Update app.py

Author: Hariprashad-Ravikumar

backend/app.py

@@ -29,13 +29,14 @@
 PLOT_PATH = os.path.join(UPLOAD_FOLDER, "plot.png")
 FORECAST_PLOT_PATH = os.path.join(UPLOAD_FOLDER, "forecast_plot.png")
 REPORT_PATH = os.path.join(UPLOAD_FOLDER, "summary_report.pdf")
+CSV_CACHE = os.path.join(UPLOAD_FOLDER, "cached_upload.csv")
+cached_summary = ""
 
 @atexit.register
 def cleanup_temp_dir():
     TEMP_DIR.cleanup()
 
 log_stream = io.StringIO()
-cached_summary = ""  # Global cache for OpenAI summary
 
 def log_print(*args):
     print(*args, file=log_stream)
@@ -68,34 +69,36 @@ def generate_pdf_report(summary, r2, mse, forecast_dict):
         text.textLine(f"{k}: {v}")
 
     c.drawText(text)
-
     if os.path.exists(FORECAST_PLOT_PATH):
         c.drawImage(FORECAST_PLOT_PATH, 1 * inch, 1 * inch, width=5.5 * inch, preserveAspectRatio=True)
-
     c.save()
 
-@app.route("/")
-def index():
-    return jsonify({"message": "AI DataScience Backend is running on Azure."})
+@app.route("/get-columns", methods=["POST"])
+def get_columns():
+    file = request.files.get("file")
+    if file is None:
+        return jsonify({"error": "No file uploaded"}), 400
+    df = pd.read_csv(file)
+    df.to_csv(CSV_CACHE, index=False)
+    return jsonify({"columns": df.columns.tolist()})
 
 @app.route("/upload", methods=["POST"])
 def upload_file():
     global cached_summary
-
     log_stream.truncate(0)
     log_stream.seek(0)
 
     file = request.files.get("file")
     x_col = request.form.get("x_column")
     y_col = request.form.get("y_column")
-    model_choice = request.form.get("model", "linear")
 
     if file is None or not x_col or not y_col:
         return jsonify({"error": "Missing file or column selection."}), 400
 
     filepath = os.path.join(UPLOAD_FOLDER, file.filename)
     file.save(filepath)
     df = pd.read_csv(filepath)
+    df.to_csv(CSV_CACHE, index=False)
 
     if x_col not in df.columns or y_col not in df.columns:
         return jsonify({"error": f"'{x_col}' or '{y_col}' not in dataset."}), 400
@@ -114,15 +117,12 @@ def upload_file():
 
     df['X_date'] = pd.to_datetime(df['X'], errors='coerce')
     use_dates = df['X_date'].notna().sum() >= len(df) // 2
-    try:
-        if use_dates:
-            df = df.dropna(subset=['X_date'])
-            X = df['X_date'].map(pd.Timestamp.toordinal).values.reshape(-1, 1)
-        else:
-            X = df['X'].astype(float).values.reshape(-1, 1)
-        y = df['Y'].astype(float).values
-    except:
-        return jsonify({"error": "Failed to parse X or Y as numeric or date."}), 400
+    if use_dates:
+        df = df.dropna(subset=['X_date'])
+        X = df['X_date'].map(pd.Timestamp.toordinal).values.reshape(-1, 1)
+    else:
+        X = df['X'].astype(float).values.reshape(-1, 1)
+    y = df['Y'].astype(float).values
 
     model = LinearRegression()
     model.fit(X, y)
@@ -142,11 +142,9 @@ def upload_file():
             ]
         )
         summary = response.choices[0].message.content
-        log_print("Summary generated by OpenAI.")
-        cached_summary = summary  # cache for report
-    except Exception as e:
+        cached_summary = summary
+    except:
         summary = "OpenAI summarization failed."
-        log_print("OpenAI error:", str(e))
         cached_summary = summary
 
     return jsonify({
@@ -164,80 +162,58 @@ def predict():
     if not future_x:
         return jsonify({"forecast": "No future values provided."}), 400
 
-    try:
-        values = future_x.split(",")
-        numeric_vals, date_vals = [], []
-        for x in values:
-            try:
-                date_vals.append(datetime.strptime(x.strip(), "%Y-%m-%d").toordinal())
-            except:
-                numeric_vals.append(float(x.strip()))
-        values_parsed = np.array(date_vals if date_vals else numeric_vals).reshape(-1, 1)
-    except Exception as e:
-        log_print("Parsing future_x failed:", str(e))
-        return jsonify({"forecast": "Invalid format for future values."}), 400
+    values = future_x.split(",")
+    numeric_vals, date_vals = [], []
+    for x in values:
+        try:
+            date_vals.append(datetime.strptime(x.strip(), "%Y-%m-%d").toordinal())
+        except:
+            numeric_vals.append(float(x.strip()))
+    values_parsed = np.array(date_vals if date_vals else numeric_vals).reshape(-1, 1)
 
-    try:
-        files = os.listdir(UPLOAD_FOLDER)
-        csv_file = max(
-            [os.path.join(UPLOAD_FOLDER, f) for f in files if f.endswith(".csv")],
-            key=os.path.getctime
-        )
-        df = pd.read_csv(csv_file)
-        df = df.dropna()
-        df.columns = ['X', 'Y']
-        df['X_date'] = pd.to_datetime(df['X'], errors='coerce')
-        use_dates = df['X_date'].notna().sum() >= len(df) // 2
-
-        if use_dates:
-            df = df.dropna(subset=['X_date'])
-            X = df['X_date'].map(pd.Timestamp.toordinal).values.reshape(-1, 1)
-        else:
-            X = df['X'].astype(float).values.reshape(-1, 1)
-        y = df['Y'].astype(float).values
-
-        model = LinearRegression()
-        model.fit(X, y)
-
-        y_future = model.predict(values_parsed)
-        result = {
-            datetime.fromordinal(int(x)).strftime("%Y-%m-%d") if use_dates else float(x): round(p, 2)
-            for x, p in zip(values_parsed.flatten(), y_future)
-        }
-
-        X_all = np.concatenate((X, values_parsed))
-        x_min, x_max = X_all.min(), X_all.max()
-        x_plot = np.linspace(x_min, x_max, 200).reshape(-1, 1)
-        y_plot = model.predict(x_plot)
-
-        plt.figure()
-        plt.scatter(X, y, label='Training Data', alpha=0.6)
-        plt.plot(x_plot, y_plot, color='blue', label='Regression Line')
-        plt.scatter(values_parsed, y_future, color='red', label='Forecast', marker='x')
-        plt.legend()
-        plt.xlabel('X')
-        plt.ylabel('Y')
-        plt.title('Forecast with Regression Line')
-        plt.savefig(FORECAST_PLOT_PATH)
-        plt.close()
-
-        # PDF report generation
-        generate_pdf_report(cached_summary, r2_score(y, model.predict(X)), mean_squared_error(y, model.predict(X)), result)
-
-        return jsonify({
-            "forecast": result,
-            "log": log_stream.getvalue(),
-            "plot_url": f"{BACKEND_BASE_URL}/plot.png",
-            "forecast_plot_url": f"{BACKEND_BASE_URL}/forecast_plot.png"
-        })
-
-    except Exception as e:
-        log_print("Prediction failed:", str(e))
-        return jsonify({
-            "forecast": "Prediction failed.",
-            "log": log_stream.getvalue(),
-            "plot_url": None
-        })
+    df = pd.read_csv(CSV_CACHE)
+    df.columns = ['X', 'Y']
+    df['X_date'] = pd.to_datetime(df['X'], errors='coerce')
+    use_dates = df['X_date'].notna().sum() >= len(df) // 2
+    if use_dates:
+        df = df.dropna(subset=['X_date'])
+        X = df['X_date'].map(pd.Timestamp.toordinal).values.reshape(-1, 1)
+    else:
+        X = df['X'].astype(float).values.reshape(-1, 1)
+    y = df['Y'].astype(float).values
+
+    model = LinearRegression()
+    model.fit(X, y)
+
+    y_future = model.predict(values_parsed)
+    result = {
+        datetime.fromordinal(int(x)).strftime("%Y-%m-%d") if use_dates else float(x): round(p, 2)
+        for x, p in zip(values_parsed.flatten(), y_future)
+    }
+
+    x_min, x_max = min(X.min(), values_parsed.min()), max(X.max(), values_parsed.max())
+    x_plot = np.linspace(x_min, x_max, 200).reshape(-1, 1)
+    y_plot = model.predict(x_plot)
+
+    plt.figure()
+    plt.scatter(X, y, label='Training Data', alpha=0.6)
+    plt.plot(x_plot, y_plot, color='blue', label='Regression Line')
+    plt.scatter(values_parsed, y_future, color='red', label='Forecast', marker='x')
+    plt.legend()
+    plt.xlabel('X')
+    plt.ylabel('Y')
+    plt.title('Forecast with Regression Line')
+    plt.savefig(FORECAST_PLOT_PATH)
+    plt.close()
+
+    generate_pdf_report(cached_summary, r2_score(y, model.predict(X)), mean_squared_error(y, model.predict(X)), result)
+
+    return jsonify({
+        "forecast": result,
+        "log": log_stream.getvalue(),
+        "plot_url": f"{BACKEND_BASE_URL}/plot.png",
+        "forecast_plot_url": f"{BACKEND_BASE_URL}/forecast_plot.png"
+    })
 
 @app.route("/plot.png")
 def serve_plot():