Everything its working

.gitignore

@@ -182,4 +182,5 @@ LinQAChecker-saved.json
 minors_madrid/
 minors_zaragoza/
 DESCARGAS/
+sproc/DESCARGA_PLACE_NOV
 

nbs/40_io.ipynb

@@ -1599,7 +1599,7 @@
     "    \"Homogenizes the elements in a list such that they are all either `float` or `str`\"\n",
     "    \n",
     "    # *scalar* Pandas' `pd.NA` are turned into Numpy's `np.nan`\n",
-    "    l = [np.NAN if (type(e) != list) and (pd.isna(e)) else e for e in l]\n",
+    "    l = [np.nan if (type(e) != list) and (pd.isna(e)) else e for e in l]\n",
     "    \n",
     "    try:\n",
     "        return [float(e) for e in l]\n",
@@ -1636,7 +1636,7 @@
     }
    ],
    "source": [
-    "cast_list_to_floats_or_strs([np.NAN, '14.1'])"
+    "cast_list_to_floats_or_strs([np.nan, '14.1'])"
    ]
   },
   {
@@ -1665,7 +1665,7 @@
     }
    ],
    "source": [
-    "cast_list_to_floats_or_strs([np.NAN, '14.1', 'hola'])"
+    "cast_list_to_floats_or_strs([np.nan, '14.1', 'hola'])"
    ]
   },
   {

run_all.py

@@ -1,10 +1,13 @@
 from sproc.core import dl, cli_read_single_zip, cli_rename_columns, read_zips, cli_extend_parquet_with_zip
-
 import argparse
 import pathlib
 import sys
 import yaml
 
+# Script to run the different actions of the sproc package
+# It is recommended to run this script from the command line with the following command:
+# python3 run_all.py --contract_type outsiders --save_path /path/to/save/place/data 
+
 def main():
     parser = argparse.ArgumentParser(description="sproc")
     #Para tener control sobre las acciones a realizar. Se configura el arg "option" 

sproc/core.py

@@ -329,6 +329,7 @@ def dl(
 
     # Define las columnas objetivo
     columna_objetivo = (
+        'ContractFolderStatus.ContractFolderID',
         'ContractFolderStatus.TenderingTerms.FundingProgram',
         'ContractFolderStatus.TenderingTerms.ProcurementNationalLegislationCode'
     )    
@@ -339,6 +340,10 @@ def dl(
                 parquet_df[col_original] = parquet_df[col_original].astype('string')           
         else:
             print(f"La columna '{col_obj}' no se está en el DataFrame. Pero la descarga se ha completado correctamente")
+
+    #import pdb; pdb.set_trace()
+
+    print(parquet_df.columns)
     # parquet_df.to_parquet(output_file.with_stem('new'))
     parquet_df.to_parquet(output_file)
 

sproc/io.py

@@ -78,7 +78,9 @@ def cast_list_to_floats_or_strs(l: # Input
     "Homogenizes the elements in a list such that they are all either `float` or `str`"
 
     # *scalar* Pandas' `pd.NA` are turned into Numpy's `np.nan`
-    l = [np.NAN if (type(e) != list) and (pd.isna(e)) else e for e in l]
+    #l = [np.NAN if (type(e) != list) and (pd.isna(e)) else e for e in l] DEPRECATED VERSION OF NUMPY NAN (Updated 14/11/2024)-> np.nan
+    l = [np.nan if (type(e) != list) and (pd.isna(e)) else e for e in l]
+
 
     try:
         return [float(e) for e in l]