Update app.py

Author: Hariprashad-Ravikumar

backend/app.py

@@ -14,6 +14,9 @@
 from datetime import datetime
 import tempfile
 import atexit
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from reportlab.lib.units import inch
 
 # === CONFIG ===
 BACKEND_BASE_URL = "https://ai-dslab-backend-cpf2feachnetbbck.westus-01.azurewebsites.net"
@@ -25,24 +28,60 @@
 UPLOAD_FOLDER = TEMP_DIR.name
 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.txt")
+REPORT_PATH = os.path.join(UPLOAD_FOLDER, "summary_report.pdf")
 
 @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)
     sys.stdout.flush()
 
+def generate_pdf_report(summary, r2, mse, forecast_dict):
+    c = canvas.Canvas(REPORT_PATH, pagesize=letter)
+    width, height = letter
+    text = c.beginText(1 * inch, height - 1 * inch)
+
+    text.setFont("Helvetica-Bold", 14)
+    text.textLine("AI Forecast Report")
+    text.setFont("Helvetica", 10)
+    text.textLine(f"Model: Linear Regression")
+    text.textLine(f"R² Score: {r2:.4f}")
+    text.textLine(f"MSE: {mse:.4f}")
+    text.textLine("")
+
+    text.setFont("Helvetica-Bold", 12)
+    text.textLine("OpenAI Data Summary:")
+    text.setFont("Helvetica", 9)
+    for line in summary.splitlines():
+        text.textLine(line)
+
+    text.textLine("")
+    text.setFont("Helvetica-Bold", 12)
+    text.textLine("Forecast Results:")
+    text.setFont("Helvetica", 10)
+    for k, v in forecast_dict.items():
+        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("/upload", methods=["POST"])
 def upload_file():
+    global cached_summary
+
     log_stream.truncate(0)
     log_stream.seek(0)
 
@@ -63,9 +102,8 @@ def upload_file():
 
     df = df[[x_col, y_col]].dropna()
     df.columns = ['X', 'Y']
-    log_print("Cleaned Data:\n", df.head())
+    log_print("Cleaned Data:\n\n", df.head())
 
-    # Scatter plot
     plt.figure()
     plt.scatter(df['X'], df['Y'])
     plt.xlabel('X')
@@ -74,7 +112,6 @@ def upload_file():
     plt.savefig(PLOT_PATH)
     plt.close()
 
-    # Try parsing X as datetime
     df['X_date'] = pd.to_datetime(df['X'], errors='coerce')
     use_dates = df['X_date'].notna().sum() >= len(df) // 2
     try:
@@ -87,18 +124,13 @@ def upload_file():
     except:
         return jsonify({"error": "Failed to parse X or Y as numeric or date."}), 400
 
-    if model_choice == "linear":
-        model = LinearRegression()
-    else:
-        return jsonify({"error": "Only linear regression supported for now."}), 400
-
+    model = LinearRegression()
     model.fit(X, y)
     y_pred = model.predict(X)
     r2 = r2_score(y, y_pred)
     mse = mean_squared_error(y, y_pred)
     log_print(f"Model Trained. R² = {r2:.4f}, MSE = {mse:.4f}")
 
-    # OpenAI Summary
     try:
         openai.api_key = os.getenv("OPENAI_API_KEY")
         client = openai.OpenAI(api_key=openai.api_key)
@@ -111,9 +143,11 @@ 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:
         summary = "OpenAI summarization failed."
         log_print("OpenAI error:", str(e))
+        cached_summary = summary
 
     return jsonify({
         "summary": summary,
@@ -167,11 +201,10 @@ def predict():
 
         y_future = model.predict(values_parsed)
         result = {
-            (datetime.fromordinal(int(x)) if use_dates else float(x)): round(p, 2)
+            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)
         }
 
-        # Generate second plot
         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)
@@ -188,19 +221,11 @@ def predict():
         plt.savefig(FORECAST_PLOT_PATH)
         plt.close()
 
-        # Write report
-        with open(REPORT_PATH, 'w') as f:
-            f.write("AI Forecast Report\\n")
-            f.write("=================\\n\\n")
-            f.write("Model: Linear Regression\\n")
-            f.write(f"R² Score: {r2_score(y, model.predict(X)):.4f}\\n")
-            f.write(f"MSE: {mean_squared_error(y, model.predict(X)):.4f}\\n")
-            f.write("\\nForecast Results:\\n")
-            for k, v in result.items():
-                f.write(f"{k}: {v}\\n")
+        # 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": {str(k): v for k, v in result.items()},
+            "forecast": result,
             "log": log_stream.getvalue(),
             "plot_url": f"{BACKEND_BASE_URL}/plot.png",
             "forecast_plot_url": f"{BACKEND_BASE_URL}/forecast_plot.png"
@@ -224,4 +249,4 @@ def serve_forecast_plot():
 
 @app.route("/download-report", methods=["GET"])
 def download_report():
-    return send_file(REPORT_PATH, as_attachment=True, download_name="report.txt")
+    return send_file(REPORT_PATH, as_attachment=True, download_name="report.pdf")