Modification to make scripts run on server

src/data_utils.py

@@ -7,7 +7,7 @@ import geopandas as gpd
 from concurrent.futures import ThreadPoolExecutor as tpe
 import logging
 
-logging.basicConfig(level=logging.DEBUG, filename='logs/data_utils.log', format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logging.basicConfig(level=logging.INFO, filename='logs/data_utils.log', format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger('data_utils.py')
 stream_handler = logging.StreamHandler()
 formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

src/fill_db.py

@@ -22,10 +22,10 @@ Make sure db_info contain the correct credentials
 """
 db_info = {
     'host': 'localhost',
-    'database': 'test-db23',
+    'database': 'proj_db',
-    'port': '5432',
+    'port': '5433',
-    'user': 'seb',
+    'user': 'sebl',
-    'password': '',
+    'password': 'hatred-pollute-digraph-disciple',
 }
 setup_tables_script = 'setup_tables.sql'
 load_csvs_into_db_script = 'load_csvs_into_db.sql'

src/integrate.py

@@ -113,7 +113,7 @@ def process_foot_bike_data(files_present=True):
     }).reset_index()
     dt_obj = pd.to_datetime(fb_df_grouped['DATE'])
     days = dt_obj.dt.weekday
-    fb_df_grouped['Weekday_en'] = days.map(lambda x: weekday_names[x])
+    fb_df_grouped.loc[:,'Weekday_en'] = days.map(lambda x: weekday_names[x])
     cleaned_fb_df = fb_df_grouped
     cleaned_fb_df['ID'] = cleaned_fb_df.index + 1
     cleaned_fb_df = cleaned_fb_df[['ID', 'NORD', 'OST', 'DATE', 'HRS', 'VELO_IN', 'VELO_OUT', 'FUSS_IN',
@@ -131,14 +131,14 @@ def process_miv_data(files_present=True):
 
     miv_cols_to_keep = ['MSID','ZSID','Achse', 'NKoord', 'EKoord',  'Richtung', 'AnzFahrzeuge', 'AnzFahrzeugeStatus',
                         'Datum', 'Hrs',]
-    miv_df_cols_dropped = miv_df_unified[miv_cols_to_keep]
+    miv_df_cols_dropped = miv_df_unified[miv_cols_to_keep].copy()
 
     dt_obj = pd.to_datetime(miv_df_cols_dropped['Datum'])
     days = dt_obj.dt.weekday
     miv_df_cols_dropped.loc[:, 'Weekday_en'] = days.map(lambda x: weekday_names[x])
 
     miv_df_cols_dropped.loc[:, 'AnzFahrzeuge'] = miv_df_cols_dropped['AnzFahrzeuge'].fillna(0).astype(int)
-    miv_df_cols_dropped[:, 'ZSID'] = miv_df_cols_dropped['ZSID'].fillna('Missing').astype(str)
+    miv_df_cols_dropped.loc[:, 'ZSID'] = miv_df_cols_dropped['ZSID'].fillna('Missing').astype(str)
     miv_df_cols_dropped['ID'] = (miv_df_cols_dropped.index + 1).copy()
 
     cleaned_miv_df = miv_df_cols_dropped[['ID', 'MSID', 'ZSID', 'Achse', 'NKoord', 'EKoord', 'Richtung', 'AnzFahrzeuge',
@@ -239,7 +239,7 @@ def load_tempo_geojson_from_api_to_local():
 
 if __name__ == '__main__':
     # ensure_dirs_exist(data_dir, integrated_dir, logs_dir)
-    # process_all_data_sources(True, True, True)
+    process_all_data_sources(True, False, False)
     # miv_to_integrated_csv()
     # acc_to_cleaned_geojson()
     load_tempo_geojson_from_api_to_local()

src/load_csvs_into_db.sql

@@ -1,7 +1,7 @@
-COPY FootBikeCount FROM '/Users/seb/Projects/repos/group-1/src/datasets/integrated/FootBikeCount.csv'
+COPY FootBikeCount FROM '/home/sebl/group-1/src/datasets/integrated/FootBikeCount.csv'
     DELIMITER ','
     CSV HEADER;
 
-COPY MivCount FROM '/Users/seb/Projects/repos/group-1/src/datasets/integrated/MivCount.csv'
+COPY MivCount FROM '/home/sebl/group-1/src/datasets/integrated/MivCount.csv'
     DELIMITER ','
     CSV HEADER;

src/load_csvs_into_db.sql.backup

@@ -0,0 +1,7 @@
+COPY FootBikeCount FROM '/Users/seb/Projects/repos/group-1/src/datasets/integrated/FootBikeCount.csv'
+    DELIMITER ','
+    CSV HEADER;
+
+COPY MivCount FROM '/Users/seb/Projects/repos/group-1/src/datasets/integrated/MivCount.csv'
+    DELIMITER ','
+    CSV HEADER;