adapt preprocessing to new title loading

preprocess_de.py

@@ -1,17 +1,30 @@
 import pandas as pd
 import os
 
+title_file = "filename_to_titles.csv"
+
 # Preprocess data
 vote_counter = -1
 data = pd.DataFrame()
 
 name_column = 'Bezeichnung'
 
-column_to_filename = {}
+# Load filename to 
+filename_to_title_map = {}
+
+with open(os.path.join("./de/csv/", title_file), 'r') as file:
+    for line in file.readlines():
+        filename, title = line.split(';', 2)
+        filename_to_title_map[filename] = title
+
+
+
+vote_column_to_title = {}
 
 voting_features = ['ja', 'nein', 'Enthaltung', 'ungültig']
 for dirname, _, filenames in os.walk('./de/csv'):
     for filename in filenames:
+        if filename != title_file:
             vote_counter += 1
             print(os.path.join(dirname, filename))
             df = pd.read_csv(os.path.join(dirname, filename))
@@ -21,7 +34,7 @@ for dirname, _, filenames in os.walk('./de/csv'):
                 df[feature] *= i
             vote_column_name = f'vote_{vote_counter}'
             # Map column name of vote to filename -> allows retrieving what the vote was about
-        column_to_filename[vote_column_name] = filename
+            vote_column_to_title[vote_column_name] = filename_to_title_map[filename]
             
             # add feature for the vote
             df[vote_column_name] = df[voting_features].sum(axis=1)
@@ -33,5 +46,5 @@ for dirname, _, filenames in os.walk('./de/csv'):
                 # merge data with already loaded data 
                 data = data.merge(df[[name_column, vote_column_name]], on=name_column)
 
-print(column_to_filename)
+print(vote_column_to_title)
 print(data)