Upload 2 files

app.py

@@ -0,0 +1,105 @@
+import gradio as gr
+import joblib
+import pandas as pd
+from fastapi import FastAPI, Request
+from fastapi.responses import JSONResponse
+import uvicorn
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+
+# Hardcoded mappings
+phase_map = { "Framing": 0, "Foundation": 1, "Finishing": 2}
+weather_map = {"Cloudy": 0, "Rainy": 1, "Sunny": 2}
+
+# Load and preprocess training data
+df = pd.read_csv("delay_data.csv")
+
+# Encode categorical features
+df["Phase"] = df["Phase"].map(phase_map)
+df["Weather"] = df["Weather"].map(weather_map)
+
+# Handle missing or invalid mappings
+df.dropna(subset=["Phase", "Weather", "Absentee", "DelayLog", "Delay%"], inplace=True)
+
+# Split features and target
+X = df[["Phase", "Weather", "Absentee", "DelayLog"]]
+y = df["Delay%"]
+
+# Train model
+model = LinearRegression()
+model.fit(X, y)
+
+# Main prediction function
+def predict_delay(phase, weather, absentee_pct, delay_log):
+    phase_encoded = phase_map.get(phase, 0)
+    weather_encoded = weather_map.get(weather, 0)
+    input_data = [[phase_encoded, weather_encoded, absentee_pct, delay_log]]
+    
+    # Model makes prediction
+    prediction = model.predict(input_data)[0]
+    prediction = round(prediction, 2)
+
+    # Risk tagging based on predicted delay percentage
+    if prediction >= 75:
+        risk = "High Risk"
+    elif prediction >= 50:
+        risk = "Moderate Risk"
+    else:
+        risk = "Low Risk"
+
+    # AI reasoning for insights
+    insight = f"Phase: {phase}, Weather: {weather}, Absenteeism: {absentee_pct}%, Previous Delay: {delay_log} → Risk: {risk}"
+
+    return prediction, risk, insight
+
+# FastAPI for Salesforce
+api_app = FastAPI()
+
+@api_app.post("/predict")
+async def predict_from_salesforce(request: Request):
+    try:
+        data = await request.json()
+        phase = data.get("phase", "Framing")
+        weather = data.get("weather", "Sunny")
+        absentee_pct = float(data.get("absentee_pct", 0))
+        delay_log = float(data.get("delay_log", 0))
+
+        prediction, risk, insight = predict_delay(phase, weather, absentee_pct, delay_log)
+
+        return JSONResponse(content={
+            "delay_probability": prediction,
+            "risk_alert": risk,
+            "ai_insight": insight,
+            "status": "success"
+        })
+    except Exception as e:
+        return JSONResponse(status_code=500, content={"status": "error", "message": str(e)})
+
+# Gradio UI for manual testing
+with gr.Blocks() as demo:
+    gr.Markdown("## 🏗️ Delay Predictor")
+    with gr.Row():
+        phase_input = gr.Textbox(label="Phase (Framing/Foundation/Finishing)")
+        weather_input = gr.Textbox(label="Weather (Sunny/Rainy/Cloudy)")
+    with gr.Row():
+        absentee_input = gr.Number(label="Absentee %")
+        delay_input = gr.Number(label="Previous Delay Log")
+    output = gr.Textbox(label="Prediction Summary")
+
+    def predict_and_format(phase, weather, absentee, delay_log):
+        prediction, risk, insight = predict_delay(phase, weather, absentee, delay_log)
+        return f"Predicted Delay: {prediction}%\nRisk Level: {risk}\nInsight: {insight}"
+
+    submit = gr.Button("Predict")
+    submit.click(
+        predict_and_format,
+        inputs=[phase_input, weather_input, absentee_input, delay_input],
+        outputs=output
+    )
+
+# Mount Gradio inside FastAPI
+app = gr.mount_gradio_app(api_app, demo, path="/")
+
+# Run locally (Hugging Face will ignore this)
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

new_delay_data.csv

@@ -0,0 +1,52 @@
+Phase,Weather,Absentee,DelayLog,Delay%,PredictedDelay
+Framing,Sunny,10.00,2.00,48.50,43.65
+Foundation,Sunny,10.00,2.00,38.20,34.38
+Finishing,Sunny,10.00,2.00,28.10,25.29
+Framing,Cloudy,8.50,3.50,46.30,41.67
+Foundation,Cloudy,7.20,2.80,36.50,32.85
+Finishing,Cloudy,6.90,2.50,26.80,24.12
+Framing,Rainy,12.50,4.20,55.60,50.04
+Foundation,Rainy,11.80,3.90,45.30,40.77
+Finishing,Rainy,10.20,3.60,33.40,30.06
+Framing,Sunny,9.80,1.90,47.20,42.48
+Foundation,Sunny,9.50,1.80,37.10,33.39
+Finishing,Sunny,9.30,1.70,27.50,24.75
+Framing,Cloudy,11.00,4.00,50.80,45.72
+Foundation,Cloudy,10.50,3.50,40.60,36.54
+Finishing,Cloudy,9.90,3.20,30.20,27.18
+Framing,Rainy,13.20,5.00,58.90,53.01
+Foundation,Rainy,12.70,4.50,47.80,43.02
+Finishing,Rainy,11.50,4.00,34.70,31.23
+Framing,Sunny,10.20,2.10,49.10,44.19
+Foundation,Sunny,10.10,2.00,38.90,35.01
+Finishing,Sunny,9.80,1.90,28.30,25.47
+Framing,Cloudy,7.50,2.70,45.20,40.68
+Foundation,Cloudy,6.80,2.40,35.40,31.86
+Finishing,Cloudy,6.50,2.20,25.90,23.31
+Framing,Sunny,10.50,2.30,50.30,45.27
+Foundation,Sunny,10.30,2.20,39.50,35.55
+Finishing,Sunny,10.00,2.10,29.00,26.10
+Framing,Rainy,14.00,5.50,60.20,54.18
+Foundation,Rainy,13.50,5.00,48.90,44.01
+Finishing,Rainy,12.80,4.50,35.60,32.04
+Framing,Cloudy,9.00,3.00,47.90,43.11
+Foundation,Cloudy,8.50,2.80,37.70,33.93
+Finishing,Cloudy,8.20,2.60,27.80,25.02
+Framing,Sunny,10.70,2.50,51.40,46.26
+Foundation,Sunny,10.50,2.40,40.20,36.18
+Finishing,Sunny,10.20,2.30,29.50,26.55
+Framing,Cloudy,11.50,4.20,52.60,47.34
+Foundation,Cloudy,11.00,3.80,41.80,37.62
+Finishing,Cloudy,10.50,3.50,30.90,27.81
+Framing,Rainy,12.00,4.80,56.70,51.03
+Foundation,Rainy,11.50,4.30,46.20,41.58
+Finishing,Rainy,10.80,4.00,34.10,30.69
+Framing,Sunny,9.90,2.00,48.80,43.92
+Foundation,Sunny,9.70,1.90,38.40,34.56
+Finishing,Sunny,9.50,1.80,28.20,25.38
+Framing,Cloudy,8.00,3.20,46.50,41.85
+Foundation,Cloudy,7.50,2.90,36.80,33.12
+Finishing,Cloudy,7.20,2.70,27.00,24.30
+Framing,Sunny,10.40,2.40,50.00,45.00
+Foundation,Sunny,10.20,2.30,39.70,35.73
+Finishing,Sunny,10.00,2.20,29.20,26.28