Update app.py

app.py

@@ -2,52 +2,73 @@ import gradio as gr
 import pandas as pd
 import matplotlib.pyplot as plt
 
-# ---------- CLEAN DATA ----------
+# ---------- CLEAN DATA (ROBUST VERSION) ----------
 def clean_data(file):
-    df = pd.read_csv(file)
-
-    # normalize column names
-    df.columns = df.columns.str.strip().str.lower()
-
-    # flexible column mapping
-    rename_map = {}
-    for col in df.columns:
-        if "course" in col:
-            rename_map[col] = "Course Name"
-        elif "nps" in col:
-            rename_map[col] = "NPS Score"
-        elif "completion" in col:
-            rename_map[col] = "Completion Rate (%)"
-        elif "satisfaction" in col or "rating" in col:
-            rename_map[col] = "Satisfaction (1-5)"
-
-    df = df.rename(columns=rename_map)
+    try:
+        # read raw lines
+        with open(file.name if file else "sample.csv", "r", encoding="utf-8") as f:
+            lines = f.readlines()
+
+        # detect header row
+        header_index = None
+        for i, line in enumerate(lines):
+            if "course" in line.lower() and ("nps" in line.lower() or "completion" in line.lower()):
+                header_index = i
+                break
+
+        if header_index is None:
+            return pd.DataFrame()
+
+        # read actual data
+        df = pd.read_csv(file.name if file else "sample.csv", skiprows=header_index)
+
+        # normalize column names
+        df.columns = df.columns.str.strip().str.lower()
+
+        # flexible mapping
+        rename_map = {}
+        for col in df.columns:
+            if "course" in col:
+                rename_map[col] = "Course Name"
+            elif "nps" in col:
+                rename_map[col] = "NPS Score"
+            elif "completion" in col:
+                rename_map[col] = "Completion Rate (%)"
+            elif "satisfaction" in col or "rating" in col:
+                rename_map[col] = "Satisfaction (1-5)"
+
+        df = df.rename(columns=rename_map)
+
+        # ensure required columns
+        required = ["Course Name", "NPS Score", "Completion Rate (%)", "Satisfaction (1-5)"]
+        for col in required:
+            if col not in df.columns:
+                df[col] = None
+
+        # clean numeric values
+        for col in ["NPS Score", "Completion Rate (%)", "Satisfaction (1-5)"]:
+            df[col] = df[col].astype(str).str.replace('%', '', regex=False)
+            df[col] = df[col].astype(str).str.replace('/5', '', regex=False)
+            df[col] = pd.to_numeric(df[col], errors="coerce")
+
+        df = df.dropna()
 
-    # ensure required columns exist
-    required = ["Course Name", "NPS Score", "Completion Rate (%)", "Satisfaction (1-5)"]
-    for col in required:
-        if col not in df.columns:
-            df[col] = None
+        if df.empty:
+            return df
 
-    # convert to numeric safely
-    for col in ["NPS Score", "Completion Rate (%)", "Satisfaction (1-5)"]:
-        df[col] = pd.to_numeric(df[col], errors="coerce")
+        # health score
+        df["Health Score"] = (
+            (df["NPS Score"] * 0.4) +
+            (df["Completion Rate (%)"] * 0.3) +
+            (df["Satisfaction (1-5)"] * 20 * 0.3)
+        )
 
-    df = df.dropna()
+        df["Needs Attention"] = df["Health Score"] < 60
 
-    if df.empty:
         return df
 
-    # health score
-    df["Health Score"] = (
-        (df["NPS Score"] * 0.4) +
-        (df["Completion Rate (%)"] * 0.3) +
-        (df["Satisfaction (1-5)"] * 20 * 0.3)
-    )
-
-    df["Needs Attention"] = df["Health Score"] < 60
-
-    return df
+    except:
+        return pd.DataFrame()
 
 
 # ---------- CHARTS ----------
@@ -65,36 +86,13 @@ def charts(df):
     return fig1, fig2
 
 
-# ---------- MAIN PROCESS ----------
+# ---------- PROCESS ----------
 def process(file):
-    try:
-        if file is None:
-            df = pd.read_csv("sample.csv")
-            df = clean_data("sample.csv")
-        else:
-            df = clean_data(file)
+    df = clean_data(file)
 
-        if df.empty:
-            return (
-                pd.DataFrame({"Message": ["No valid data found. Check your CSV."]}),
-                pd.DataFrame(),
-                pd.DataFrame(),
-                pd.DataFrame(),
-                None,
-                None
-            )
-
-        top_courses = df.sort_values(by="Health Score", ascending=False).head(3)
-        worst_courses = df.sort_values(by="Health Score").head(3)
-        attention = df[df["Needs Attention"] == True]
-
-        fig1, fig2 = charts(df)
-
-        return df, top_courses, worst_courses, attention, fig1, fig2
-
-    except Exception as e:
+    if df.empty:
         return (
-            pd.DataFrame({"Error": [str(e)]}),
+            pd.DataFrame({"Message": ["No valid data found. Check your CSV structure."]}),
             pd.DataFrame(),
             pd.DataFrame(),
             pd.DataFrame(),
@@ -102,12 +100,25 @@ def process(file):
             None
         )
 
+    top_courses = df.sort_values(by="Health Score", ascending=False).head(3)
+    worst_courses = df.sort_values(by="Health Score").head(3)
+    attention = df[df["Needs Attention"] == True]
+
+    fig1, fig2 = charts(df)
+
+    return df, top_courses, worst_courses, attention, fig1, fig2
+
+
+# ---------- DEFAULT LOAD ----------
+def load_default():
+    return process(None)
+
 
 # ---------- UI ----------
 with gr.Blocks() as app:
     gr.Markdown("# 📊 Course Quality Tracker")
 
-    gr.Markdown("Upload a CSV or use default sample dataset.")
+    gr.Markdown("Upload a CSV or view sample dataset.")
 
     file_input = gr.File(label="Upload CSV")
 
@@ -133,10 +144,9 @@ with gr.Blocks() as app:
         outputs=[table, top_table, worst_table, attention_table, chart1, chart2]
     )
 
-    # load default data on start
     app.load(
-        fn=process,
-        inputs=None,
+        fn=load_default,
+        inputs=[],
         outputs=[table, top_table, worst_table, attention_table, chart1, chart2]
     )