db = [] for rf in tqdm.tqdm_notebook(results_files): if rf.endswith(".csv"): loaded = ScmDataFrame(rf) else: loaded = ScmDataFrame(rf, sheet_name="your_data") db.append(loaded) db = df_append(db).timeseries().reset_index() db["unit"] = db["unit"].apply(lambda x: x.replace( "Dimensionless", "dimensionless") if isinstance(x, str) else x) db = ScmDataFrame(db) db.head() # %% db.filter(climatemodel="*cicero*").head() # %% db["climatemodel"].unique() # %% [markdown] # ### Minor quick fixes # %% [markdown] # We relabel all the ssp370-lowNTCF data to remove ambiguity. # %% db = db.timeseries().reset_index() db["scenario"] = db["scenario"].apply(lambda x: "ssp370-lowNTCF-gidden" if x == "ssp370-lowNTCF" else x) db["scenario"] = db["scenario"].apply(lambda x: "esm-ssp370-lowNTCF-gidden"
relevant_files = [str(p) for p in relevant_files if quantile not in p] print("Number of relevant files: {}".format(len(relevant_files))) relevant_files # %% [markdown] # ### Read in all variables: # %% jupyter={"outputs_hidden": false} pycharm={"name": "#%%\n"} db = [] for rf in tqdm.tqdm_notebook(relevant_files): # print(rf.endswith('sf')) if rf.endswith(".csv"): loaded = ScmDataFrame(rf) else: loaded = ScmDataFrame(rf, sheet_name="your_data") db.append(loaded.filter(variable=variables_erf, scenario=scenarios_fl)) # variables_of_interest)) print(db) db = df_append(db).timeseries().reset_index() db["unit"] = db["unit"].apply(lambda x: x.replace( "Dimensionless", "dimensionless") if isinstance(x, str) else x) clear_output() db = ScmDataFrame(db) db.head() # %% jupyter={"outputs_hidden": false} pycharm={"name": "#%%\n"} db[variable].unique() # %% db[climatemodel].unique() # %%