def point_comparisons_at_outlets(hdf_folder="/home/huziy/skynet3_rech1/hdf_store"): start_year = 1979 end_year = 1981 sim_name_to_file_name = { # "CRCM5-R": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r_spinup.hdf", # "CRCM5-HCD-R": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r_spinup2.hdf", "CRCM5-HCD-RL": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf", "CRCM5-HCD-RL-INTFL": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_do_not_discard_small.hdf", # "SANI=10000, ignore THFC": # "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_sani-10000_not_care_about_thfc.hdf", # "CRCM5-HCD-RL-ERA075": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ecoclimap_era075.hdf", "SANI=10000": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_sani-10000.hdf" # "CRCM5-HCD-RL-ECOCLIMAP": "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ecoclimap.hdf" } path0 = os.path.join(hdf_folder, list(sim_name_to_file_name.items())[0][1]) path1 = os.path.join(hdf_folder, list(sim_name_to_file_name.items())[1][1]) flow_directions = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_FLOW_DIRECTIONS_NAME) lake_fraction = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_LAKE_FRACTION_NAME) slope = analysis.get_array_from_file(path=path1, var_name=infovar.HDF_SLOPE_NAME) lons2d, lats2d, _ = analysis.get_basemap_from_hdf(file_path=path0) cell_manager = CellManager(flow_directions, lons2d=lons2d, lats2d=lats2d) mp_list = cell_manager.get_model_points_of_outlets(lower_accumulation_index_limit=10) assert len(mp_list) > 0 # Get the accumulation indices so that the most important outlets can be identified acc_ind_list = [np.sum(cell_manager.get_mask_of_upstream_cells_connected_with_by_indices(mp.ix, mp.jy)) for mp in mp_list] for mp, acc_ind in zip(mp_list, acc_ind_list): mp.acc_index = acc_ind mp_list.sort(key=lambda x: x.acc_index) # do not take global lake cells into consideration, and discard points with slopes 0 or less mp_list = [mp for mp in mp_list if lake_fraction[mp.ix, mp.jy] < 0.6 and slope[mp.ix, mp.jy] >= 0] mp_list = mp_list[-12:] # get 12 most important outlets print("The following outlets were chosen for analysis") pattern = "({0}, {1}): acc_index = {2} cells; fldr = {3}; lake_fraction = {4}" for mp in mp_list: print(pattern.format(mp.ix, mp.jy, mp.acc_index, cell_manager.flow_directions[mp.ix, mp.jy], lake_fraction[mp.ix, mp.jy])) draw_model_comparison(model_points=mp_list, sim_name_to_file_name=sim_name_to_file_name, hdf_folder=hdf_folder, start_year=start_year, end_year=end_year, cell_manager=cell_manager)
def main(): data_path = "/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5" start_year = 1980 end_year = 2010 vname = "TRAF" level_index = 0 fldr = analysis.get_array_from_file(data_path, var_name="flow_direction") lkfr = analysis.get_array_from_file(data_path, var_name="lake_fraction") the_mask = np.ma.masked_all_like(fldr) the_mask[fldr > 0] = (1 - lkfr)[fldr > 0] ser = analysis.get_area_mean_timeseries(hdf_path=data_path, var_name=vname, level_index=level_index, start_year=start_year, end_year=end_year, the_mask=the_mask) monthly_ser = ser.groupby(lambda d: datetime(d.year, d.month, 15)).mean() # do the plotting plot_utils.apply_plot_params() fig = plt.figure() monthly_ser = monthly_ser * 24 * 3600 # convert to mm/day monthly_ser.groupby(lambda d: d.month).plot() ax = plt.gca() assert isinstance(ax, Axes) ax.grid() fig.savefig(data_path[:-5] + "_{}_level_index_{}_{}-{}_timeseries.png".format(vname, level_index, start_year, end_year), transparent=True, dpi=common_plot_params.FIG_SAVE_DPI, bbox_inches="tight") plt.show()
def main(): data_path = "/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5" start_year = 1980 end_year = 2010 vname = "TRAF" level_index = 0 fldr = analysis.get_array_from_file(data_path, var_name="flow_direction") lkfr = analysis.get_array_from_file(data_path, var_name="lake_fraction") the_mask = np.ma.masked_all_like(fldr) the_mask[fldr > 0] = (1 - lkfr)[fldr > 0] ser = analysis.get_area_mean_timeseries(hdf_path=data_path, var_name=vname, level_index=level_index, start_year=start_year, end_year=end_year, the_mask=the_mask) monthly_ser = ser.groupby(lambda d: datetime(d.year, d.month, 15)).mean() # do the plotting plot_utils.apply_plot_params() fig = plt.figure() monthly_ser = monthly_ser * 24 * 3600 # convert to mm/day monthly_ser.groupby(lambda d: d.month).plot() ax = plt.gca() assert isinstance(ax, Axes) ax.grid() fig.savefig(data_path[:-5] + "_{}_level_index_{}_{}-{}_timeseries.png".format( vname, level_index, start_year, end_year), transparent=True, dpi=common_plot_params.FIG_SAVE_DPI, bbox_inches="tight") plt.show()
def main(): # Define the simulations to be validated r_config = RunConfig( data_path= "/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5", start_year=1990, end_year=2010, label="CRCM5-L1") r_config_list = [r_config] r_config = RunConfig( data_path= "/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5", start_year=1990, end_year=2010, label="CRCM5-NL") r_config_list.append(r_config) bmp_info = analysis.get_basemap_info_from_hdf(file_path=r_config.data_path) bmp_info.should_draw_grey_map_background = True bmp_info.should_draw_basin_boundaries = False bmp_info.map_bg_color = "0.75" station_ids = ["104001", "093806", "093801", "081002", "081007", "080718"] # get river network information used in the model flow_directions = analysis.get_array_from_file( r_config.data_path, var_name=infovar.HDF_FLOW_DIRECTIONS_NAME) accumulation_area_km2 = analysis.get_array_from_file( path=r_config.data_path, var_name=infovar.HDF_ACCUMULATION_AREA_NAME) cell_manager = CellManager(flow_dirs=flow_directions, lons2d=bmp_info.lons, lats2d=bmp_info.lats, accumulation_area_km2=accumulation_area_km2) # Get the list of stations to indicate on the bias map stations = cehq_station.read_station_data(start_date=None, end_date=None, selected_ids=station_ids) """:type : list[Station]""" xx, yy = bmp_info.get_proj_xy() station_to_modelpoint = cell_manager.get_model_points_for_stations( station_list=stations) upstream_edges = cell_manager.get_upstream_polygons_for_points( model_point_list=station_to_modelpoint.values(), xx=xx, yy=yy) bmp_info.draw_colorbar_for_each_subplot = True # Validate temperature, precip and swe obs_path_anusplin = "/home/huziy/skynet3_rech1/anusplin_links" obs_path_swe = "data/swe_ross_brown/swe.nc" model_var_to_obs_path = OrderedDict([("TT", obs_path_anusplin), ("I5", obs_path_swe)]) model_var_to_season = OrderedDict([ ("TT", OrderedDict([("Spring", range(3, 6))])), ("I5", OrderedDict([("Winter", [1, 2, 12])])) ]) vname_to_obs_data = {} # parameters that won't change in the loop over variable names params_const = dict(rconfig=r_config, bmp_info=bmp_info) for vname, obs_path in model_var_to_obs_path.items(): season_to_obs_data = get_seasonal_clim_obs_data( vname=vname, obs_path=obs_path, season_to_months=model_var_to_season[vname], **params_const) # Comment swe over lakes, since I5 calculated only for land if vname in [ "I5", ]: for season in season_to_obs_data: season_to_obs_data[season] = maskoceans( bmp_info.lons, bmp_info.lats, season_to_obs_data[season], inlands=True) vname_to_obs_data[vname] = season_to_obs_data # Plotting plot_all_vars_in_one_fig = True fig = None gs = None if plot_all_vars_in_one_fig: plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=20) fig = plt.figure() ncols = len(model_var_to_obs_path) + 1 gs = GridSpec(len(r_config_list), ncols, width_ratios=(ncols - 1) * [ 1., ] + [ 0.05, ]) else: plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=25) station_x_list = [] station_y_list = [] mvarname_to_cs = {} for row, r_config in enumerate(r_config_list): for col, mname in enumerate(model_var_to_obs_path): row_axes = [ fig.add_subplot(gs[row, col]), ] mvarname_to_cs[mname] = compare_vars( vname_model=mname, vname_to_obs=vname_to_obs_data, r_config=r_config, season_to_months=model_var_to_season[mname], bmp_info_agg=bmp_info, axes_list=row_axes) # -1 in order to exclude colorbars for the_ax in row_axes: the_ax.set_title(the_ax.get_title() + ", {}".format( infovar.get_long_display_label_for_var(mname))) # Need titles only for the first row if row > 0: the_ax.set_title("") if col == 0: the_ax.set_ylabel(r_config.label) else: the_ax.set_ylabel("") draw_upstream_area_bounds(the_ax, upstream_edges, color="g") if len(station_x_list) == 0: for the_station in stations: xst, yst = bmp_info.basemap(the_station.longitude, the_station.latitude) station_x_list.append(xst) station_y_list.append(yst) bmp_info.basemap.scatter(station_x_list, station_y_list, c="g", ax=the_ax, s=20, zorder=10, alpha=0.5) # Save the figure if necessary if plot_all_vars_in_one_fig: if not img_folder.is_dir(): img_folder.mkdir(parents=True) fig_path = img_folder.joinpath("{}.png".format( "_".join(model_var_to_obs_path))) with fig_path.open("wb") as figfile: fig.savefig(figfile, format="png", bbox_inches="tight") plt.close(fig)
def main(): start_year = 1980 end_year = 2003 months_of_obs = [12, 1, 2, 3, 4, 5] r_config = RunConfig( data_path="/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", start_year=start_year, end_year=end_year, label="ERAI-CRCM5-L" ) var_name = "LC" bmp_info = analysis.get_basemap_info(r_config=r_config) lkid_to_mask = get_lake_masks(bmp_info.lons, bmp_info.lats) cell_area_m2 = analysis.get_array_from_file(path=r_config.data_path, var_name="cell_area_m2") # read the model data lkid_to_ts_model = {} for lkid, the_mask in lkid_to_mask.items(): lkid_to_ts_model[lkid] = analysis.get_area_mean_timeseries(r_config.data_path, var_name=var_name, the_mask=the_mask * cell_area_m2, start_year=start_year, end_year=end_year) df = lkid_to_ts_model[lkid] # remove the last December df = df.select(lambda d: not (d.year == end_year and d.month == 12)) # remove the first Jan and Feb df = df.select(lambda d: not (d.year == start_year and d.month in [1, 2])) # remove the Feb 29th df = df.select(lambda d: not (d.month == 2 and d.day == 29)) # select months of interest df = df.select(lambda d: d.month in months_of_obs) # calculate the climatology df = df.groupby(lambda d: datetime(2001 if d.month == 12 else 2002, d.month, d.day)).mean() df.sort_index(inplace=True) lkid_to_ts_model[lkid] = df * 100 # read obs data and calculate climatology lkid_to_ts_obs = {} for lkid in LAKE_IDS: lkid_to_ts_obs[lkid] = GL_obs_timeseries.get_ts_from_file(path=os.path.join(OBS_DATA_FOLDER, "{}-30x.TXT".format(lkid)), start_year=start_year, end_year=end_year - 1) # get the climatology dfm = lkid_to_ts_obs[lkid].mean(axis=1) dfm.index = [datetime(2001, 1, 1) + timedelta(days=int(jd - 1)) for jd in dfm.index] lkid_to_ts_obs[lkid] = dfm # plotting plot_utils.apply_plot_params(font_size=10) fig = plt.figure() gs = GridSpec(nrows=len(lkid_to_ts_model), ncols=2) for row, lkid in enumerate(lkid_to_ts_model): ax = fig.add_subplot(gs[row, 0]) mod = lkid_to_ts_model[lkid] obs = lkid_to_ts_obs[lkid] print(obs.index) print(obs.values) ax.plot(mod.index, mod.values, label=r_config.label, color="r", lw=2) ax.plot(obs.index, obs.values, label="NOAA NIC/CIS", color="k", lw=2) if row == 0: ax.legend() ax.set_title(lkid) ax.xaxis.set_major_formatter(DateFormatter("%b")) fig.tight_layout() fig.savefig(os.path.join(img_folder, "GL_ice-cover-validation.png"), bbox_inches="tight", dpi=common_plot_params.FIG_SAVE_DPI)
def main(): season_to_months = DEFAULT_SEASON_TO_MONTHS r_config = RunConfig( data_path="/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5", start_year=1990, end_year=2010, label="CRCM5-L" ) bmp_info = analysis.get_basemap_info_from_hdf(file_path=r_config.data_path) bmp_info.should_draw_grey_map_background = True bmp_info.should_draw_basin_boundaries = False bmp_info.map_bg_color = "0.75" station_ids = [ "104001", "093806", "093801", "081002", "081007", "080718" ] # get river network information used in the model flow_directions = analysis.get_array_from_file(r_config.data_path, var_name=infovar.HDF_FLOW_DIRECTIONS_NAME) accumulation_area_km2 = analysis.get_array_from_file(path=r_config.data_path, var_name=infovar.HDF_ACCUMULATION_AREA_NAME) cell_manager = CellManager(flow_dirs=flow_directions, lons2d=bmp_info.lons, lats2d=bmp_info.lats, accumulation_area_km2=accumulation_area_km2) # Get the list of stations to indicate on the bias map stations = cehq_station.read_station_data( start_date=None, end_date=None, selected_ids=station_ids ) """:type : list[Station]""" xx, yy = bmp_info.get_proj_xy() station_to_modelpoint = cell_manager.get_model_points_for_stations(station_list=stations) upstream_edges = cell_manager.get_upstream_polygons_for_points( model_point_list=station_to_modelpoint.values(), xx=xx, yy=yy) # Validate temperature, precip and swe obs_path_anusplin = "/home/huziy/skynet3_rech1/anusplin_links" obs_path_swe = "data/swe_ross_brown/swe.nc" model_var_to_obs_path = OrderedDict([ ("TT", obs_path_anusplin), # ("PR", obs_path_anusplin), ("I5", obs_path_swe) ]) vname_to_obs_data = {} # parameters that won't change in the loop over variable names params_const = dict(rconfig=r_config, bmp_info=bmp_info, season_to_months=season_to_months) for vname, obs_path in model_var_to_obs_path.items(): season_to_obs_data = get_seasonal_clim_obs_data(vname=vname, obs_path=obs_path, **params_const) # Comment swe over lakes, since I5 calculated only for land if vname in ["I5", ]: for season in season_to_obs_data: season_to_obs_data[season] = maskoceans(bmp_info.lons, bmp_info.lats, season_to_obs_data[season], inlands=True) vname_to_obs_data[vname] = season_to_obs_data # Plotting plot_all_vars_in_one_fig = True fig = None gs = None row_axes = [] ncols = None if plot_all_vars_in_one_fig: plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=20) fig = plt.figure() ncols = len(season_to_months) + 1 gs = GridSpec(len(model_var_to_obs_path), ncols, width_ratios=(ncols - 1) * [1., ] + [0.05, ]) else: plot_utils.apply_plot_params(font_size=12, width_pt=None, width_cm=25, height_cm=25) row = 0 station_x_list = [] station_y_list = [] for mname in model_var_to_obs_path: if plot_all_vars_in_one_fig: row_axes = [fig.add_subplot(gs[row, col]) for col in range(ncols)] compare_vars(vname_model=mname, vname_to_obs=vname_to_obs_data, r_config=r_config, season_to_months=season_to_months, bmp_info_agg=bmp_info, axes_list=row_axes) # -1 in order to exclude colorbars for the_ax in row_axes[:-1]: # Need titles only for the first row if row > 0: the_ax.set_title("") draw_upstream_area_bounds(the_ax, upstream_edges) if len(station_x_list) == 0: for the_station in stations: xst, yst = bmp_info.basemap(the_station.longitude, the_station.latitude) station_x_list.append(xst) station_y_list.append(yst) bmp_info.basemap.scatter(station_x_list, station_y_list, c="g", ax=the_ax, s=5, zorder=10, alpha=0.5) # Hide fall swe if mname in ["I5"]: row_axes[-2].set_visible(False) row += 1 # Save the figure if necessary if plot_all_vars_in_one_fig: fig_path = img_folder.joinpath("{}.png".format("_".join(model_var_to_obs_path))) with fig_path.open("wb") as figfile: fig.savefig(figfile, format="png", bbox_inches="tight") plt.close(fig)
def get_mean_diffs(interflow_data_path="", base_data_path="", start_year=1980, end_year=2010, months_of_interest=(4, 5, 6, 7, 8, 9), delete_cache=True): """ Get mean differences for fixed variables, between interflow_data_path and base_data_path files :param interflow_data_path: :param base_data_path: :param start_year: :param end_year: :param months_of_interest: :return: """ # Build the name of the cache file cache_file = "cache_extr_intf_effect{}-{}_{}.bin".format(start_year, end_year, "-".join(str(m) for m in months_of_interest)) # Do not use caching by default if delete_cache: os.remove(cache_file) if os.path.isfile(cache_file): return pickle.load(open(cache_file)) precip_limit = 0.0 # at least it should rain tt_limit = 0 # and the oil should not be frozen traf_diff = None # surface runoff difference prcip_diff = None drainage_diff = None # drainage difference i1_diff = None # soil moisture difference months_query = "{}".format("|".join(["(month=={})".format(m) for m in months_of_interest])) year_query = "(year >= {}) & (year <= {})".format(start_year, end_year) print("months_query = {}".format(months_query)) depth_to_bedrock = pt_analysis.get_array_from_file(base_data_path, var_name=infovar.HDF_DEPTH_TO_BEDROCK_NAME) with tb.open_file(interflow_data_path) as h_intf: pr_intf_table = h_intf.get_node("/", "PR") tt_intf_table = h_intf.get_node("/", "TT") traf_intf_table = h_intf.get_node("/", "TRAF") tdra_intf_table = h_intf.get_node("/", "TDRA") i1_intf_table = h_intf.get_node("/", "I1") assert isinstance(pr_intf_table, tb.Table) assert isinstance(tt_intf_table, tb.Table) assert isinstance(traf_intf_table, tb.Table) assert isinstance(tdra_intf_table, tb.Table) print(len(pr_intf_table), len(tt_intf_table), len(traf_intf_table)) with tb.open_file(base_data_path) as h_nointf: pr_nointf_table = h_nointf.get_node("/", "PR") tt_nointf_table = h_nointf.get_node("/", "TT") traf_nointf_table = h_nointf.get_node("/", "TRAF") tdra_nointf_table = h_nointf.get_node("/", "TDRA") i1_nointf_table = h_nointf.get_node("/", "I1") assert isinstance(pr_nointf_table, tb.Table) assert isinstance(tt_nointf_table, tb.Table) assert isinstance(traf_nointf_table, tb.Table) assert isinstance(tdra_nointf_table, tb.Table) for rownum, pr_intf_row in enumerate(pr_intf_table.where("({}) & {}".format(months_query, year_query))): year, month, day, hour = [pr_intf_row[k] for k in ["year", "month", "day", "hour"]] # print year, month, day, hour pr_intf_field = pr_intf_row["field"] tt_intf_field = None traf_intf_field = None tdra_intf_field = None i1_intf_field = None pr_nointf_field = None tt_nointf_field = None traf_nointf_field = None tdra_nointf_field = None i1_nointf_field = None # Get air temperature and precipitation for the same time tt_query = "(year == {}) & (month == {}) & (day == {}) & (hour == {})".format(year, month, day, hour) traf_query = "{} & (level_index == {})".format(tt_query, 0) for tt_row in tt_intf_table.where(tt_query): tt_intf_field = tt_row["field"] break # print tt_intf_field.min(), tt_intf_field.max() for traf_row in traf_intf_table.where(traf_query): traf_intf_field = traf_row["field"] break for tdra_row in tdra_intf_table.where(traf_query): tdra_intf_field = tdra_row["field"] break for i1_row in i1_intf_table.where(traf_query): i1_intf_field = i1_row["field"] break # for no interflow simulation for tt_row in tt_nointf_table.where(tt_query): tt_nointf_field = tt_row["field"] break for pr_row in pr_nointf_table.where(tt_query): pr_nointf_field = pr_row["field"] break for traf_row in traf_nointf_table.where(traf_query): traf_nointf_field = traf_row["field"] break for tdra_row in tdra_nointf_table.where(traf_query): tdra_nointf_field = tdra_row["field"] break for i1_row in i1_nointf_table.where(traf_query): i1_nointf_field = i1_row["field"] break if traf_diff is None: traf_diff = np.zeros(pr_intf_field.shape) prcip_diff = np.zeros(pr_intf_field.shape) drainage_diff = np.zeros(pr_intf_field.shape) i1_diff = np.zeros(pr_intf_field.shape) points_of_interest = ( (pr_intf_field > precip_limit) & (pr_nointf_field > precip_limit) & (tt_intf_field > tt_limit) & (tt_nointf_field > tt_limit) & (abs(pr_intf_field - pr_nointf_field) < 0.01 * (pr_intf_field + pr_nointf_field) / 2.0) ) if rownum % 100 == 0: print("Precipitation ranges in M/s") print(pr_intf_field.min(), pr_intf_field.max()) print(pr_nointf_field.min(), pr_nointf_field.max()) if traf_intf_field is None: print("intf field is none") print(traf_query) if traf_nointf_field is None: print("nointf field is none") print(traf_query) traf_diff[points_of_interest] += traf_intf_field[points_of_interest] - \ traf_nointf_field[points_of_interest] prcip_diff[points_of_interest] += pr_intf_field[points_of_interest] - \ pr_nointf_field[points_of_interest] drainage_diff[points_of_interest] += tdra_intf_field[points_of_interest] - \ tdra_nointf_field[points_of_interest] i1_diff[points_of_interest] += i1_intf_field[points_of_interest] - \ i1_nointf_field[points_of_interest] # if rownum % 100 == 0 and debug_plots: # fig = plt.figure() # im = plt.pcolormesh(traf_diff.transpose() * 3 * 60 * 60) # plt.colorbar(im) # plt.savefig("{}/{}.jpg".format(img_dir, rownum)) # plt.close(fig) # # plt.figure() # im = plt.pcolormesh(traf_intf_field.transpose() * 60 * 60 * 24) # plt.colorbar(im) # plt.savefig("{}/traf_{}.jpg".format(img_dir, rownum)) # plt.close(fig) pickle.dump([traf_diff, prcip_diff, drainage_diff, i1_diff], open(cache_file, "w")) return traf_diff, prcip_diff, drainage_diff, i1_diff
def compare(paths=None, path_to_control_data=None, control_label="", labels=None, varnames=None, levels=None, months_of_interest=None, start_year=None, end_year=None): """ Comparing 2D fields :param paths: paths to the simulation results :param varnames: :param labels: Display name for each simulation (number of labels should be equal to the number of paths) :param path_to_control_data: the path with which the comparison done i.e. a in the following formula delta = (x - a)/a * 100% generates one image file per variable (in the folder images_for_lake-river_paper): compare_varname_<control_label>_<label1>_..._<labeln>_startyear_endyear.png """ # get coordinate data (assumes that all the variables and runs have the same coordinates) lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=path_to_control_data) x, y = basemap(lons2d, lats2d) lake_fraction = analysis.get_array_from_file(path=path_to_control_data, var_name="lake_fraction") if lake_fraction is None: lake_fraction = np.zeros(lons2d.shape) ncolors = 10 # +1 to include white diff_cmap = cm.get_cmap("RdBu_r", ncolors + 1) for var_name, level in zip(varnames, levels): sfmt = infovar.get_colorbar_formatter(var_name) control_means = analysis.get_mean_2d_fields_for_months(path=path_to_control_data, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) control_mean = np.mean(control_means, axis=0) fig = plt.figure() assert isinstance(fig, Figure) gs = gridspec.GridSpec(2, len(paths) + 1, wspace=0.5) # plot the control ax = fig.add_subplot(gs[0, 0]) assert isinstance(ax, Axes) ax.set_title("{0}".format(control_label)) ax.set_ylabel("Mean: $X_{0}$") to_plot = infovar.get_to_plot(var_name, control_mean, lake_fraction=lake_fraction, mask_oceans=True, lons=lons2d, lats=lats2d) # determine colorabr extent and spacing field_cmap, field_norm = infovar.get_colormap_and_norm_for(var_name, to_plot, ncolors=ncolors) basemap.pcolormesh(x, y, to_plot, cmap=field_cmap, norm=field_norm) cb = basemap.colorbar(format=sfmt) assert isinstance(cb, Colorbar) # cb.ax.set_ylabel(infovar.get_units(var_name)) units = infovar.get_units(var_name) info = "Variable:" \ "\n{0}" \ "\nPeriod: {1}-{2}" \ "\nMonths: {3}" \ "\nUnits: {4}" info = info.format(infovar.get_long_name(var_name), start_year, end_year, ",".join([datetime(2001, m, 1).strftime("%b") for m in months_of_interest]), units) ax.annotate(info, xy=(0.1, 0.3), xycoords="figure fraction") sel_axes = [ax] for the_path, the_label, column in zip(paths, labels, list(range(1, len(paths) + 1))): means_for_years = analysis.get_mean_2d_fields_for_months(path=the_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year) the_mean = np.mean(means_for_years, axis=0) # plot the mean value ax = fig.add_subplot(gs[0, column]) sel_axes.append(ax) ax.set_title("{0}".format(the_label)) to_plot = infovar.get_to_plot(var_name, the_mean, lake_fraction=lake_fraction, mask_oceans=True, lons=lons2d, lats=lats2d) basemap.pcolormesh(x, y, to_plot, cmap=field_cmap, norm=field_norm) ax.set_ylabel("Mean: $X_{0}$".format(column)) cb = basemap.colorbar(format=sfmt) # cb.ax.set_ylabel(infovar.get_units(var_name)) # plot the difference ax = fig.add_subplot(gs[1, column]) sel_axes.append(ax) ax.set_ylabel("$X_{0} - X_0$".format(column)) # #Mask only if the previous plot (means) is masked thediff = the_mean - control_mean if hasattr(to_plot, "mask"): to_plot = np.ma.masked_where(to_plot.mask, thediff) else: to_plot = thediff if var_name == "PR": # convert to mm/day to_plot = infovar.get_to_plot(var_name, to_plot, mask_oceans=False) vmin = np.ma.min(to_plot) vmax = np.ma.max(to_plot) d = max(abs(vmin), abs(vmax)) vmin = -d vmax = d field_norm, bounds, vmn_nice, vmx_nice = infovar.get_boundary_norm(vmin, vmax, diff_cmap.N, exclude_zero=False) basemap.pcolormesh(x, y, to_plot, cmap=diff_cmap, norm=field_norm, vmin=vmn_nice, vmax=vmx_nice) cb = basemap.colorbar(format=sfmt) t, pval = ttest_ind(means_for_years, control_means, axis=0) sig = pval < 0.1 basemap.contourf(x, y, sig.astype(int), nlevels=2, hatches=["+", None], colors="none") # cb.ax.set_ylabel(infovar.get_units(var_name)) # plot coastlines for the_ax in sel_axes: basemap.drawcoastlines(ax=the_ax, linewidth=common_plot_params.COASTLINE_WIDTH) # depends on the compared simulations and the months of interest fig_file_name = "compare_{0}_{1}_{2}_months-{3}.jpeg".format(var_name, control_label, "_".join(labels), "-".join([str(m) for m in months_of_interest])) figpath = os.path.join(images_folder, fig_file_name) fig.savefig(figpath, dpi=cpp.FIG_SAVE_DPI, bbox_inches="tight") plt.close(fig)
def plot_control_and_differences_in_one_panel_for_all_seasons_for_all_vars( varnames=None, levels=None, season_to_months=None, start_year=None, end_year=None): season_list = list(season_to_months.keys()) pvalue_max = 0.1 # crcm5-r vs crcm5-hcd-r # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r_spinup.hdf" # control_label = "CRCM5-R" # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r_spinup2.hdf", ] # labels = ["CRCM5-HCD-R"] # crcm5-hcd-rl vs crcm5-hcd-r # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r_spinup2.hdf" # control_label = "CRCM5-HCD-R" # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf", ] # labels = ["CRCM5-HCD-RL"] # compare simulations with and without interflow # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf" # control_label = "CRCM5-HCD-RL" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_do_not_discard_small.hdf", ] # labels = ["CRCM5-HCD-RL-INTFL"] # very high hydr cond # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_do_not_discard_small.hdf" # control_label = "CRCM5-HCD-RL-INTFL" ## # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_sani-10000.hdf", ] # labels = ["CRCM5-HCD-RL-INTFL-sani=10000"] # Interflow effect # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf" # control_label = "CRCM5-HCD-RL" # ## # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ITFS.hdf5", ] # labels = ["ITFS"] # total lake effect # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5" # control_label = "CRCM5-NL" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", ] # labels = ["CRCM5-L2", ] # lake effect (lake-atm interactions) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5" # control_label = "CRCM5-R" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5", ] # labels = ["CRCM5-HCD-R", ] # lake effect (lake-river interactions) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5" # control_label = "CRCM5-L1" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", ] # labels = ["CRCM5-HCD-L2", ] # interflow effect () control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5" control_label = "CRCM5-L2" paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5", ] labels = ["CRCM5-L2I", ] # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS_avoid_truncation1979-1989.hdf5", ] # labels = ["CRCM5-HCD-RL-INTFb", ] # interflow effect (avoid truncation and bigger slopes) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5" # control_label = "CRCM5-HCD-RL-INTF" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS_avoid_truncation1979-1989.hdf5", ] # labels = ["CRCM5-HCD-RL-INTF-improved", ] # row_labels = [ r"{} vs {}".format(s, control_label) for s in labels ] print(labels) # varnames = ["QQ", ] # levels = [None, ] assert len(levels) == len(varnames) lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=control_path) x, y = basemap(lons2d, lats2d) # save the domain properties for reuse domain_props = DomainProperties() domain_props.basemap = basemap domain_props.lons2d = lons2d domain_props.lats2d = lats2d domain_props.x = x domain_props.y = y lake_fraction = analysis.get_array_from_file(path=control_path, var_name=infovar.HDF_LAKE_FRACTION_NAME) dpth_to_bedrock = analysis.get_array_from_file(path=control_path, var_name=infovar.HDF_DEPTH_TO_BEDROCK_NAME) assert dpth_to_bedrock is not None if lake_fraction is None: lake_fraction = np.zeros(lons2d.shape) ncolors = 10 # +1 to include white diff_cmap = cm.get_cmap("RdBu", ncolors + 1) # Do the plotting for each variable fig = plt.figure() assert isinstance(fig, Figure) # plot the control data ncols = len(season_list) + 1 # +1 is for the colorbar gs = gridspec.GridSpec(len(varnames), ncols, width_ratios=[1.0, ] * (ncols - 1) + [0.07], top=0.95) lev_width_3d = np.ones(dpth_to_bedrock.shape + infovar.soil_layer_widths_26_to_60.shape) lev_width_3d *= infovar.soil_layer_widths_26_to_60[np.newaxis, np.newaxis, :] lev_bot_3d = lev_width_3d.cumsum(axis=2) correction = -lev_bot_3d + dpth_to_bedrock[:, :, np.newaxis] # Apply the correction only at points where the layer bottom is lower than # the bedrock lev_width_3d[correction < 0] += correction[correction < 0] lev_width_3d[lev_width_3d < 0] = 0 # plot the plots one file per variable for var_name, level, the_row in zip(varnames, levels, list(range(len(varnames)))): sfmt = infovar.get_colorbar_formatter(var_name) season_to_control_mean = {} label_to_season_to_difference = {} label_to_season_to_significance = {} try: # Calculate the difference for each season, and save the results to dictionaries # to access later when plotting for season, months_of_interest in season_to_months.items(): print("working on season: {0}".format(season)) control_means = analysis.get_mean_2d_fields_for_months(path=control_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) control_mean = np.mean(control_means, axis=0) control_mean = infovar.get_to_plot(var_name, control_mean, lake_fraction=domain_props.lake_fraction, lons=lons2d, lats=lats2d, level_width_m=lev_width_3d[:, :, level]) # multiply by the number of days in a season for PR and TRAF to convert them into mm from mm/day if var_name in ["PR", "TRAF", "TDRA"]: control_mean *= get_num_days(months_of_interest) infovar.change_units_to(varnames=[var_name, ], new_units=r"${\rm mm}$") season_to_control_mean[season] = control_mean print("calculated mean from {0}".format(control_path)) # calculate the difference for each simulation for the_path, the_label in zip(paths, row_labels): modified_means = analysis.get_mean_2d_fields_for_months(path=the_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) tval, pval = ttest_ind(modified_means, control_means, axis=0, equal_var=False) significance = ((pval <= pvalue_max) & (~control_mean.mask)).astype(int) print("pval ranges: {} to {}".format(pval.min(), pval.max())) modified_mean = np.mean(modified_means, axis=0) if the_label not in label_to_season_to_difference: label_to_season_to_difference[the_label] = OrderedDict() label_to_season_to_significance[the_label] = OrderedDict() modified_mean = infovar.get_to_plot(var_name, modified_mean, lake_fraction=domain_props.lake_fraction, lons=lons2d, lats=lats2d, level_width_m=lev_width_3d[:, :, level]) # multiply by the number of days in a season for PR and TRAF to convert them into mm from mm/day if var_name in ["PR", "TRAF", "TDRA"]: modified_mean *= get_num_days(months_of_interest) diff_vals = modified_mean - control_mean print("diff ranges: min: {0}; max: {1}".format(diff_vals.min(), diff_vals.max())) label_to_season_to_difference[the_label][season] = diff_vals label_to_season_to_significance[the_label][season] = significance print("Calculated mean and diff from {0}".format(the_path)) except NoSuchNodeError: print("Could not find {0}, skipping...".format(var_name)) continue for the_label, data in label_to_season_to_difference.items(): axes = [] for col in range(ncols): axes.append(fig.add_subplot(gs[the_row, col])) # Set season titles if the_row == 0: for the_season, ax in zip(season_list, axes): ax.set_title(the_season) _plot_row(axes, data, the_label, var_name, increments=True, domain_props=domain_props, season_list=season_list, significance=label_to_season_to_significance[the_label]) var_label = infovar.get_long_display_label_for_var(var_name) if var_name in ["I1"]: var_label = "{}\n{} layer".format(var_label, ordinal(level + 1)) axes[0].set_ylabel(var_label) fig.suptitle("({}) vs ({})".format(labels[0], control_label), font_properties=FontProperties(weight="bold")) folderpath = os.path.join(images_folder, "seasonal_mean_maps/{0}_vs_{1}_for_{2}_{3}-{4}".format( "_".join(labels), control_label, "-".join(list(season_to_months.keys())), start_year, end_year)) if not os.path.isdir(folderpath): os.mkdir(folderpath) imname = "{0}_{1}.png".format("-".join(varnames), "_".join(labels + [control_label])) impath = os.path.join(folderpath, imname) fig.savefig(impath, bbox_inches="tight")
def draw_model_comparison(model_points=None, stations=None, sim_name_to_file_name=None, hdf_folder=None, start_year=None, end_year=None, cell_manager=None, stfl_name="STFA", drainage_area_reldiff_min=0.1, plot_upstream_area_averaged=True, sim_name_to_color=None): """ :param model_points: list of model point objects :param stations: list of stations corresponding to the list of model points :param cell_manager: is a CellManager instance which can be provided for better performance if necessary len(model_points) == len(stations) if stations is not None. if stations is None - then no measured streamflow will be plotted """ assert model_points is None or stations is None or len(stations) == len(model_points) label_list = list(sim_name_to_file_name.keys()) # Needed to keep the order the same for all subplots path0 = os.path.join(hdf_folder, list(sim_name_to_file_name.items())[0][1]) flow_directions = analysis.get_array_from_file(path=path0, var_name="flow_direction") lake_fraction = analysis.get_array_from_file(path=path0, var_name="lake_fraction") # mask lake fraction in the ocean lake_fraction = np.ma.masked_where((flow_directions <= 0) | (flow_directions > 128), lake_fraction) accumulation_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_ACCUMULATION_AREA_NAME) area_m2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_M2) # Try to read cell areas im meters if it is not Ok then try in km2 if area_m2 is not None: cell_area_km2 = area_m2 * 1.0e-6 else: cell_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_KM2) print("cell area ranges from {} to {}".format(cell_area_km2.min(), cell_area_km2.max())) # print "plotting from {0}".format(path0) # plt.pcolormesh(lake_fraction.transpose()) # plt.colorbar() # plt.show() # exit() file_scores = open("scores_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w") file_correlations = open("corr_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w") file_annual_discharge = open("flow_{0}_{1}-{2}.txt".format("_".join(label_list), start_year, end_year), "w") text_files = [file_scores, file_correlations, file_annual_discharge] # write the following columns to the scores file header_format = "{0:10s}\t{1:10s}\t{2:10s}\t" + "\t".join(["{" + str(i + 3) + ":10s}" for i in range(len(sim_name_to_file_name))]) line_format = "{0:10s}\t{1:10.1f}\t{2:10.1f}\t" + "\t".join(["{" + str(i + 3) + ":10.1f}" for i in range(len(sim_name_to_file_name))]) header_ns = ("ID", "DAo", "DAm",) + tuple(["NS({0})".format(key) for key in sim_name_to_file_name]) file_scores.write(header_format.format(*header_ns) + "\n") header_qyear = ("ID", "DAo", "DAm",) + tuple(["Qyear({0})".format(key) for key in label_list]) + \ ("Qyear(obs)",) header_format_qyear = header_format + "\t{" + str(len(label_list) + 3) + ":10s}" file_annual_discharge.write(header_format_qyear.format(*header_qyear) + "\n") lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=path0) # Create a cell manager if it is not provided if cell_manager is None: cell_manager = CellManager(flow_directions, accumulation_area_km2=accumulation_area_km2, lons2d=lons2d, lats2d=lats2d) if stations is not None: # Get the list of the corresponding model points station_to_modelpoint = cell_manager.get_model_points_for_stations( station_list=stations, lake_fraction=lake_fraction, drainaige_area_reldiff_limit=drainage_area_reldiff_min) station_list = list(station_to_modelpoint.keys()) station_list.sort(key=lambda st1: st1.latitude, reverse=True) mp_list = [station_to_modelpoint[st] for st in station_list] else: mp_list = model_points station_list = None # sort so that the northernmost stations appear uppermost mp_list.sort(key=lambda mpt: mpt.latitude, reverse=True) # set ids to the model points so they can be distinguished easier model_point.set_model_point_ids(mp_list) # ###Uncomment the lines below for the validation plot in paper 2 # brewer2mpl.get_map args: set name set type number of colors # bmap = brewer2mpl.get_map("Set1", "qualitative", 9) # Change the default colors # mpl.rcParams["axes.color_cycle"] = bmap.mpl_colors # For the streamflow only plot ncols = 3 nrows = max(len(mp_list) // ncols, 1) if ncols * nrows < len(mp_list): nrows += 1 figure_stfl = plt.figure(figsize=(4 * ncols, 3 * nrows)) gs_stfl = gridspec.GridSpec(nrows=nrows, ncols=ncols) # a flag which signifies if a legend should be added to the plot, it is needed so we ahve only one legend per plot legend_added = False ax_stfl = None all_years = [y for y in range(start_year, end_year + 1)] if station_list is not None: processed_stations = station_list else: processed_stations = [None] * len(mp_list) processed_model_points = mp_list plot_point_positions_with_upstream_areas(processed_stations, processed_model_points, basemap, cell_manager, lake_fraction_field=lake_fraction) if plot_upstream_area_averaged: # create obs data managers anusplin_tmin = AnuSplinManager(variable="stmn") anusplin_tmax = AnuSplinManager(variable="stmx") anusplin_pcp = AnuSplinManager(variable="pcp") daily_dates, obs_tmin_fields = anusplin_tmin.get_daily_clim_fields_interpolated_to( start_year=start_year, end_year=end_year, lons_target=lons2d, lats_target=lats2d) _, obs_tmax_fields = anusplin_tmax.get_daily_clim_fields_interpolated_to( start_year=start_year, end_year=end_year, lons_target=lons2d, lats_target=lats2d) _, obs_pcp_fields = anusplin_pcp.get_daily_clim_fields_interpolated_to( start_year=start_year, end_year=end_year, lons_target=lons2d, lats_target=lats2d) swe_path = "/skynet3_rech1/huziy/swe_ross_brown/swe.nc4" if not os.path.isfile(os.path.realpath(swe_path)): raise IOError("SWE-obs file {} does not exist".format(swe_path)) swe_manager = SweDataManager(path=swe_path, var_name="SWE") obs_swe_daily_clim = swe_manager.get_daily_climatology(start_year, end_year) interpolated_obs_swe_clim = swe_manager.interpolate_daily_climatology_to(obs_swe_daily_clim, lons2d_target=lons2d, lats2d_target=lats2d) values_obs = None for i, the_model_point in enumerate(mp_list): ax_stfl = figure_stfl.add_subplot(gs_stfl[i // ncols, i % ncols], sharex=ax_stfl) assert isinstance(the_model_point, ModelPoint) # Check the number of years accessible for the station if the list of stations is given the_station = None if station_list is None else station_list[i] if the_station is not None: assert isinstance(the_station, Station) year_list = the_station.get_list_of_complete_years() year_list = list(filter(lambda yi: start_year <= yi <= end_year, year_list)) if len(year_list) < 1: continue else: year_list = all_years fig = plt.figure(figsize=(12, 15)) gs = gridspec.GridSpec(4, 4, wspace=1) # plot station position ax = fig.add_subplot(gs[3, 0:2]) upstream_mask = _plot_station_position(ax, the_station, basemap, cell_manager, the_model_point) # plot streamflows ax = fig.add_subplot(gs[0:2, 0:2]) dates = None model_daily_temp_clim = {} model_daily_precip_clim = {} model_daily_clim_surf_runoff = {} model_daily_clim_subsurf_runoff = {} model_daily_clim_swe = {} # get model data for the list of years simlabel_to_vals = {} for label in label_list: fname = sim_name_to_file_name[label] if hdf_folder is None: fpath = fname else: fpath = os.path.join(hdf_folder, fname) if plot_upstream_area_averaged: # read temperature data and calculate daily climatologic fileds _, model_daily_temp_clim[label] = analysis.get_daily_climatology( path_to_hdf_file=fpath, var_name="TT", level=0, start_year=start_year, end_year=end_year) # read modelled precip and calculate daily climatologic fields _, model_daily_precip_clim[label] = analysis.get_daily_climatology( path_to_hdf_file=fpath, var_name="PR", level=0, start_year=start_year, end_year=end_year) # read modelled surface runoff and calculate daily climatologic fields _, model_daily_clim_surf_runoff[label] = analysis.get_daily_climatology( path_to_hdf_file=fpath, var_name="TRAF", level=0, start_year=start_year, end_year=end_year) # read modelled subsurface runoff and calculate daily climatologic fields _, model_daily_clim_subsurf_runoff[label] = analysis.get_daily_climatology( path_to_hdf_file=fpath, var_name="TDRA", level=0, start_year=start_year, end_year=end_year) # read modelled swe and calculate daily climatologic fields _, model_daily_clim_swe[label] = analysis.get_daily_climatology( path_to_hdf_file=fpath, var_name="I5", level=0, start_year=start_year, end_year=end_year) dates, values_model = analysis.get_daily_climatology_for_a_point(path=fpath, var_name=stfl_name, years_of_interest=year_list, i_index=the_model_point.ix, j_index=the_model_point.jy) ax.plot(dates, values_model, label=label, lw=2) if sim_name_to_color is None: ax_stfl.plot(dates, values_model, label=label, lw=2) else: ax_stfl.plot(dates, values_model, sim_name_to_color[label], label=label, lw=2) print(20 * "!!!") print("{} -> {}".format(label, sim_name_to_color[label])) print(20 * "!!!") simlabel_to_vals[label] = values_model if the_station is not None: assert isinstance(the_station, Station) dates, values_obs = the_station.get_daily_climatology_for_complete_years_with_pandas(stamp_dates=dates, years=year_list) # To keep the colors consistent for all the variables, the obs Should be plotted last ax.plot(dates, values_obs, label="Obs.", lw=2) # no ticklabels for streamflow plot plt.setp(ax.get_xticklabels(), visible=False) if sim_name_to_color is None: ax_stfl.plot(dates, values_obs, label="Obs.", lw=2) else: ax_stfl.plot(dates, values_obs, label="Obs.", lw=2, color=sim_name_to_color["Obs."]) # Print excesss from streamflow validation for label, values_model in simlabel_to_vals.items(): calclulate_spring_peak_err(dates, values_obs, values_model, st_id="{}: {}".format(label, the_station.id), da_mod=the_model_point.accumulation_area, da_obs=the_station.drainage_km2) ax.set_ylabel(r"Streamflow: ${\rm m^3/s}$") assert isinstance(ax, Axes) assert isinstance(fig, Figure) upstream_area_km2 = np.sum(cell_area_km2[upstream_mask == 1]) # Put some information about the point if the_station is not None: lf_upstream = lake_fraction[upstream_mask == 1] point_info = "{0}".format(the_station.id) write_annual_flows_to_txt(label_list, simlabel_to_vals, values_obs, file_annual_discharge, station_id=the_station.id, da_obs=the_station.drainage_km2, da_mod=the_model_point.accumulation_area) else: point_info = "{0}".format(the_model_point.point_id) ax.annotate(point_info, (0.8, 0.8), xycoords="axes fraction", bbox=dict(facecolor="white", alpha=0.5), va="top", ha="right") ax.legend(loc=(0.0, 1.05), borderaxespad=0, ncol=3) ax.xaxis.set_minor_formatter(FuncFormatter(lambda x, pos: num2date(x).strftime("%b")[0])) ax.xaxis.set_minor_locator(MonthLocator(bymonthday=15)) ax.xaxis.set_major_locator(MonthLocator()) ax.grid() streamflow_axes = ax # save streamflow axes for later use if not legend_added: ax_stfl.legend(loc="lower left", bbox_to_anchor=(0, 1.15), borderaxespad=0, ncol=3) ax_stfl.xaxis.set_minor_formatter(FuncFormatter(lambda x, pos: num2date(x).strftime("%b")[0])) ax_stfl.xaxis.set_minor_locator(MonthLocator(bymonthday=15)) ax_stfl.xaxis.set_major_locator(MonthLocator()) ax_stfl.set_ylabel(r"Streamflow ${\rm m^3/s}$") legend_added = True plt.setp(ax_stfl.get_xmajorticklabels(), visible=False) ax_stfl.yaxis.set_major_locator(MaxNLocator(nbins=5)) sfmt = ScalarFormatter(useMathText=True) sfmt.set_powerlimits((-2, 2)) ax_stfl.yaxis.set_major_formatter(sfmt) ax_stfl.grid() # annotate streamflow-only panel plot ax_stfl.annotate(point_info, (0.05, 0.95), xycoords="axes fraction", bbox=dict(facecolor="white"), va="top", ha="left") if plot_upstream_area_averaged: # plot temperature comparisons (tmod - daily with anusplin tmin and tmax) ax = fig.add_subplot(gs[3, 2:], sharex=streamflow_axes) _validate_temperature_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2, upstream_mask=upstream_mask, daily_dates=daily_dates, obs_tmin_clim_fields=obs_tmin_fields, obs_tmax_clim_fields=obs_tmax_fields, model_data_dict=model_daily_temp_clim, simlabel_list=label_list) # plot temperature comparisons (tmod - daily with anusplin tmin and tmax) ax = fig.add_subplot(gs[2, 2:], sharex=streamflow_axes) _validate_precip_with_anusplin(ax, the_model_point, cell_area_km2=cell_area_km2, upstream_mask=upstream_mask, daily_dates=daily_dates, obs_precip_clim_fields=obs_pcp_fields, model_data_dict=model_daily_precip_clim, simlabel_list=label_list) # plot mean upstream surface runoff ax = fig.add_subplot(gs[0, 2:], sharex=streamflow_axes) _plot_upstream_surface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2, upstream_mask=upstream_mask, daily_dates=daily_dates, model_data_dict=model_daily_clim_surf_runoff, simlabel_list=label_list) # plot mean upstream subsurface runoff ax = fig.add_subplot(gs[1, 2:], sharex=streamflow_axes, sharey=ax) _plot_upstream_subsurface_runoff(ax, the_model_point, cell_area_km2=cell_area_km2, upstream_mask=upstream_mask, daily_dates=daily_dates, model_data_dict=model_daily_clim_subsurf_runoff, simlabel_list=label_list) # plot mean upstream swe comparison ax = fig.add_subplot(gs[2, 0:2], sharex=streamflow_axes) print("Validating SWE for ", the_station.id, "--" * 20) _validate_swe_with_ross_brown(ax, the_model_point, cell_area_km2=cell_area_km2, upstream_mask=upstream_mask, daily_dates=daily_dates, model_data_dict=model_daily_clim_swe, obs_swe_clim_fields=interpolated_obs_swe_clim, simlabel_list=label_list) if the_station is not None: im_name = "comp_point_with_obs_{0}_{1}_{2}.png".format(the_station.id, the_station.source, "_".join(label_list)) im_folder_path = os.path.join(images_folder, the_station.source) else: im_name = "comp_point_with_obs_{0}_{1}.png".format(the_model_point.point_id, "_".join(label_list)) im_folder_path = os.path.join(images_folder, "outlets_point_comp") # create a folder for a given source of observed streamflow if it does not exist yet if not os.path.isdir(im_folder_path): os.mkdir(im_folder_path) im_path = os.path.join(im_folder_path, im_name) if plot_upstream_area_averaged: fig.savefig(im_path, dpi=cpp.FIG_SAVE_DPI, bbox_inches="tight", transparent=True) plt.close(fig) # return # temporary plot only one point assert isinstance(figure_stfl, Figure) figure_stfl.tight_layout() figure_stfl.savefig(os.path.join(images_folder, "comp_point_with_obs_{0}.png".format("_".join(label_list))), bbox_inches="tight", transparent=True, dpi=cpp.FIG_SAVE_DPI) plt.close(figure_stfl) # close information text files for f in text_files: f.close()
def compare(paths=None, path_to_control_data=None, control_label="", labels=None, varnames=None, levels=None, months_of_interest=None, start_year=None, end_year=None): """ Comparing 2D fields :param paths: paths to the simulation results :param varnames: :param labels: Display name for each simulation (number of labels should be equal to the number of paths) :param path_to_control_data: the path with which the comparison done i.e. a in the following formula delta = (x - a)/a * 100% generates one image file per variable (in the folder images_for_lake-river_paper): compare_varname_<control_label>_<label1>_..._<labeln>_startyear_endyear.png """ # get coordinate data (assumes that all the variables and runs have the same coordinates) lons2d, lats2d, basemap = analysis.get_basemap_from_hdf( file_path=path_to_control_data) x, y = basemap(lons2d, lats2d) lake_fraction = analysis.get_array_from_file(path=path_to_control_data, var_name="lake_fraction") if lake_fraction is None: lake_fraction = np.zeros(lons2d.shape) ncolors = 10 # +1 to include white diff_cmap = cm.get_cmap("RdBu_r", ncolors + 1) for var_name, level in zip(varnames, levels): sfmt = infovar.get_colorbar_formatter(var_name) control_means = analysis.get_mean_2d_fields_for_months( path=path_to_control_data, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) control_mean = np.mean(control_means, axis=0) fig = plt.figure() assert isinstance(fig, Figure) gs = gridspec.GridSpec(2, len(paths) + 1, wspace=0.5) # plot the control ax = fig.add_subplot(gs[0, 0]) assert isinstance(ax, Axes) ax.set_title("{0}".format(control_label)) ax.set_ylabel("Mean: $X_{0}$") to_plot = infovar.get_to_plot(var_name, control_mean, lake_fraction=lake_fraction, mask_oceans=True, lons=lons2d, lats=lats2d) # determine colorabr extent and spacing field_cmap, field_norm = infovar.get_colormap_and_norm_for( var_name, to_plot, ncolors=ncolors) basemap.pcolormesh(x, y, to_plot, cmap=field_cmap, norm=field_norm) cb = basemap.colorbar(format=sfmt) assert isinstance(cb, Colorbar) # cb.ax.set_ylabel(infovar.get_units(var_name)) units = infovar.get_units(var_name) info = "Variable:" \ "\n{0}" \ "\nPeriod: {1}-{2}" \ "\nMonths: {3}" \ "\nUnits: {4}" info = info.format( infovar.get_long_name(var_name), start_year, end_year, ",".join([ datetime(2001, m, 1).strftime("%b") for m in months_of_interest ]), units) ax.annotate(info, xy=(0.1, 0.3), xycoords="figure fraction") sel_axes = [ax] for the_path, the_label, column in zip(paths, labels, list(range(1, len(paths) + 1))): means_for_years = analysis.get_mean_2d_fields_for_months( path=the_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year) the_mean = np.mean(means_for_years, axis=0) # plot the mean value ax = fig.add_subplot(gs[0, column]) sel_axes.append(ax) ax.set_title("{0}".format(the_label)) to_plot = infovar.get_to_plot(var_name, the_mean, lake_fraction=lake_fraction, mask_oceans=True, lons=lons2d, lats=lats2d) basemap.pcolormesh(x, y, to_plot, cmap=field_cmap, norm=field_norm) ax.set_ylabel("Mean: $X_{0}$".format(column)) cb = basemap.colorbar(format=sfmt) # cb.ax.set_ylabel(infovar.get_units(var_name)) # plot the difference ax = fig.add_subplot(gs[1, column]) sel_axes.append(ax) ax.set_ylabel("$X_{0} - X_0$".format(column)) # #Mask only if the previous plot (means) is masked thediff = the_mean - control_mean if hasattr(to_plot, "mask"): to_plot = np.ma.masked_where(to_plot.mask, thediff) else: to_plot = thediff if var_name == "PR": # convert to mm/day to_plot = infovar.get_to_plot(var_name, to_plot, mask_oceans=False) vmin = np.ma.min(to_plot) vmax = np.ma.max(to_plot) d = max(abs(vmin), abs(vmax)) vmin = -d vmax = d field_norm, bounds, vmn_nice, vmx_nice = infovar.get_boundary_norm( vmin, vmax, diff_cmap.N, exclude_zero=False) basemap.pcolormesh(x, y, to_plot, cmap=diff_cmap, norm=field_norm, vmin=vmn_nice, vmax=vmx_nice) cb = basemap.colorbar(format=sfmt) t, pval = ttest_ind(means_for_years, control_means, axis=0) sig = pval < 0.1 basemap.contourf(x, y, sig.astype(int), nlevels=2, hatches=["+", None], colors="none") # cb.ax.set_ylabel(infovar.get_units(var_name)) # plot coastlines for the_ax in sel_axes: basemap.drawcoastlines( ax=the_ax, linewidth=common_plot_params.COASTLINE_WIDTH) # depends on the compared simulations and the months of interest fig_file_name = "compare_{0}_{1}_{2}_months-{3}.jpeg".format( var_name, control_label, "_".join(labels), "-".join([str(m) for m in months_of_interest])) figpath = os.path.join(images_folder, fig_file_name) fig.savefig(figpath, dpi=cpp.FIG_SAVE_DPI, bbox_inches="tight") plt.close(fig)
def plot_control_and_differences_in_one_panel_for_all_seasons_for_all_vars( varnames=None, levels=None, season_to_months=None, start_year=None, end_year=None): season_list = list(season_to_months.keys()) pvalue_max = 0.1 # crcm5-r vs crcm5-hcd-r # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r_spinup.hdf" # control_label = "CRCM5-R" # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r_spinup2.hdf", ] # labels = ["CRCM5-HCD-R"] # crcm5-hcd-rl vs crcm5-hcd-r # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r_spinup2.hdf" # control_label = "CRCM5-HCD-R" # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf", ] # labels = ["CRCM5-HCD-RL"] # compare simulations with and without interflow # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf" # control_label = "CRCM5-HCD-RL" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_do_not_discard_small.hdf", ] # labels = ["CRCM5-HCD-RL-INTFL"] # very high hydr cond # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_do_not_discard_small.hdf" # control_label = "CRCM5-HCD-RL-INTFL" ## # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_sani-10000.hdf", ] # labels = ["CRCM5-HCD-RL-INTFL-sani=10000"] # Interflow effect # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl_spinup.hdf" # control_label = "CRCM5-HCD-RL" # ## # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_spinup_ITFS.hdf5", ] # labels = ["ITFS"] # total lake effect # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5" # control_label = "CRCM5-NL" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", ] # labels = ["CRCM5-L2", ] # lake effect (lake-atm interactions) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-r.hdf5" # control_label = "CRCM5-R" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5", ] # labels = ["CRCM5-HCD-R", ] # lake effect (lake-river interactions) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-r.hdf5" # control_label = "CRCM5-L1" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", ] # labels = ["CRCM5-HCD-L2", ] # interflow effect () control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5" control_label = "CRCM5-L2" paths = [ "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5", ] labels = [ "CRCM5-L2I", ] # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS_avoid_truncation1979-1989.hdf5", ] # labels = ["CRCM5-HCD-RL-INTFb", ] # interflow effect (avoid truncation and bigger slopes) # control_path = "/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS.hdf5" # control_label = "CRCM5-HCD-RL-INTF" # # paths = ["/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl-intfl_ITFS_avoid_truncation1979-1989.hdf5", ] # labels = ["CRCM5-HCD-RL-INTF-improved", ] # row_labels = [r"{} vs {}".format(s, control_label) for s in labels] print(labels) # varnames = ["QQ", ] # levels = [None, ] assert len(levels) == len(varnames) lons2d, lats2d, basemap = analysis.get_basemap_from_hdf( file_path=control_path) x, y = basemap(lons2d, lats2d) # save the domain properties for reuse domain_props = DomainProperties() domain_props.basemap = basemap domain_props.lons2d = lons2d domain_props.lats2d = lats2d domain_props.x = x domain_props.y = y lake_fraction = analysis.get_array_from_file( path=control_path, var_name=infovar.HDF_LAKE_FRACTION_NAME) dpth_to_bedrock = analysis.get_array_from_file( path=control_path, var_name=infovar.HDF_DEPTH_TO_BEDROCK_NAME) assert dpth_to_bedrock is not None if lake_fraction is None: lake_fraction = np.zeros(lons2d.shape) ncolors = 10 # +1 to include white diff_cmap = cm.get_cmap("RdBu", ncolors + 1) # Do the plotting for each variable fig = plt.figure() assert isinstance(fig, Figure) # plot the control data ncols = len(season_list) + 1 # +1 is for the colorbar gs = gridspec.GridSpec(len(varnames), ncols, width_ratios=[ 1.0, ] * (ncols - 1) + [0.07], top=0.95) lev_width_3d = np.ones(dpth_to_bedrock.shape + infovar.soil_layer_widths_26_to_60.shape) lev_width_3d *= infovar.soil_layer_widths_26_to_60[np.newaxis, np.newaxis, :] lev_bot_3d = lev_width_3d.cumsum(axis=2) correction = -lev_bot_3d + dpth_to_bedrock[:, :, np.newaxis] # Apply the correction only at points where the layer bottom is lower than # the bedrock lev_width_3d[correction < 0] += correction[correction < 0] lev_width_3d[lev_width_3d < 0] = 0 # plot the plots one file per variable for var_name, level, the_row in zip(varnames, levels, list(range(len(varnames)))): sfmt = infovar.get_colorbar_formatter(var_name) season_to_control_mean = {} label_to_season_to_difference = {} label_to_season_to_significance = {} try: # Calculate the difference for each season, and save the results to dictionaries # to access later when plotting for season, months_of_interest in season_to_months.items(): print("working on season: {0}".format(season)) control_means = analysis.get_mean_2d_fields_for_months( path=control_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) control_mean = np.mean(control_means, axis=0) control_mean = infovar.get_to_plot( var_name, control_mean, lake_fraction=domain_props.lake_fraction, lons=lons2d, lats=lats2d, level_width_m=lev_width_3d[:, :, level]) # multiply by the number of days in a season for PR and TRAF to convert them into mm from mm/day if var_name in ["PR", "TRAF", "TDRA"]: control_mean *= get_num_days(months_of_interest) infovar.change_units_to(varnames=[ var_name, ], new_units=r"${\rm mm}$") season_to_control_mean[season] = control_mean print("calculated mean from {0}".format(control_path)) # calculate the difference for each simulation for the_path, the_label in zip(paths, row_labels): modified_means = analysis.get_mean_2d_fields_for_months( path=the_path, var_name=var_name, months=months_of_interest, start_year=start_year, end_year=end_year, level=level) tval, pval = ttest_ind(modified_means, control_means, axis=0, equal_var=False) significance = ((pval <= pvalue_max) & (~control_mean.mask)).astype(int) print("pval ranges: {} to {}".format( pval.min(), pval.max())) modified_mean = np.mean(modified_means, axis=0) if the_label not in label_to_season_to_difference: label_to_season_to_difference[the_label] = OrderedDict( ) label_to_season_to_significance[ the_label] = OrderedDict() modified_mean = infovar.get_to_plot( var_name, modified_mean, lake_fraction=domain_props.lake_fraction, lons=lons2d, lats=lats2d, level_width_m=lev_width_3d[:, :, level]) # multiply by the number of days in a season for PR and TRAF to convert them into mm from mm/day if var_name in ["PR", "TRAF", "TDRA"]: modified_mean *= get_num_days(months_of_interest) diff_vals = modified_mean - control_mean print("diff ranges: min: {0}; max: {1}".format( diff_vals.min(), diff_vals.max())) label_to_season_to_difference[the_label][ season] = diff_vals label_to_season_to_significance[the_label][ season] = significance print("Calculated mean and diff from {0}".format(the_path)) except NoSuchNodeError: print("Could not find {0}, skipping...".format(var_name)) continue for the_label, data in label_to_season_to_difference.items(): axes = [] for col in range(ncols): axes.append(fig.add_subplot(gs[the_row, col])) # Set season titles if the_row == 0: for the_season, ax in zip(season_list, axes): ax.set_title(the_season) _plot_row(axes, data, the_label, var_name, increments=True, domain_props=domain_props, season_list=season_list, significance=label_to_season_to_significance[the_label]) var_label = infovar.get_long_display_label_for_var(var_name) if var_name in ["I1"]: var_label = "{}\n{} layer".format(var_label, ordinal(level + 1)) axes[0].set_ylabel(var_label) fig.suptitle("({}) vs ({})".format(labels[0], control_label), font_properties=FontProperties(weight="bold")) folderpath = os.path.join( images_folder, "seasonal_mean_maps/{0}_vs_{1}_for_{2}_{3}-{4}".format( "_".join(labels), control_label, "-".join(list(season_to_months.keys())), start_year, end_year)) if not os.path.isdir(folderpath): os.mkdir(folderpath) imname = "{0}_{1}.png".format("-".join(varnames), "_".join(labels + [control_label])) impath = os.path.join(folderpath, imname) fig.savefig(impath, bbox_inches="tight")
def main(): lkfr_limit = 0.05 model_data_current_path = "/skynet3_rech1/huziy/hdf_store/cc-canesm2-driven/" \ "quebec_0.1_crcm5-hcd-rl-cc-canesm2-1980-2010.hdf5" modif_label = "CanESM2-CRCM5-L" start_year_c = 1980 end_year_c = 2010 future_shift_years = 90 params = dict( start_year=start_year_c, end_year=end_year_c ) params.update( dict(data_path=model_data_current_path, label=modif_label) ) model_config_c = RunConfig(**params) model_config_f = model_config_c.get_shifted_config(future_shift_years) bmp_info = analysis.get_basemap_info(r_config=model_config_c) specific_cond_heat = 0.250100e7 # J/kg water_density = 1000.0 # kg/m**3 season_to_months = OrderedDict([ ("Summer", [6, 7, 8]), ]) lkfr = analysis.get_array_from_file(path="/RESCUE/skynet3_rech1/huziy/hdf_store/quebec_0.1_crcm5-hcd-rl.hdf5", var_name=infovar.HDF_LAKE_FRACTION_NAME) assert lkfr is not None, "Could not find lake fraction in the file" # Current climate traf_c = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_c, varname="TRAF", level=5, season_to_months=season_to_months) pr_c = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_c, varname="PR", level=0, season_to_months=season_to_months) lktemp_c = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_c, varname="L1", level=0, season_to_months=season_to_months) airtemp_c = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_c, varname="TT", level=0, season_to_months=season_to_months) lhc = OrderedDict([ (s, specific_cond_heat * (pr_c[s] * water_density - traf_c[s])) for s, traf in traf_c.items() ]) avc = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_c, varname="AV", level=0, season_to_months=season_to_months) plt.figure() lhc["Summer"] = np.ma.masked_where(lkfr < lkfr_limit, lhc["Summer"]) print("min: {}, max: {}".format(lhc["Summer"].min(), lhc["Summer"].max())) cs = plt.contourf(lhc["Summer"].T) plt.title("lhc") plt.colorbar() plt.figure() cs = plt.contourf(avc["Summer"].T, levels=cs.levels, norm=cs.norm, cmap=cs.cmap) plt.title("avc") plt.colorbar() # Future climate traf_f = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_f, varname="TRAF", level=5, season_to_months=season_to_months) pr_f = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_f, varname="PR", level=0, season_to_months=season_to_months) lktemp_f = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_f, varname="L1", level=0, season_to_months=season_to_months) airtemp_f = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_f, varname="TT", level=0, season_to_months=season_to_months) lhf = OrderedDict([ (s, specific_cond_heat * (pr_f[s] * water_density - traf_f[s])) for s, traf in traf_f.items() ]) plt.figure() plt.pcolormesh(traf_c["Summer"].T) plt.title("TRAF over lakes current") plt.colorbar() avf = analysis.get_seasonal_climatology_for_runconfig(run_config=model_config_f, varname="AV", level=0, season_to_months=season_to_months) plt.figure() cs = plt.contourf(avf["Summer"].T) plt.title("avf") plt.colorbar() plt.figure() cs = plt.contourf(avf["Summer"].T - avc["Summer"].T, levels=np.arange(-40, 45, 5)) plt.title("d(av)") plt.colorbar() plt.figure() plt.contourf(lhf["Summer"].T - lhc["Summer"].T, levels=cs.levels, cmap=cs.cmap, norm=cs.norm) plt.title("d(lh)") plt.colorbar() # plotting plot_utils.apply_plot_params(width_cm=15, height_cm=15, font_size=10) gs = GridSpec(2, 2) # tair_c_ts = analysis.get_area_mean_timeseries(model_config_c.data_path, var_name="TT", level_index=0, # start_year=model_config_c.start_year, end_year=model_config_c.end_year, # the_mask=lkfr >= lkfr_limit) # # tair_f_ts = analysis.get_area_mean_timeseries(model_config_f.data_path, var_name="TT", level_index=0, # start_year=model_config_f.start_year, end_year=model_config_f.end_year, # the_mask=lkfr >= lkfr_limit) # # # tlake_c_ts = analysis.get_area_mean_timeseries(model_config_c.data_path, var_name="TT", level_index=0, # start_year=model_config_c.start_year, end_year=model_config_c.end_year, # the_mask=lkfr >= lkfr_limit) # # tlake_f_ts = analysis.get_area_mean_timeseries(model_config_f.data_path, var_name="TT", level_index=0, # start_year=model_config_f.start_year, end_year=model_config_f.end_year, # the_mask=lkfr >= lkfr_limit) for season in season_to_months: fig = plt.figure() lktemp_c[season] -= 273.15 dT_c = np.ma.masked_where(lkfr < lkfr_limit, lktemp_c[season] - airtemp_c[season]) lktemp_f[season] -= 273.15 dT_f = np.ma.masked_where(lkfr < lkfr_limit, lktemp_f[season] - airtemp_f[season]) d = np.round(max(np.ma.abs(dT_c).max(), np.ma.abs(dT_f).max())) vmin = -d vmax = d clevs = np.arange(-12, 13, 1) ncolors = len(clevs) - 1 bn = BoundaryNorm(clevs, ncolors=ncolors) cmap = cm.get_cmap("seismic", ncolors) ax_list = [] fig.suptitle(season) xx, yy = bmp_info.get_proj_xy() # Current gradient ax = fig.add_subplot(gs[0, 0]) ax.set_title(r"current: $T_{\rm lake} - T_{\rm atm}$") cs = bmp_info.basemap.pcolormesh(xx, yy, dT_c, ax=ax, norm=bn, cmap=cmap) bmp_info.basemap.colorbar(cs, ax=ax, extend="both") ax_list.append(ax) # Future Gradient ax = fig.add_subplot(gs[0, 1]) ax.set_title(r"future: $T_{\rm lake} - T_{\rm atm}$") cs = bmp_info.basemap.pcolormesh(xx, yy, dT_f, ax=ax, norm=cs.norm, cmap=cs.cmap, vmin=vmin, vmax=vmax) bmp_info.basemap.colorbar(cs, ax=ax, extend="both") ax_list.append(ax) # Change in the gradient ax = fig.add_subplot(gs[1, 0]) ax.set_title(r"$\Delta T_{\rm future} - \Delta T_{\rm current}$") ddT = dT_f - dT_c d = np.round(np.ma.abs(ddT).max()) clevs = np.arange(-3, 3.1, 0.1) ncolors = len(clevs) - 1 bn = BoundaryNorm(clevs, ncolors=ncolors) cmap = cm.get_cmap("seismic", ncolors) cs = bmp_info.basemap.pcolormesh(xx, yy, ddT, norm=bn, cmap=cmap) bmp_info.basemap.colorbar(cs, ax=ax, extend="both") ax_list.append(ax) # Change in the latent heat flux # ax = fig.add_subplot(gs[1, 1]) # ax.set_title(r"$LE_{\rm future} - LE_{\rm current}$") # dlh = np.ma.masked_where(lkfr < lkfr_limit, lhf[season] - lhc[season]) # # d = np.round(np.ma.abs(dlh).max() // 10) * 10 # clevs = np.arange(0, 105, 5) # bn = BoundaryNorm(clevs, ncolors=ncolors) # cmap = cm.get_cmap("jet", ncolors) # # cs = bmp_info.basemap.pcolormesh(xx, yy, dlh, norm=bn, cmap=cmap) # bmp_info.basemap.colorbar(cs, ax=ax, extend="max") # Change in the latent heat flux # ax_list.append(ax) for the_ax in ax_list: bmp_info.basemap.drawcoastlines(linewidth=0.3, ax=the_ax) fig.tight_layout() fig.savefig(os.path.join(img_folder, "lake_atm_gradients_and_fluxes_{}-{}_{}-{}.png".format(model_config_f.start_year, model_config_f.end_year, start_year_c, end_year_c)), dpi=800, bbox_inches="tight")
def get_mean_diffs(interflow_data_path="", base_data_path="", start_year=1980, end_year=2010, months_of_interest=(4, 5, 6, 7, 8, 9), delete_cache=True): """ Get mean differences for fixed variables, between interflow_data_path and base_data_path files :param interflow_data_path: :param base_data_path: :param start_year: :param end_year: :param months_of_interest: :return: """ # Build the name of the cache file cache_file = "cache_extr_intf_effect{}-{}_{}.bin".format( start_year, end_year, "-".join(str(m) for m in months_of_interest)) # Do not use caching by default if delete_cache: os.remove(cache_file) if os.path.isfile(cache_file): return pickle.load(open(cache_file)) precip_limit = 0.0 # at least it should rain tt_limit = 0 # and the oil should not be frozen traf_diff = None # surface runoff difference prcip_diff = None drainage_diff = None # drainage difference i1_diff = None # soil moisture difference months_query = "{}".format("|".join( ["(month=={})".format(m) for m in months_of_interest])) year_query = "(year >= {}) & (year <= {})".format(start_year, end_year) print("months_query = {}".format(months_query)) depth_to_bedrock = pt_analysis.get_array_from_file( base_data_path, var_name=infovar.HDF_DEPTH_TO_BEDROCK_NAME) with tb.open_file(interflow_data_path) as h_intf: pr_intf_table = h_intf.get_node("/", "PR") tt_intf_table = h_intf.get_node("/", "TT") traf_intf_table = h_intf.get_node("/", "TRAF") tdra_intf_table = h_intf.get_node("/", "TDRA") i1_intf_table = h_intf.get_node("/", "I1") assert isinstance(pr_intf_table, tb.Table) assert isinstance(tt_intf_table, tb.Table) assert isinstance(traf_intf_table, tb.Table) assert isinstance(tdra_intf_table, tb.Table) print(len(pr_intf_table), len(tt_intf_table), len(traf_intf_table)) with tb.open_file(base_data_path) as h_nointf: pr_nointf_table = h_nointf.get_node("/", "PR") tt_nointf_table = h_nointf.get_node("/", "TT") traf_nointf_table = h_nointf.get_node("/", "TRAF") tdra_nointf_table = h_nointf.get_node("/", "TDRA") i1_nointf_table = h_nointf.get_node("/", "I1") assert isinstance(pr_nointf_table, tb.Table) assert isinstance(tt_nointf_table, tb.Table) assert isinstance(traf_nointf_table, tb.Table) assert isinstance(tdra_nointf_table, tb.Table) for rownum, pr_intf_row in enumerate( pr_intf_table.where("({}) & {}".format( months_query, year_query))): year, month, day, hour = [ pr_intf_row[k] for k in ["year", "month", "day", "hour"] ] # print year, month, day, hour pr_intf_field = pr_intf_row["field"] tt_intf_field = None traf_intf_field = None tdra_intf_field = None i1_intf_field = None pr_nointf_field = None tt_nointf_field = None traf_nointf_field = None tdra_nointf_field = None i1_nointf_field = None # Get air temperature and precipitation for the same time tt_query = "(year == {}) & (month == {}) & (day == {}) & (hour == {})".format( year, month, day, hour) traf_query = "{} & (level_index == {})".format(tt_query, 0) for tt_row in tt_intf_table.where(tt_query): tt_intf_field = tt_row["field"] break # print tt_intf_field.min(), tt_intf_field.max() for traf_row in traf_intf_table.where(traf_query): traf_intf_field = traf_row["field"] break for tdra_row in tdra_intf_table.where(traf_query): tdra_intf_field = tdra_row["field"] break for i1_row in i1_intf_table.where(traf_query): i1_intf_field = i1_row["field"] break # for no interflow simulation for tt_row in tt_nointf_table.where(tt_query): tt_nointf_field = tt_row["field"] break for pr_row in pr_nointf_table.where(tt_query): pr_nointf_field = pr_row["field"] break for traf_row in traf_nointf_table.where(traf_query): traf_nointf_field = traf_row["field"] break for tdra_row in tdra_nointf_table.where(traf_query): tdra_nointf_field = tdra_row["field"] break for i1_row in i1_nointf_table.where(traf_query): i1_nointf_field = i1_row["field"] break if traf_diff is None: traf_diff = np.zeros(pr_intf_field.shape) prcip_diff = np.zeros(pr_intf_field.shape) drainage_diff = np.zeros(pr_intf_field.shape) i1_diff = np.zeros(pr_intf_field.shape) points_of_interest = ( (pr_intf_field > precip_limit) & (pr_nointf_field > precip_limit) & (tt_intf_field > tt_limit) & (tt_nointf_field > tt_limit) & (abs(pr_intf_field - pr_nointf_field) < 0.01 * (pr_intf_field + pr_nointf_field) / 2.0)) if rownum % 100 == 0: print("Precipitation ranges in M/s") print(pr_intf_field.min(), pr_intf_field.max()) print(pr_nointf_field.min(), pr_nointf_field.max()) if traf_intf_field is None: print("intf field is none") print(traf_query) if traf_nointf_field is None: print("nointf field is none") print(traf_query) traf_diff[points_of_interest] += traf_intf_field[points_of_interest] - \ traf_nointf_field[points_of_interest] prcip_diff[points_of_interest] += pr_intf_field[points_of_interest] - \ pr_nointf_field[points_of_interest] drainage_diff[points_of_interest] += tdra_intf_field[points_of_interest] - \ tdra_nointf_field[points_of_interest] i1_diff[points_of_interest] += i1_intf_field[points_of_interest] - \ i1_nointf_field[points_of_interest] # if rownum % 100 == 0 and debug_plots: # fig = plt.figure() # im = plt.pcolormesh(traf_diff.transpose() * 3 * 60 * 60) # plt.colorbar(im) # plt.savefig("{}/{}.jpg".format(img_dir, rownum)) # plt.close(fig) # # plt.figure() # im = plt.pcolormesh(traf_intf_field.transpose() * 60 * 60 * 24) # plt.colorbar(im) # plt.savefig("{}/traf_{}.jpg".format(img_dir, rownum)) # plt.close(fig) pickle.dump([traf_diff, prcip_diff, drainage_diff, i1_diff], open(cache_file, "w")) return traf_diff, prcip_diff, drainage_diff, i1_diff
def main(hdf_folder="/home/huziy/skynet3_rech1/hdf_store", start_year=1980, end_year=2010): prepare() all_markers = ["*", "s", "p", "+", "x", "d", "h"] excluded = ["white", "w", "aliceblue", "azure"] excluded.extend([ci for ci in colors.cnames if "yellow" in ci]) all_colors = ["k", "b", "r", "g", "m"] + sorted([ci for ci in colors.cnames if ci not in excluded]) # Station ids to get from the CEHQ database ids_with_lakes_upstream = [ "104001", "093806", "093801", "081002", "081007", "080718" ] selected_ids = ids_with_lakes_upstream filedir = Path(hdf_folder) sim_name_to_file_path = OrderedDict([ # ("CRCM5-LI", filedir.joinpath("quebec_0.1_crcm5-hcd-r.hdf5").as_posix()), ("ERAI-CRCM5-L", filedir.joinpath("quebec_0.1_crcm5-hcd-rl.hdf5").as_posix()), # ("CanESM2-CRCM5-NL", filedir.joinpath("cc-canesm2-driven/quebec_0.1_crcm5-r-cc-canesm2-1980-2010.hdf5").as_posix()), ("CanESM2-CRCM5-L", filedir.joinpath("cc-canesm2-driven/quebec_0.1_crcm5-hcd-rl-cc-canesm2-1980-2010.hdf5").as_posix()), # ("CanESM2-CRCM5-LI", filedir.joinpath("cc-canesm2-driven/quebec_0.1_crcm5-hcd-rl-intfl-cc-canesm2-1980-2010.hdf5").as_posix()), ]) obs_label = "Obs." labels = [obs_label, ] + list(sim_name_to_file_path.keys()) label_to_marker = dict(zip(labels, all_markers)) label_to_color = dict(zip(labels, all_colors)) # Get the list of stations to do the comparison with start_date = datetime(start_year, 1, 1) end_date = datetime(end_year, 12, 31) stations = cehq_station.read_station_data( start_date=start_date, end_date=end_date, selected_ids=selected_ids ) # Get geophysical fields from one of the model simulations path0 = list(sim_name_to_file_path.values())[0] lons2d, lats2d, basemap = analysis.get_basemap_from_hdf(file_path=path0) flow_directions = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_FLOW_DIRECTIONS_NAME) lake_fraction = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_LAKE_FRACTION_NAME) accumulation_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_ACCUMULATION_AREA_NAME) area_m2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_M2) # Try to read cell areas im meters if it is not Ok then try in km2 if area_m2 is not None: cell_area_km2 = area_m2 * 1.0e-6 else: cell_area_km2 = analysis.get_array_from_file(path=path0, var_name=infovar.HDF_CELL_AREA_NAME_KM2) # Create a cell manager if it is not provided cell_manager = CellManager(flow_directions, accumulation_area_km2=accumulation_area_km2, lons2d=lons2d, lats2d=lats2d) # Get the list of the corresponding model points station_to_modelpoint = cell_manager.get_model_points_for_stations( station_list=stations, lake_fraction=lake_fraction, drainaige_area_reldiff_limit=0.1) # plot_utils.apply_plot_params(font_size=10, width_cm=20, height_cm=18) fig = plt.figure() ncols = max([len(rp_list) for et, rp_list in ExtremeProperties.extreme_type_to_return_periods.items()]) nrows = len(ExtremeProperties.extreme_types) gs = GridSpec(nrows, ncols) ext_type_to_rp_to_ax = OrderedDict() ax_with_legend = None label_to_ax_to_xdata = {} label_to_ax_to_ydata = {} for row, ext_type in enumerate(ExtremeProperties.extreme_types): ext_type_to_rp_to_ax[ext_type] = OrderedDict() for col, rperiod in enumerate(ExtremeProperties.extreme_type_to_return_periods[ext_type]): ax = fig.add_subplot(gs[row, col]) ext_type_to_rp_to_ax[ext_type][rperiod] = ax if col == 0: ax.set_ylabel(ext_type) if row == nrows - 1 and col == ncols - 1: ax_with_legend = ax # Set axes labels if row == nrows - 1: ax.set_xlabel("Observations") if col == 0: ax.set_ylabel("Model") for label in sim_name_to_file_path: if label not in label_to_ax_to_xdata: label_to_ax_to_xdata[label] = {ax: []} label_to_ax_to_ydata[label] = {ax: []} else: label_to_ax_to_xdata[label][ax] = [] label_to_ax_to_ydata[label][ax] = [] ax.set_xscale("log") ax.set_yscale("log") print("Initial list of stations:") sim_label_to_handle = {} for s in stations: print("{0}".format(s)) assert isinstance(s, Station) print(len([y for y in s.get_list_of_complete_years() if start_year <= y <= end_year])) df_ext_obs = extreme_commons.get_annual_extrema(ts_times=s.dates, ts_vals=s.values, start_year=start_year, end_year=end_year) mp = station_to_modelpoint[s] assert isinstance(mp, ModelPoint) years_of_interest = df_ext_obs.index label_to_extrema_model = {} # label -> ext_type -> [return period -> ret level, return period -> std] label_to_return_levels = OrderedDict( [(obs_label, OrderedDict())] ) for sim_label, sim_path in sim_name_to_file_path.items(): label_to_return_levels[sim_label] = OrderedDict() label_to_extrema_model[sim_label] = OrderedDict() # Calculate the return levels and standard deviations for ext_type in ExtremeProperties.extreme_types: return_periods = ExtremeProperties.extreme_type_to_return_periods[ext_type] # fit GEV distribution and apply non-parametric bootstrap to get std label_to_return_levels[obs_label][ext_type] = gevfit.do_gevfit_for_a_point(df_ext_obs[ext_type].values, extreme_type=ext_type, return_periods=return_periods) return_levels_obs, rl_stds_obs = label_to_return_levels[obs_label][ext_type] # get annual extremas for the model output at the points colose to the stations for sim_label, sim_path in sim_name_to_file_path.items(): label_to_return_levels[sim_label] = OrderedDict() ext_field = analysis.get_annual_extrema( rconfig=RunConfig(data_path=sim_path, start_year=start_year, end_year=end_year), varname="STFL", months_of_interest=ExtremeProperties.extreme_type_to_month_of_interest[ext_type], n_avg_days=ExtremeProperties.extreme_type_to_n_agv_days[ext_type], high_flow=ext_type == ExtremeProperties.high) # Select only those years when obs are available ts_data = [v for y, v in zip(range(start_year, end_year + 1), ext_field[:, mp.ix, mp.jy]) if y in years_of_interest] ts_data = np.array(ts_data) return_levels, rl_stds = gevfit.do_gevfit_for_a_point(ts_data, extreme_type=ext_type, return_periods=return_periods) # Do the plotting for rp in return_periods: ax = ext_type_to_rp_to_ax[ext_type][rp] ax.set_title("T = {rp}-year".format(rp=rp)) # h = ax.errorbar(return_levels_obs[rp], return_levels[rp], # marker=label_to_marker[sim_label], color=label_to_color[sim_label], label=sim_label, # xerr=rl_stds_obs[rp] * 1.96, yerr=rl_stds[rp] * 1.96) h = ax.scatter(return_levels_obs[rp], return_levels[rp], marker=label_to_marker[sim_label], color=label_to_color[sim_label], label=sim_label) # save the data for maybe further calculation of the correlation coefficients label_to_ax_to_xdata[sim_label][ax].append(return_levels_obs[rp]) label_to_ax_to_ydata[sim_label][ax].append(return_levels[rp]) sim_label_to_handle[sim_label] = h # Calculate the biases for sim_label in sim_name_to_file_path: for ext_type in ExtremeProperties.extreme_types: ret_periods = ExtremeProperties.extreme_type_to_return_periods[ext_type] for rp in ret_periods: ax = ext_type_to_rp_to_ax[ext_type][rp] mod = np.asarray(label_to_ax_to_ydata[sim_label][ax]) obs = np.asarray(label_to_ax_to_xdata[sim_label][ax]) bias = np.mean((mod - obs)/obs) corr, pv = stats.pearsonr(mod, obs) print("({sim_label}) Mean bias for {rp}-year {ext_type}-flow return level is: {bias}; corr={corr:.2f}; corr_pval={corr_pval:2g}".format( sim_label=sim_label, rp=rp, bias=bias, corr=corr, corr_pval=pv, ext_type=ext_type )) sfmt = ScalarFormatter(useMathText=True) sfmt.set_powerlimits((-2, 2)) for et, rp_to_ax in ext_type_to_rp_to_ax.items(): for rp, ax in rp_to_ax.items(): xmin, xmax = ax.get_xlim() ymin, ymax = ax.get_ylim() x1 = min(xmin, ymin) x2 = min(xmax, ymax) ax.plot([x1, x2], [x1, x2], "k--") # ax.xaxis.set_major_locator(MaxNLocator(nbins=5)) # ax.yaxis.set_major_locator(MaxNLocator(nbins=5)) # ax.xaxis.set_major_formatter(sfmt) # ax.yaxis.set_major_formatter(sfmt) sim_labels = list(sim_name_to_file_path.keys()) ax_with_legend.legend([sim_label_to_handle[sl] for sl in sim_labels], sim_labels, bbox_to_anchor=(1, -0.25), borderaxespad=0.0, loc="upper right", ncol=2, scatterpoints=1, numpoints=1) # Save the plot img_file = "{}.eps".format("_".join(sorted(label_to_marker.keys()))) img_file = img_folder.joinpath(img_file) fig.tight_layout() with img_file.open("wb") as f: fig.savefig(f, bbox_inches="tight")