill values
elif len(z[z != fv]) == 0:
print('Array of all fill values - skipping plot.')
else:
# reject fill values
fv_ind = z != fv
y_nofv = y[fv_ind]
t_nofv = t[fv_ind]
z_nofv = z[fv_ind]
print(len(z) - len(fv_ind), ' fill values')
# reject NaNs
nan_ind = ~np.isnan(z)
t_nofv_nonan = t_nofv[nan_ind]
y_nofv_nonan = y_nofv[nan_ind]
z_nofv_nonan = z_nofv[nan_ind]
print(len(z) - len(nan_ind), ' NaNs')
# reject extreme values
ev_ind = cf.reject_extreme_values(z_nofv_nonan)
t_nofv_nonan_noev = t_nofv_nonan[ev_ind]
colors = cm.rainbow(
np.linspace(0, 1, len(t_nofv_nonan_noev)))
y_nofv_nonan_noev = y_nofv_nonan[ev_ind]
z_nofv_nonan_noev = z_nofv_nonan[ev_ind]
print(
len(z) - len(ev_ind), ' Extreme Values',
'|1e7|')
if len(y_nofv_nonan_noev) > 0:
if m == 'common_stream_placeholder':
sname = '-'.join((r, sv))
else:
sname = '-'.join((r, m, sv))
# Plot all data
ylabel = y_name + " (" + y_unit + ")"
xlabel = sv + " (" + sv_units + ")"
clabel = 'Time'
clabel = sv + " (" + sv_units + ")"
fig, ax = pf.plot_profiles(z_nofv_nonan_noev,
y_nofv_nonan_noev,
colors,
xlabel,
ylabel,
stdev=None)
ax.set_title((
title + '\n' + str(deployment_num) + ': ' + t0 +
' - ' + t1 + '\n' +
'used bin = 2 dbar to calculate an average profile (black line) and 3-STD envelope (shaded area)'
),
fontsize=9)
# group by depth range
columns = ['time', 'pressure', str(sv)]
# ranges = [0, 50, 100, 200, 400, 600]
ranges = list(
range(int(round(min(y_nofv_nonan_noev))),
int(round(max(y_nofv_nonan_noev))), 1))
groups, d_groups = gt.group_by_depth_range(
t_nofv_nonan_noev, y_nofv_nonan_noev,
z_nofv_nonan_noev, columns, ranges)
# describe_file = '_'.join((sname, 'statistics.csv'))
# # groups.describe().to_csv(save_dir + '/' + describe_file)
ind = groups.describe()[sv]['mean'].notnull()
groups.describe()[sv][ind].to_csv(
'{}/{}_statistics.csv'.format(save_dir, sname),
index=True)
tm = 1
fig, ax = pyplot.subplots(nrows=2, ncols=1)
pyplot.margins(y=.08, x=.02)
pyplot.grid()
y_avg, n_avg, n_min, n_max, n0_std, n1_std, l_arr = [], [], [], [], [], [], []
for ii in range(len(groups)):
nan_ind = d_groups[ii + tm].notnull()
xtime = d_groups[ii + tm][nan_ind]
colors = cm.rainbow(np.linspace(0, 1, len(xtime)))
ypres = d_groups[ii + tm + 1][nan_ind]
nval = d_groups[ii + tm + 2][nan_ind]
tm += 2
# fig, ax = pf.plot_xsection(subsite, xtime, ypres, nval, clabel, ylabel, stdev=None)
# ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9)
# pf.plot_profiles(nval, ypres, colors, ylabel, clabel, stdev=None)
# ax.set_title((title + '\n' + t0 + ' - ' + t1), fontsize=9)
ind2 = cf.reject_outliers(nval, 5)
xD = nval[ind2]
yD = ypres[ind2]
nZ = colors[ind2]
outliers = str(len(nval) - len(xD))
leg_text = ('removed {} outliers (SD={})'.format(
outliers, stdev), )
ax.scatter(xD, yD, c=nZ, s=2, edgecolor='None')
ax.invert_yaxis()
ax.set_xlabel(clabel, fontsize=9)
ax.set_ylabel(ylabel, fontsize=9)
ax.legend(leg_text, loc='best', fontsize=6)
ax.set_title((title + '\n' + t0 + ' - ' + t1),
fontsize=9)
l_arr.append(
len(nval)
) # count of data to filter out small groups
y_avg.append(ypres.mean())
n_avg.append(nval.mean())
n_min.append(nval.min())
n_max.append(nval.max())
n0_std.append(nval.mean() + 3 * nval.std())
n1_std.append(nval.mean() - 3 * nval.std())
ax.plot(n_avg, y_avg, '-k')
# ax.plot(n_min, y_avg, '-b')
# ax.plot(n_max, y_avg, '-b')
ax.fill_betweenx(y_avg,
n0_std,
n1_std,
color='m',
alpha=0.2)
sfile = '_'.join((sname, 'statistics'))
pf.save_fig(save_dir, sfile)