Upload 6 files

README.md

@@ -1,13 +1,62 @@
----
-title: Devpro
-emoji: 📚
-colorFrom: indigo
-colorTo: green
-sdk: gradio
-sdk_version: 6.2.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: GitHub Developer Productivity Predictor
+emoji: 🚀
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# 🚀 GitHub Developer Productivity Predictor
+
+This is an AI-powered tool that predicts developer productivity scores based on GitHub activity metrics.
+
+## 🎯 What it does
+
+The model analyzes 6 key developer metrics to predict a productivity score (0-100):
+
+- **Daily Coding Hours**: Average hours spent coding per day
+- **Commits Per Day**: Average number of commits made per day  
+- **Pull Requests Per Week**: Average number of pull requests created per week
+- **Issues Closed Per Week**: Average number of issues resolved per week
+- **Active Repositories**: Number of repositories actively contributed to
+- **Code Reviews Per Week**: Average number of code reviews performed per week
+
+## 🤖 Model Details
+
+- **Algorithm**: Random Forest Regressor
+- **Features**: 6 numeric GitHub activity metrics
+- **Performance**: Trained on synthetic GitHub developer data
+- **Preprocessing**: StandardScaler for feature normalization
+
+## 🎮 How to Use
+
+1. Enter your GitHub activity metrics in the input fields
+2. Click "Predict Productivity Score" to get your score
+3. Try the example buttons to see different developer profiles
+
+## 📊 Score Interpretation
+
+- **80-100**: 🌟 Excellent - High productivity developer!
+- **70-79**: ✅ Very Good - Above average productivity!
+- **60-69**: 👍 Good - Solid productivity level!
+- **50-59**: ⚖️ Average - Room for improvement!
+- **Below 50**: 📈 Below Average - Consider focusing on key metrics!
+
+## ⚠️ Disclaimer
+
+This is a demonstration model for educational purposes. Real developer productivity depends on many factors beyond GitHub metrics, including code quality, collaboration, problem-solving skills, and project complexity.
+
+## 🛠️ Technical Stack
+
+- **Frontend**: Gradio
+- **Backend**: Python, scikit-learn
+- **Model**: Random Forest Regressor
+- **Deployment**: Hugging Face Spaces
+
+---
+
+*Built with ❤️ for the developer community*

app.py

@@ -0,0 +1,185 @@
+import gradio as gr
+import joblib
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+
+# Load the trained model and scaler
+model = joblib.load('developer_productivity_model.joblib')
+scaler = joblib.load('scaler.joblib')
+
+def predict_productivity(daily_coding_hours, commits_per_day, pull_requests_per_week, 
+                        issues_closed_per_week, active_repos, code_reviews_per_week):
+    """
+    Predict developer productivity score based on numeric features.
+    
+    Parameters:
+    - daily_coding_hours: float (hours spent coding per day)
+    - commits_per_day: int (number of commits per day)
+    - pull_requests_per_week: int (number of pull requests per week)
+    - issues_closed_per_week: int (number of issues closed per week)
+    - active_repos: int (number of active repositories)
+    - code_reviews_per_week: int (number of code reviews per week)
+    
+    Returns:
+    - predicted_score: float (predicted productivity score)
+    """
+    
+    try:
+        # Create feature array
+        features = np.array([[
+            daily_coding_hours,
+            commits_per_day,
+            pull_requests_per_week,
+            issues_closed_per_week,
+            active_repos,
+            code_reviews_per_week
+        ]])
+        
+        # Scale features
+        features_scaled = scaler.transform(features)
+        
+        # Make prediction
+        prediction = model.predict(features_scaled)[0]
+        
+        score = round(prediction, 2)
+        
+        # Add interpretation
+        if score >= 80:
+            interpretation = "🌟 Excellent - High productivity developer!"
+        elif score >= 70:
+            interpretation = "✅ Very Good - Above average productivity!"
+        elif score >= 60:
+            interpretation = "👍 Good - Solid productivity level!"
+        elif score >= 50:
+            interpretation = "⚖️ Average - Room for improvement!"
+        else:
+            interpretation = "📈 Below Average - Consider focusing on key metrics!"
+        
+        return f"{score} - {interpretation}"
+        
+    except Exception as e:
+        return f"Error in prediction: {str(e)}"
+
+# Create Gradio interface
+with gr.Blocks(title="GitHub Developer Productivity Predictor", theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        # 🚀 GitHub Developer Productivity Predictor
+        
+        This AI model predicts developer productivity scores based on GitHub activity metrics.
+        Enter your development metrics below to get your predicted productivity score!
+        
+        **Features used for prediction:**
+        - Daily coding hours
+        - Commits per day  
+        - Pull requests per week
+        - Issues closed per week
+        - Active repositories
+        - Code reviews per week
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column():
+            daily_hours = gr.Number(
+                label="Daily Coding Hours",
+                value=4.0,
+                minimum=0,
+                maximum=24,
+                info="Average hours spent coding per day"
+            )
+            commits_day = gr.Number(
+                label="Commits Per Day",
+                value=5,
+                minimum=0,
+                maximum=50,
+                info="Average number of commits made per day"
+            )
+            prs_week = gr.Number(
+                label="Pull Requests Per Week",
+                value=4,
+                minimum=0,
+                maximum=20,
+                info="Average number of pull requests created per week"
+            )
+            
+        with gr.Column():
+            issues_week = gr.Number(
+                label="Issues Closed Per Week",
+                value=3,
+                minimum=0,
+                maximum=20,
+                info="Average number of issues resolved per week"
+            )
+            repos = gr.Number(
+                label="Active Repositories",
+                value=5,
+                minimum=0,
+                maximum=50,
+                info="Number of repositories actively contributed to"
+            )
+            reviews_week = gr.Number(
+                label="Code Reviews Per Week",
+                value=3,
+                minimum=0,
+                maximum=20,
+                info="Average number of code reviews performed per week"
+            )
+    
+    with gr.Row():
+        predict_btn = gr.Button("🔮 Predict Productivity Score", variant="primary", size="lg")
+        clear_btn = gr.Button("🔄 Clear", variant="secondary")
+    
+    output = gr.Textbox(
+        label="Productivity Prediction",
+        placeholder="Click 'Predict Productivity Score' to see your result...",
+        interactive=False
+    )
+    
+    # Example buttons
+    gr.Markdown("### 📊 Try these examples:")
+    with gr.Row():
+        high_prod_btn = gr.Button("🌟 High Productivity Developer")
+        avg_prod_btn = gr.Button("⚖️ Average Developer") 
+        beginner_btn = gr.Button("🌱 Beginner Developer")
+    
+    # Event handlers
+    predict_btn.click(
+        fn=predict_productivity,
+        inputs=[daily_hours, commits_day, prs_week, issues_week, repos, reviews_week],
+        outputs=output
+    )
+    
+    clear_btn.click(
+        fn=lambda: [4.0, 5, 4, 3, 5, 3, ""],
+        outputs=[daily_hours, commits_day, prs_week, issues_week, repos, reviews_week, output]
+    )
+    
+    high_prod_btn.click(
+        fn=lambda: [6.0, 10, 8, 6, 8, 5],
+        outputs=[daily_hours, commits_day, prs_week, issues_week, repos, reviews_week]
+    )
+    
+    avg_prod_btn.click(
+        fn=lambda: [4.0, 5, 4, 3, 5, 3],
+        outputs=[daily_hours, commits_day, prs_week, issues_week, repos, reviews_week]
+    )
+    
+    beginner_btn.click(
+        fn=lambda: [3.0, 2, 2, 1, 2, 1],
+        outputs=[daily_hours, commits_day, prs_week, issues_week, repos, reviews_week]
+    )
+
+    gr.Markdown(
+        """
+        ### 📝 About the Model
+        This Random Forest model was trained on GitHub developer activity data and uses 6 key metrics to predict productivity scores (0-100).
+        The model achieves good performance in predicting developer productivity based on quantifiable GitHub activities.
+        
+        **Note**: This is a demonstration model. Actual productivity depends on many factors beyond GitHub metrics.
+        """
+    )
+
+if __name__ == "__main__":
+    demo.launch()

developer_productivity_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c3691e8f0fb4bdea31a0d458d6702ef3bd6fe0bae6e377a507dffaf3beeccd
+size 388001

feature_names.json

@@ -0,0 +1 @@
+["daily_coding_hours", "commits_per_day", "pull_requests_per_week", "issues_closed_per_week", "active_repos", "code_reviews_per_week"]

requirements.txt

@@ -0,0 +1,5 @@
+gradio==4.44.0
+joblib==1.3.2
+numpy==1.24.3
+pandas==2.0.3
+scikit-learn==1.3.0

scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c3cafb0ca38a5181eff58e595505296f56e491749a38c2daaa2a7313e34746
+size 1143