Update app.py

app.py

@@ -17,12 +17,11 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import numpy as np
 
-# Import Hugging Face transformers pipeline for text generation
+# Hugging Face transformers pipeline import
 from transformers import pipeline
 
 weather_map = {"Cloudy": 0, "Rainy": 1, "Sunny": 2}
 
-# Load and preprocess data
 print("Loading and preprocessing data...")
 try:
     if not os.path.exists("new_delay_data.csv"):
@@ -38,19 +37,18 @@ try:
     else:
         df = pd.read_csv("new_delay_data.csv")
     
-    df = pd.get_dummies(df, columns=["Phase"], drop_first=True)  # Finishing as baseline
+    df = pd.get_dummies(df, columns=["Phase"], drop_first=True)
     df["Weather"] = df["Weather"].map(weather_map)
     df.dropna(subset=["Weather", "Absentee", "DelayLog", "Delay%"], inplace=True)
     
     for col in ["Phase_Framing", "Phase_Foundation"]:
         if col not in df.columns:
             df[col] = 0
-    print("Data loaded and preprocessed successfully. Columns:", df.columns.tolist())
+    print("Data loaded and preprocessed. Columns:", df.columns.tolist())
 except Exception as e:
     print(f"Error loading data: {e}")
     raise
 
-# Split features and target
 try:
     X = df[["Phase_Framing", "Phase_Foundation", "Weather", "Absentee", "DelayLog"]]
     y = df["Delay%"]
@@ -58,7 +56,6 @@ except Exception as e:
     print(f"Error preparing features: {e}")
     raise
 
-# Train Linear Regression model
 print("Training model...")
 try:
     model = LinearRegression()
@@ -68,37 +65,34 @@ except Exception as e:
     print(f"Error training model: {e}")
     raise
 
-# Load GPT-2 text generation pipeline for AI insights and migration plans
-print("Loading AI text generation model...")
+print("Loading AI text generation model (EleutherAI/gpt-neo-125M)...")
 try:
-    text_generator = pipeline("text-generation", model="gpt2")
+    text_generator = pipeline("text-generation", model="EleutherAI/gpt-neo-125M")
     print("Text generation model loaded successfully.")
 except Exception as e:
     print(f"Failed to load text generation model: {e}")
     raise
 
-# Generate AI insight and migration plan dynamically
 def generate_ai_insight(phase, weather, absentee_pct, delay_log, prediction):
     prompt = (
-        f"Project phase: {phase}. Weather: {weather}. "
-        f"Absentee percentage: {absentee_pct}%. Previous delay log: {delay_log}. "
-        f"Predicted delay: {prediction}%. "
-        "Provide a concise AI-generated insight about delay risks and a practical migration plan "
-        "to reduce these delays and improve project efficiency."
+        f"You are an expert construction project manager.\n"
+        f"Project phase: {phase}\n"
+        f"Weather: {weather}\n"
+        f"Absenteeism rate: {absentee_pct}%\n"
+        f"Previous delay log: {delay_log}\n"
+        f"Predicted delay percentage: {prediction}%\n"
+        f"Provide a brief insight on the delay risks and a practical migration plan to mitigate these delays."
     )
     try:
-        result = text_generator(prompt, max_length=150, num_return_sequences=1)
+        result = text_generator(prompt, max_length=120, num_return_sequences=1, temperature=0.7, top_p=0.9)
         generated_text = result[0]['generated_text']
-        # Strip out prompt to get only generated part
         insight = generated_text[len(prompt):].strip()
         return insight
     except Exception as e:
         print(f"AI insight generation failed: {e}")
         return "AI insight generation failed. Please check logs."
 
-# Heatmap generation function (unchanged)
 def generate_heatmap(phase, weather, model):
-    print("Generating heatmap...")
     try:
         absentee_range = np.linspace(0, 100, 20)
         delay_log_range = np.linspace(0, 20, 20)
@@ -125,15 +119,12 @@ def generate_heatmap(phase, weather, model):
         heatmap_path = os.path.join(output_dir, f"heatmap_{timestamp}.png")
         plt.savefig(heatmap_path, bbox_inches='tight')
         plt.close()
-        print(f"Heatmap saved at: {heatmap_path}")
         return heatmap_path
     except Exception as e:
         print(f"Heatmap generation failed: {e}")
         return None
 
-# PDF generation function (unchanged except uses AI-generated insight)
 def generate_pdf_report(phase, weather, absentee_pct, delay_log, prediction, risk, insight):
-    print("Generating PDF report...")
     try:
         buffer = BytesIO()
         c = canvas.Canvas(buffer, pagesize=letter)
@@ -193,16 +184,13 @@ def generate_pdf_report(phase, weather, absentee_pct, delay_log, prediction, ris
         output_path = os.path.join(output_dir, f"delay_report_{timestamp}.pdf")
         with open(output_path, "wb") as f:
             f.write(pdf_data)
-        print(f"PDF saved locally at: {output_path}")
         
         return pdf_base64, output_path, heatmap_path
     except Exception as e:
         print(f"PDF generation failed: {e}")
         return None, None, None
 
-# Main prediction logic
 def predict_delay(phase, weather, absentee_pct, delay_log):
-    print(f"Predicting delay for Phase: {phase}, Weather: {weather}, Absentee: {absentee_pct}, Delay Log: {delay_log}")
     try:
         valid_phases = ["Framing", "Foundation", "Finishing"]
         valid_weather = ["Sunny", "Rainy", "Cloudy"]
@@ -235,12 +223,10 @@ def predict_delay(phase, weather, absentee_pct, delay_log):
         print(f"Prediction error: {e}")
         return None, None, f"Error: {e}", None, None, None
 
-# FastAPI app
 api_app = FastAPI()
 
 @api_app.post("/predict")
 async def predict_from_salesforce(request: Request):
-    print("Received API request...")
     try:
         data = await request.json()
         phase = data.get("phase", "Framing")
@@ -263,12 +249,9 @@ async def predict_from_salesforce(request: Request):
             "status": "success"
         })
     except Exception as e:
-        print(f"API error: {e}")
         return JSONResponse(status_code=500, content={"status": "error", "message": str(e)})
 
-# Gradio UI
 try:
-    print("Setting up Gradio UI...")
     with gr.Blocks() as demo:
         gr.Markdown("## 🏗️ Delay Predictor with AI Insights")
         with gr.Row():
@@ -281,7 +264,6 @@ try:
         submit = gr.Button("Predict")
 
         def predict_and_format(phase, weather, absentee, delay_log):
-            print("Gradio predict button clicked.")
             prediction, risk, insight, pdf_base64, pdf_path, heatmap_path = predict_delay(phase, weather, absentee, delay_log)
             if prediction is None:
                 return f"Error: {insight}"
@@ -298,24 +280,15 @@ try:
             inputs=[phase_input, weather_input, absentee_input, delay_input],
             outputs=output
         )
-    print("Gradio UI setup complete.")
 except Exception as e:
     print(f"Error setting up Gradio UI: {e}")
     raise
 
-# Mount Gradio app inside FastAPI
 try:
-    print("Mounting Gradio app...")
     app = gr.mount_gradio_app(api_app, demo, path="/")
-    print("Gradio app mounted successfully.")
 except Exception as e:
     print(f"Error mounting Gradio app: {e}")
     raise
 
 if __name__ == "__main__":
-    print("Starting server on http://0.0.0.0:7860...")
-    try:
-        uvicorn.run(app, host="0.0.0.0", port=7860)
-    except Exception as e:
-        print(f"Server failed to start: {e}")
-        raise
+    uvicorn.run(app, host="0.0.0.0", port=7860)