Update app.py

app.py

@@ -1,192 +1,160 @@
 import gradio as gr
-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
-import os
-import subprocess
-import uuid
-from datetime import datetime
-from fastapi.staticfiles import StaticFiles
-
-# Hardcoded mappings
-weather_map = {"Cloudy": 0, "Rainy": 1, "Sunny": 2}
-
-# Load and preprocess training data
-df = pd.read_csv("new_delay_data.csv")
-
-# Encode categorical features
-df = pd.get_dummies(df, columns=["Phase"], drop_first=True)  # Finishing as baseline
-df["Weather"] = df["Weather"].map(weather_map)
-
-# Handle missing or invalid mappings
-df.dropna(subset=["Phase_Framing", "Phase_Foundation", "Weather", "Absentee", "DelayLog", "Delay%"], inplace=True)
-
-# Split features and target
-X = df[["Phase_Framing", "Phase_Foundation", "Weather", "Absentee", "DelayLog"]]
-y = df["Delay%"]
-
-# Train model
-model = LinearRegression()
-model.fit(X, y)
-
-# Function to clean up old files
-def clean_tmp():
-    directory = "./static_files"
-    for file in os.listdir(directory):
-        if file.endswith((".pdf", ".tex", ".aux", ".log")):
-            try:
-                os.remove(os.path.join(directory, file))
-            except OSError:
-                pass
-
-# Function to generate LaTeX content for PDF
-def generate_latex_content(phase, weather, absentee_pct, delay_log, prediction, risk, insight):
-    return f"""
-\\documentclass[a4paper,12pt]{{article}}
-\\usepackage{{geometry}}
-\\usepackage{{utf8x}}
-\\usepackage{{parskip}}
-\\usepackage{{titlesec}}
-\\usepackage{{xcolor}}
-\\geometry{{margin=1in}}
-\\titleformat{{\\section}}{{\\Large\\bfseries\\color{{blue}}}}{{\\thesection}}{{1em}}{{}}
-\\begin{{document}}
-\\section*{{Delay Prediction Report}}
-\\textbf{{Generated on:}} {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\\\\
-\\textbf{{Project Details}}\\\\
-\\begin{{itemize}}
-    \\item \\textbf{{Phase:}} {phase}
-    \\item \\textbf{{Weather:}} {weather}
-    \\item \\textbf{{Absentee \\%:}} {absentee_pct:.2f}\\%
-    \\item \\textbf{{Previous Delay Log:}} {delay_log:.2f} days
-\\end{{itemize}}
-\\vspace{{0.5cm}}
-\\textbf{{Prediction Results}}\\\\
-\\begin{{itemize}}
-    \\item \\textbf{{Predicted Delay:}} {prediction:.2f}\\%
-    \\item \\textbf{{Risk Level:}} {risk}
-    \\item \\textbf{{AI Insight:}} {insight}
-\\end{{itemize}}
-\\end{{document}}
-"""
-
-# Function to generate PDF and return its URL
-def generate_pdf(phase, weather, absentee_pct, delay_log, prediction, risk, insight):
-    os.makedirs("./static_files", exist_ok=True)
-    clean_tmp()  # Clean up old files
-    pdf_filename = f"delay_report_{uuid.uuid4().hex}.pdf"
-    tex_filename = f"./static_files/{pdf_filename.replace('.pdf', '.tex')}"
-    pdf_path = f"./static_files/{pdf_filename}"
-    
-    latex_content = generate_latex_content(phase, weather, absentee_pct, delay_log, prediction, risk, insight)
-    with open(tex_filename, "w") as f:
-        f.write(latex_content)
-    
-    try:
-        subprocess.run(
-            ["pdflatex", f"-output-directory=./static_files", tex_filename],
-            check=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            text=True
-        )
-    except subprocess.CalledProcessError as e:
-        raise Exception(f"PDF generation failed: {e.stderr}")
-    
-    for ext in [".aux", ".log", ".tex"]:
-        try:
-            os.remove(tex_filename.replace(".tex", ext))
-        except OSError:
-            pass
-    
-    pdf_url = f"https://ajaykumarpilla-delay-predictor.hf.space/static/{pdf_filename}"
-    return pdf_url, pdf_path
-
-# Main prediction function
-def predict_delay(phase, weather, absentee_pct, delay_log):
-    framing = 1 if phase == "Framing" else 0
-    foundation = 1 if phase == "Foundation" else 0
-    weather_encoded = weather_map.get(weather, 0)
-    input_data = [[framing, foundation, weather_encoded, absentee_pct, delay_log]]
-    
-    prediction = model.predict(input_data)[0]
-    prediction = round(prediction, 2)
-
-    if prediction >= 75:
-        risk = "High Risk"
-    elif prediction >= 50:
-        risk = "Moderate Risk"
-    else:
-        risk = "Low Risk"
-
-    insight = f"Phase: {phase}, Weather: {weather}, Absenteeism: {absentee_pct}%, Previous Delay: {delay_log} → Risk: {risk}"
-
-    pdf_url, pdf_path = generate_pdf(phase, weather, absentee_pct, delay_log, prediction, risk, insight)
-    return prediction, risk, insight, pdf_url
-
-# FastAPI for Salesforce
-api_app = FastAPI()
-
-# Create static_files directory at startup
-os.makedirs("./static_files", exist_ok=True)
-
-# Mount static files directory
-api_app.mount("/static", StaticFiles(directory="./static_files"), name="static")
-
-@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, pdf_url = predict_delay(phase, weather, absentee_pct, delay_log)
-
-        return JSONResponse(content={
-            "delay_probability": prediction,
-            "risk_alert": risk,
-            "ai_insight": insight,
-            "pdf_url": pdf_url,
-            "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")
-    pdf_output = gr.File(label="Download PDF Report")
-
-    def predict_and_format(phase, weather, absentee, delay_log):
-        try:
-            prediction, risk, insight, pdf_url = predict_delay(phase, weather, absentee, delay_log)
-            return (
-                f"Predicted Delay: {prediction}%\nRisk Level: {risk}\nInsight: {insight}\nPDF URL: {pdf_url}",
-                pdf_url
-            )
-        except Exception as e:
-            return f"Error: {str(e)}", None
-
-    submit = gr.Button("Predict")
-    submit.click(
-        predict_and_format,
-        inputs=[phase_input, weather_input, absentee_input, delay_input],
-        outputs=[output, pdf_output]
-    )
-
-app = gr.mount_gradio_app(api_app, demo, path="/")
-
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+  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
+  import os
+  import uuid
+  from datetime import datetime
+  from fastapi.staticfiles import StaticFiles
+  from reportlab.lib.pagesizes import A4
+  from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+  from reportlab.lib.styles import getSampleStyleSheet
+
+  # Hardcoded mappings
+  weather_map = {"Cloudy": 0, "Rainy": 1, "Sunny": 2}
+
+  # Load and preprocess training data
+  df = pd.read_csv("new_delay_data.csv")
+
+  # Encode categorical features
+  df = pd.get_dummies(df, columns=["Phase"], drop_first=True)  # Finishing as baseline
+  df["Weather"] = df["Weather"].map(weather_map)
+
+  # Handle missing or invalid mappings
+  df.dropna(subset=["Phase_Framing", "Phase_Foundation", "Weather", "Absentee", "DelayLog", "Delay%"], inplace=True)
+
+  # Split features and target
+  X = df[["Phase_Framing", "Phase_Foundation", "Weather", "Absentee", "DelayLog"]]
+  y = df["Delay%"]
+
+  # Train model
+  model = LinearRegression()
+  model.fit(X, y)
+
+  # Function to clean up old files
+  def clean_tmp():
+      directory = "./static_files"
+      for file in os.listdir(directory):
+          if file.endswith(".pdf"):
+              try:
+                  os.remove(os.path.join(directory, file))
+              except OSError:
+                  pass
+
+  # Function to generate PDF using reportlab
+  def generate_pdf(phase, weather, absentee_pct, delay_log, prediction, risk, insight):
+      os.makedirs("./static_files", exist_ok=True)
+      clean_tmp()
+      pdf_filename = f"delay_report_{uuid.uuid4().hex}.pdf"
+      pdf_path = f"./static_files/{pdf_filename}"
+      
+      doc = SimpleDocTemplate(pdf_path, pagesize=A4)
+      styles = getSampleStyleSheet()
+      story = []
+
+      story.append(Paragraph("Delay Prediction Report", styles['Title']))
+      story.append(Spacer(1, 12))
+      story.append(Paragraph(f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", styles['Normal']))
+      story.append(Spacer(1, 12))
+      
+      story.append(Paragraph("Project Details", styles['Heading2']))
+      story.append(Paragraph(f"Phase: {phase}", styles['Normal']))
+      story.append(Paragraph(f"Weather: {weather}", styles['Normal']))
+      story.append(Paragraph(f"Absentee %: {absentee_pct:.2f}%", styles['Normal']))
+      story.append(Paragraph(f"Previous Delay Log: {delay_log:.2f} days", styles['Normal']))
+      story.append(Spacer(1, 12))
+      
+      story.append(Paragraph("Prediction Results", styles['Heading2']))
+      story.append(Paragraph(f"Predicted Delay: {prediction:.2f}%", styles['Normal']))
+      story.append(Paragraph(f"Risk Level: {risk}", styles['Normal']))
+      story.append(Paragraph(f"AI Insight: {insight}", styles['Normal']))
+      
+      doc.build(story)
+      
+      pdf_url = f"https://ajaykumarpilla-delay-predictor.hf.space/static/{pdf_filename}"
+      return pdf_url, pdf_path
+
+  # Main prediction function
+  def predict_delay(phase, weather, absentee_pct, delay_log):
+      framing = 1 if phase == "Framing" else 0
+      foundation = 1 if phase == "Foundation" else 0
+      weather_encoded = weather_map.get(weather, 0)
+      input_data = [[framing, foundation, weather_encoded, absentee_pct, delay_log]]
+      
+      prediction = model.predict(input_data)[0]
+      prediction = round(prediction, 2)
+
+      if prediction >= 75:
+          risk = "High Risk"
+      elif prediction >= 50:
+          risk = "Moderate Risk"
+      else:
+          risk = "Low Risk"
+
+      insight = f"Phase: {phase}, Weather: {weather}, Absenteeism: {absentee_pct}%, Previous Delay: {delay_log} → Risk: {risk}"
+
+      pdf_url, pdf_path = generate_pdf(phase, weather, absentee_pct, delay_log, prediction, risk, insight)
+      return prediction, risk, insight, pdf_url
+
+  # FastAPI for Salesforce
+  api_app = FastAPI()
+  os.makedirs("./static_files", exist_ok=True)
+  api_app.mount("/static", StaticFiles(directory="./static_files"), name="static")
+
+  @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, pdf_url = predict_delay(phase, weather, absentee_pct, delay_log)
+
+          return JSONResponse(content={
+              "delay_probability": prediction,
+              "risk_alert": risk,
+              "ai_insight": insight,
+              "pdf_url": pdf_url,
+              "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")
+      pdf_output = gr.File(label="Download PDF Report")
+
+      def predict_and_format(phase, weather, absentee, delay_log):
+          try:
+              prediction, risk, insight, pdf_url = predict_delay(phase, weather, absentee, delay_log)
+              return (
+                  f"Predicted Delay: {prediction}%\nRisk Level: {risk}\nInsight: {insight}\nPDF URL: {pdf_url}",
+                  pdf_url
+              )
+          except Exception as e:
+              return f"Error: {str(e)}", None
+
+      submit = gr.Button("Predict")
+      submit.click(
+          predict_and_format,
+          inputs=[phase_input, weather_input, absentee_input, delay_input],
+          outputs=[output, pdf_output]
+      )
+
+  app = gr.mount_gradio_app(api_app, demo, path="/")
+
+  if __name__ == "__main__":
+      uvicorn.run(app, host="0.0.0.0", port=7860)