msg

folder1/.env

@@ -0,0 +1,2 @@
+SUPABASE_URL=https://qxvpaoeakhddzabctekw.supabase.co
+SUPABASE_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6InF4dnBhb2Vha2hkZHphYmN0ZWt3Iiwicm9sZSI6ImFub24iLCJpYXQiOjE3NDEwNjU2MzEsImV4cCI6MjA1NjY0MTYzMX0.I3GsBjFRfuBKw-KxmSJ7R5iKn2cgGegqIls2Bf32UpI

folder1/config.py

@@ -0,0 +1,8 @@
+import os
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+SUPABASE_URL = os.getenv("SUPABASE_URL")
+SUPABASE_KEY = os.getenv("SUPABASE_KEY")

folder1/database.py

@@ -0,0 +1,13 @@
+from supabase import create_client, Client
+from config import SUPABASE_URL, SUPABASE_KEY
+
+# Initialize Supabase client
+supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
+
+def fetch_data():
+    """Fetch HR analytics data from Supabase"""
+    response = supabase.table("HR analysis").select("*").execute()
+    if response.data:
+        return response.data
+    else:
+        raise ValueError("Failed to fetch data from Supabase")

folder1/logger.py

@@ -0,0 +1,13 @@
+import logging
+
+def setup_logger():
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
+        handlers=[
+            logging.FileHandler("app.log"),
+            logging.StreamHandler()
+        ]
+    )
+
+logger = logging.getLogger(__name__)

folder1/logs/app.log

@@ -0,0 +1,58 @@
+2025-03-04 20:13:37,909 - INFO - Will watch for changes in these directories: ['D:\\capstone\\dataset\\folder1']
+2025-03-04 20:13:37,915 - INFO - Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
+2025-03-04 20:13:37,921 - INFO - Started reloader process [984] using WatchFiles
+2025-03-04 20:13:40,128 - INFO - 1 change detected
+2025-03-04 20:13:43,883 - INFO - Started server process [21136]
+2025-03-04 20:13:43,893 - INFO - Waiting for application startup.
+2025-03-04 20:13:43,897 - INFO - Application startup complete.
+2025-03-04 20:16:27,062 - INFO - 1 change detected
+2025-03-04 20:16:27,067 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:16:27,183 - INFO - Shutting down
+2025-03-04 20:16:27,291 - INFO - Waiting for application shutdown.
+2025-03-04 20:16:27,295 - INFO - Application shutdown complete.
+2025-03-04 20:16:27,297 - INFO - Finished server process [21136]
+2025-03-04 20:16:28,113 - INFO - 2 changes detected
+2025-03-04 20:16:28,116 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:16:30,880 - INFO - 5 changes detected
+2025-03-04 20:16:41,194 - INFO - 1 change detected
+2025-03-04 20:16:41,237 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:16:43,626 - INFO - 5 changes detected
+2025-03-04 20:16:47,175 - INFO - Started server process [3356]
+2025-03-04 20:16:47,182 - INFO - Waiting for application startup.
+2025-03-04 20:16:47,185 - INFO - Application startup complete.
+2025-03-04 20:17:08,401 - INFO - 1 change detected
+2025-03-04 20:17:08,403 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:08,507 - INFO - Shutting down
+2025-03-04 20:17:08,616 - INFO - Waiting for application shutdown.
+2025-03-04 20:17:08,619 - INFO - Application shutdown complete.
+2025-03-04 20:17:08,622 - INFO - Finished server process [3356]
+2025-03-04 20:17:09,347 - INFO - 1 change detected
+2025-03-04 20:17:11,124 - INFO - 5 changes detected
+2025-03-04 20:17:15,863 - INFO - 1 change detected
+2025-03-04 20:17:15,865 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:18,191 - INFO - 5 changes detected
+2025-03-04 20:17:23,542 - INFO - 1 change detected
+2025-03-04 20:17:23,543 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:25,729 - INFO - 5 changes detected
+2025-03-04 20:17:26,701 - INFO - 1 change detected
+2025-03-04 20:17:26,702 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:30,341 - INFO - 1 change detected
+2025-03-04 20:17:30,342 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:31,745 - INFO - 1 change detected
+2025-03-04 20:17:31,746 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:37,489 - INFO - 6 changes detected
+2025-03-04 20:17:37,490 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:39,793 - INFO - 6 changes detected
+2025-03-04 20:17:39,795 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:44,073 - INFO - 1 change detected
+2025-03-04 20:17:44,074 - WARNING - WatchFiles detected changes in 'routes\analytics.py'. Reloading...
+2025-03-04 20:17:46,261 - INFO - 5 changes detected
+2025-03-04 20:17:49,746 - INFO - Started server process [8820]
+2025-03-04 20:17:49,754 - INFO - Waiting for application startup.
+2025-03-04 20:17:49,756 - INFO - Application startup complete.
+2025-03-04 20:18:25,834 - INFO - Will watch for changes in these directories: ['D:\\capstone\\dataset\\folder1']
+2025-03-04 20:18:25,837 - INFO - Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
+2025-03-04 20:18:25,840 - INFO - Started reloader process [10832] using WatchFiles
+2025-03-04 20:18:31,454 - INFO - Started server process [9576]
+2025-03-04 20:18:31,461 - INFO - Waiting for application startup.
+2025-03-04 20:18:31,464 - INFO - Application startup complete.

folder1/main.py

@@ -0,0 +1,45 @@
+from fastapi import FastAPI
+from routes import analytics
+from logger import setup_logger
+from database import supabase  # Ensure this is properly initialized
+from fastapi import FastAPI, HTTPException
+import pandas as pd
+
+# Initialize FastAPI app
+app = FastAPI(title="HR Analytics API", description="HR Insights and Predictive Analytics")
+
+# Setup logger
+setup_logger()
+
+# Include routes
+app.include_router(analytics.router)
+
+@app.get("/home")
+def home():
+    """
+    Home endpoint providing API overview.
+    """
+    return {
+        "message": "Welcome to the HR Analytics and Predictive Insights API",
+        "description": "This API provides HR analytics, including employee satisfaction, performance metrics, and training insights.",
+        "employee_statistics": {
+            "total_employees": 2845,
+            "male_employees": 1257,
+            "female_employees": 1588
+        },
+        "endpoints": {
+            "/satisfaction-analysis": "Analyze employee satisfaction by department.",
+            "/department-performance": "Get average performance scores by department.",
+            "/training-analytics": "Analyze training program completion rates.",
+            "/engagement-performance-correlation": "Find correlation between engagement and performance scores.",
+            "/cost-benefit-analysis": "Perform cost-benefit analysis for training programs.",
+            "/training-effectiveness": "Evaluate the effectiveness of training programs.",
+            "/diversity-dashboard": "View diversity metrics by department.",
+            "/worklife-balance-impact": "Analyze the impact of work-life balance on performance.",
+            "/career-development": "Track employee career development over time."
+        },
+        "documentation": {
+            "Swagger UI": "/docs",
+            "Redoc": "/redoc"
+        }
+    }

folder1/models/schemas.py

@@ -0,0 +1,11 @@
+from pydantic import BaseModel
+from typing import Optional
+
+class EmployeeSatisfaction(BaseModel):
+    department: str
+    satisfaction_score: float
+
+class DepartmentPerformance(BaseModel):
+    department: str
+    performance_score: float
+    employee_rating: Optional[float] = None

folder1/requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+pandas
+python-dotenv
+supabase

folder1/routes/analytics.py

@@ -0,0 +1,102 @@
+from fastapi import APIRouter, HTTPException
+import pandas as pd
+from database import fetch_data
+from utils.data_processing import preprocess_data
+from logger import logger
+
+# Initialize router
+router = APIRouter()
+
+def get_filtered_data(columns):
+    """Fetches and filters data based on required columns."""
+    try:
+        raw_data = fetch_data()
+        df = preprocess_data(pd.DataFrame(raw_data))
+        missing_cols = [col for col in columns if col not in df.columns]
+        if missing_cols:
+            raise HTTPException(status_code=400, detail=f"Missing columns: {missing_cols}")
+        return df[columns].dropna()
+    except Exception as e:
+        logger.error(f"Error fetching data: {e}")
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/satisfaction-analysis")
+def satisfaction_analysis():
+    try:
+        data = get_filtered_data(['Satisfaction Score', 'DepartmentType'])
+        result = data.groupby("DepartmentType")["Satisfaction Score"].mean().reset_index()
+        return result.to_dict(orient="records")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/department-performance")
+def department_performance():
+    try:
+        data = get_filtered_data(["Performance Score", "Current Employee Rating", "DepartmentType"])
+        result = data.groupby("DepartmentType")[["Performance Score", "Current Employee Rating"]].mean().reset_index()
+        return result.to_dict(orient="records")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/training-analytics")
+def training_analytics():
+    try:
+        data = get_filtered_data(['Training Outcome', 'Training Cost'])
+        completion_rates = data.groupby("Training Cost")['Training Outcome'].value_counts(normalize=True).unstack(fill_value=0)
+        return completion_rates.to_dict()
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/engagement-performance-correlation")
+def engagement_performance_correlation():
+    try:
+        data = get_filtered_data(['Engagement Score', 'Performance Score'])
+        correlation = data[['Engagement Score', 'Performance Score']].corr().iloc[0, 1]
+        return {"correlation_coefficient": correlation}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/cost-benefit-analysis")
+def cost_benefit_analysis():
+    try:
+        data = get_filtered_data(['Training Cost', 'Performance Score', 'DepartmentType'])
+        result = data.groupby("DepartmentType").apply(lambda g: g["Performance Score"].mean() / g["Training Cost"].sum()).reset_index(name="ROI")
+        return result.to_dict(orient="records")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/training-effectiveness")
+def training_effectiveness():
+    try:
+        data = get_filtered_data(['Training Outcome', 'Performance Score', 'Training Program Name'])
+        result = data.groupby("Training Program Name")["Performance Score"].mean().reset_index()
+        return result.to_dict(orient="records")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/diversity-dashboard")
+def diversity_dashboard():
+    try:
+        data = get_filtered_data(['GenderCode', 'RaceDesc', 'DepartmentType'])
+        diversity_metrics = data.groupby("DepartmentType")['GenderCode'].value_counts(normalize=True).unstack(fill_value=0)
+        return diversity_metrics.to_dict()
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/worklife-balance-impact")
+def worklife_balance_impact():
+    try:
+        data = get_filtered_data(['Work-Life Balance Score', 'Performance Score'])
+        correlation = data[['Work-Life Balance Score', 'Performance Score']].corr().iloc[0, 1]
+        return {"correlation_coefficient": correlation}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
+
+@router.get("/career-development")
+def career_development():
+    try:
+        data = get_filtered_data(['Employee ID', 'StartDate'])
+        career_progress = data.groupby("Employee ID")["StartDate"].count().reset_index(name="Career Movements")
+        return career_progress.to_dict(orient="records")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")

folder1/utils/data_processing.py

@@ -0,0 +1,30 @@
+import pandas as pd
+
+def preprocess_data(data: pd.DataFrame):
+    """Clean and preprocess HR analytics data."""
+    
+    # Convert date columns
+    date_columns = ['Survey Date', 'StartDate', 'DOB']
+    for col in date_columns:
+        if col in data.columns:
+            data[col] = pd.to_datetime(data[col], errors='coerce')
+
+    # Calculate Age from DOB
+    if 'DOB' in data.columns:
+        data['Age'] = (pd.to_datetime("today") - data['DOB']).dt.days // 365
+
+    # Convert Performance Score to Numeric
+    def clean_performance_score(value):
+        score_map = {"Exceeds": 5, "Fully Meets": 4, "Needs Improvement": 3, "PIP": 2}
+        if isinstance(value, (int, float)):
+            return value
+        if isinstance(value, str):
+            value = value.strip()
+            return score_map.get(value, None)
+        return None
+
+    if 'Performance Score' in data.columns:
+        data['Performance Score'] = data['Performance Score'].apply(clean_performance_score)
+        data['Performance Score'] = pd.to_numeric(data['Performance Score'], errors='coerce')
+
+    return data