Update app.py

app.py

@@ -8,7 +8,6 @@ def process_file(file_obj):
     if file_obj is None:
         return "Please upload a dataset.", None, None
 
-    # Read file (CSV or Excel)
     try:
         if file_obj.name.endswith(".xlsx"):
             df = pd.read_excel(file_obj)
@@ -17,26 +16,27 @@ def process_file(file_obj):
     except Exception as e:
         return f"Error reading file: {e}", None, None
 
-    # Auto-clean: drop empty rows, normalize numeric columns
+    # Clean
     df = df.dropna(how="all")
-    for col in df.select_dtypes(include="object").columns:
-        df[col] = df[col].str.strip()
-
-    # Example: compute a QualityScore if columns exist
-    if {"NPS","CompletionRate","LearnerSatisfaction","ContentQuality"}.issubset(df.columns):
-        nps_norm = (df["NPS"].astype(float) + 100) / 2
-        score = 0.3*nps_norm + 0.3*(df["CompletionRate"].astype(float)*100) \
-                + 0.2*(df["LearnerSatisfaction"].astype(float)/5*100) \
-                + 0.2*df["ContentQuality"].astype(float)
-        df["QualityScore"] = score.round(1)
-
-        bar = px.bar(df, x="CourseName", y="QualityScore", title="Course Quality Score")
-        heat = px.imshow(df[["NPS","CompletionRate","LearnerSatisfaction","ContentQuality"]].T,
-                         x=df["CourseName"], aspect="auto", title="Metrics Heatmap")
-        return df, bar, heat
-    else:
+
+    # Check required columns
+    required = {"CourseName","NPS","CompletionRate","LearnerSatisfaction","ContentQuality"}
+    if not required.issubset(df.columns):
         return "Dataset missing expected columns (NPS, CompletionRate, etc.)", None, None
 
+    # Compute QualityScore
+    nps_norm = (df["NPS"].astype(float) + 100) / 2
+    score = 0.3*nps_norm + 0.3*(df["CompletionRate"].astype(float)*100) \
+            + 0.2*(df["LearnerSatisfaction"].astype(float)/5*100) \
+            + 0.2*df["ContentQuality"].astype(float)
+    df["QualityScore"] = score.round(1)
+
+    bar = px.bar(df, x="CourseName", y="QualityScore", title="Course Quality Score")
+    heat = px.imshow(df[["NPS","CompletionRate","LearnerSatisfaction","ContentQuality"]].T,
+                     x=df["CourseName"], aspect="auto", title="Metrics Heatmap")
+
+    return df, bar, heat
+
 demo = gr.Interface(
     fn=process_file,
     inputs=gr.File(label="Upload CSV/XLSX"),