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'.

bascriptie studiepunten controle/script.py

@@ -0,0 +1,104 @@
+import os
+import sys
+import pandas as pd
+import numpy as np
+
+SCRIPT_DIR = os.path.dirname(__file__)
+SCRIPTIE_XLSX = os.path.join(SCRIPT_DIR, "scriptie.xlsx")
+DASH_XLSX = os.path.join(SCRIPT_DIR, "dashboard_inschrijvingen.xlsx")
+
+
+def find_common_id_col(df1, df2):
+    common = set(df1.columns).intersection(df2.columns)
+    # prefer obvious id-like names
+    for kw in ("ID"):
+        for c in common:
+            if kw in c.lower():
+                return c
+    if len(common) == 1:
+        return next(iter(common))
+    if common:
+        return sorted(common)[0]
+    raise ValueError(f"No common column found between files.\nFile1 cols: {df1.columns.tolist()}\nFile2 cols: {df2.columns.tolist()}")
+
+
+def find_col_by_keywords(df, keywords):
+    for k in keywords:
+        for c in df.columns:
+            if k in c.lower():
+                return c
+    return None
+
+
+def main():
+    if not os.path.exists(SCRIPTIE_XLSX) or not os.path.exists(DASH_XLSX):
+        print("Missing files. Make sure scriptie.xlsx and dashboard_inschrijvingen.xlsx are in the script folder.")
+        sys.exit(1)
+
+    df_scriptie = pd.read_excel(SCRIPTIE_XLSX)
+    df_dash = pd.read_excel(DASH_XLSX)
+
+    try:
+        id_col = find_common_id_col(df_scriptie, df_dash)
+    except ValueError as e:
+        print(e)
+        sys.exit(1)
+
+    # find relevant columns (best-effort)
+    col_target_oo = find_col_by_keywords(df_scriptie, ["target oo", "target_oo", "targetoo", "target oo"])
+    col_target_plan = find_col_by_keywords(df_scriptie, ["target plan", "target_plan", "targetplan", "target"])
+    col_sp = find_col_by_keywords(df_dash, ["sp", "punten", "ects", "study points"])
+
+    if col_target_oo is None or col_target_plan is None or col_sp is None:
+        print("Could not locate required columns. Detected:")
+        print("scriptie columns:", df_scriptie.columns.tolist())
+        print("dashboard columns:", df_dash.columns.tolist())
+        print(f"Found -> target_oo: {col_target_oo}, target_plan: {col_target_plan}, SP: {col_sp}")
+        sys.exit(1)
+
+    merged = df_scriptie.merge(df_dash, on=id_col, how="inner", suffixes=("_scriptie", "_dash"))
+
+    # filter rows where Target OO contains 1070FLWGES
+    mask_oo = merged[col_target_oo].astype(str).str.contains("1070FLWGES", na=False)
+
+    subset = merged[mask_oo].copy()
+    if subset.empty:
+        print("No rows with Target OO containing '1070FLWGES'. No violations.")
+        return
+
+    # determine thresholds per row: default 180-9 = 171, if Target plan contains 'Ba geschiedenis (major)' then 180-12 = 168
+    plan_contains = subset[col_target_plan].astype(str).str.contains("ba geschiedenis (major)", case=False, na=False)
+    subset["threshold"] = np.where(plan_contains, 180 - 12, 180 - 9)
+
+    # coerce SP to numeric (non-numeric become NaN)
+    subset["SP_value"] = pd.to_numeric(subset[col_sp], errors="coerce")
+
+    # violation: SP is NaN or SP < threshold
+    violations = subset[subset["SP_value"] < subset["threshold"]]
+
+    # also consider NaN as violation
+    nan_viol = subset[subset["SP_value"].isna()]
+    violations = pd.concat([violations, nan_viol]).drop_duplicates()
+
+    if violations.empty:
+        print("No violations found for entries with Target OO == 1070FLWGES.")
+        return
+
+    report_cols = [id_col, col_sp, "SP_value", "threshold", col_target_plan, col_target_oo]
+    report = violations.loc[:, [id_col, col_sp, "SP_value", "threshold", col_target_plan, col_target_oo]]
+    report = report.rename(columns={col_sp: "SP_raw", col_target_plan: "Target_plan", col_target_oo: "Target_OO"})
+
+    out_csv = os.path.join(SCRIPT_DIR, "violations_report.csv")
+    out_xlsx = os.path.join(SCRIPT_DIR, "violations_report.xlsx")
+    report.to_csv(out_csv, index=False)
+    try:
+        report.to_excel(out_xlsx, index=False)
+    except Exception:
+        pass
+
+    print(f"Found {len(report)} violation(s). Saved to: {out_csv} (and {out_xlsx} if Excel write succeeded).")
+    print(report.to_string(index=False))
+
+
+if __name__ == "__main__":
+    main()

bascriptie studiepunten controle/violations_report.csv

@@ -0,0 +1,3 @@
+ID,SP_raw,SP_value,threshold,Target_plan,Target_OO
+20224729,168,168,171,Ba geschiedenis,1070FLWGES
+20224915,162,162,171,Ba geschiedenis,1070FLWGES

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")
-            print(f"Deleted {header_row} rows in dashboard_file, set proper headers")
+    elif header_row == -1:
-        elif header_row == -1:
+        # Headers were already correct; nothing to change
-            print(f"Headers were already correct in dashboard_file.")
+        print("Headers were already correct in dashboard_file.")
-        
-        return df
     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