if not os.path.isdir(OUTPUT_DATABASE_PATH): make_folders(OUTPUT_DATABASE_PATH) if not os.path.isdir(OBS_DATABASE_PATH): make_folders(OBS_DATABASE_PATH) # %% [markdown] # ## Protocol # %% SCENARIO_PROTOCOL = os.path.join(INPUT_DATA_DIR, "data", "protocol", "rcmip-emissions-annual-means.csv") # %% protocol_db = ScmDataFrame(SCENARIO_PROTOCOL) protocol_db.head() # %% protocol_db["scenario"].unique() # %% DATA_PROTOCOL = os.path.join( INPUT_DATA_DIR, "data", "submission-template", "rcmip-data-submission-template.xlsx", ) # %% protocol_variables = pd.read_excel(DATA_PROTOCOL, sheet_name="variable_definitions")
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() # %% db[scenario].unique() # %% db['unit'].unique() # %% for cm in db[climatemodel].unique():