Implement script for checking study points compliance

- Added a Python script to read data from 'scriptie.xlsx' and 'dashboard_inschrijvingen.xlsx'.
- Implemented functions to find common ID columns and relevant columns based on keywords.
- Merged dataframes on the common ID column and filtered for entries with 'Target OO' containing '1070FLWGES'.
- Calculated thresholds for study points and identified violations based on specified criteria.
- Generated a report of violations saved as both CSV and Excel formats.
- Added sample violation data to 'violations_report.csv'.

startpakketten/checkheaders.py

@@ -37,13 +37,26 @@ def check_headers_predelibfile(df):
         df = df[existing_columns]
 
         print(f"Deleted {header_row} rows, set proper headers, and kept {len(existing_columns)} columns")
-        return df
     else:
         print("Headers 'Achternaam' and 'Voornaam' not found in the file")
         return df
+    
+    if 'Programma status omschrijving' in df.columns:
+        before = len(df)
+        mask = df['Programma status omschrijving'].astype(str).str.contains(r'\bBeëindigd\b', case=False, na=False)
+        df = df[~mask].reset_index(drop=True)
+        removed = before - len(df)
+        print(f"Removed {removed} rows where Programma status omschrijving contains 'Beëindigd'")
+    else:
+        print("Column 'Programma status omschrijving' not found; no rows removed")
+
+    return df
+    
+
+
 
 def check_headers_dashboard_inschrijvingenfile(df):
-     # Check if the headers are already in the column names (first row)
+    # Check if the headers are already in the column names (first row)
     if 'Naam' in df.columns and 'Voornaam' in df.columns:
         print("Headers found in first row  of dashboard_inschrijvingen - no need to search for header row")
         header_row = -1  # Indicates headers are already set
@@ -55,7 +68,8 @@ def check_headers_dashboard_inschrijvingenfile(df):
                 header_row = i
                 break
 
-    if header_row is not None:
+    # Apply headers only when a valid header row was found (>= 0)
+    if header_row is not None and header_row >= 0:
         # Delete all rows before the header row
         df = df.iloc[header_row:].reset_index(drop=True)
 
@@ -63,16 +77,26 @@ def check_headers_dashboard_inschrijvingenfile(df):
         df.columns = df.iloc[0]
         df = df.iloc[1:].reset_index(drop=True)
 
-        if header_row is not None and header_row >= 0:
-            print(f"Deleted {header_row} rows in dashboard_file, set proper headers")
-        elif header_row == -1:
-            print(f"Headers were already correct in dashboard_file.")
-        
-        return df
+        print(f"Deleted {header_row} rows in dashboard_file, set proper headers")
+    elif header_row == -1:
+        # Headers were already correct; nothing to change
+        print("Headers were already correct in dashboard_file.")
     else:
-        print("Headers 'Achternaam' and 'Voornaam' not found in the file")
+        print("Headers 'Naam' and 'Voornaam' not found in the file")
         return df
 
+    # Remove rows where Status contains 'Beëindigd'
+    if 'Status' in df.columns:
+        before = len(df)
+        mask = df['Status'].astype(str).str.contains(r'\bBeëindigd\b', case=False, na=False)
+        df = df[~mask].reset_index(drop=True)
+        removed = before - len(df)
+        print(f"Removed {removed} rows where Status contains 'Beëindigd'")
+    else:
+        print("Column 'Status' not found; no rows removed")
+
+    return df
+
 
 if __name__ == "__main__":
     # Read the Excel files