script: join job prediction & job infos

README.md

@@ -53,3 +53,8 @@ nix develop .#use-python-scripts --command m100-agg-danilo-estimations danilo-du
 ```sh
 nix develop .#use-python-scripts --command m100-agg-jobs-info ./m100-data/ ./m100-data/22-jobs.csv 22-01 22-02 22-03 22-04 22-05 22-06 22-07 22-08 22-09
 ```
+
+## merge power estimations with job informations into a single file
+```sh
+nix develop .#use-python-scripts --command m100-join-usable-jobs-info ./m100-data/22-job-power-estimations.csv ./m100-data/22-jobs.csv ./m100-data/22-jobs-with-prediction.csv
+```

scripts-py/expe_energumen/m100_join_usable_jobs_info.py

+#!/usr/bin/env python3
+import argparse
+import csv
+import os
+import pandas as pd
+
+def join():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("input_prediction_csv_file", help='filepath to the job power prediction file')
+    parser.add_argument("input_jobs_info_csv_file", help='filepath to the job information file')
+    parser.add_argument("output_file", help="where to write the result CSV file")
+    args = parser.parse_args()
+
+    prediction_df = pd.read_csv(args.input_prediction_csv_file)
+    jobs_info_df = pd.read_csv(args.input_jobs_info_csv_file)
+    prediction_df.merge(jobs_info_df, how='left').to_csv(args.output_file, index=False, quoting=csv.QUOTE_NONNUMERIC)

scripts-py/pyproject.toml

@@ -12,3 +12,4 @@ m100-data-downloader = "expe_energumen.m100_data_downloader:main"
 m100-agg-power-months = "expe_energumen.m100_agg_month_power_values:several_months"
 m100-agg-danilo-estimations = "expe_energumen.m100_agg_danilo_estimations:agg_all_files"
 m100-agg-jobs-info = "expe_energumen.m100_agg_jobs_info:several_months"
+m100-join-usable-jobs-info = "expe_energumen.m100_join_usable_jobs_info:join"