Commit Updates

Dockerfile

@@ -17,4 +17,4 @@ EXPOSE 8000
 ENV MODEL_PATH="/app/cox_model.pkl"
 
 # Run app.py when the container launches
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8960"]

app.py

@@ -1,28 +1,9 @@
-# main.py
-
-from fastapi import FastAPI
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
-import joblib
 import pandas as pd
-from typing import Dict, Any
+import joblib
 
-class HRAttritionModel:
-    def __init__(self, model_path: str):
-        self.model = joblib.load(model_path)
-        self.features = ['Age', 'DistanceFromHome', 'Education', 'NumCompaniesWorked', 'PercentSalaryHike', 
-                         'TotalWorkingYears', 'TrainingTimesLastYear', 'WorkLifeBalance', 'YearsInCurrentRole', 
-                         'YearsSinceLastPromotion', 'YearsWithCurrManager', 'BusinessTravel_Travel_Rarely', 
-                         'BusinessTravel_Travel_Frequently', 'Department_Research & Development', 'Department_Sales', 
-                         'EducationField_Life Sciences', 'EducationField_Medical', 'EducationField_Marketing', 
-                         'EducationField_Other', 'EducationField_Technical Degree', 'Gender_Male', 'JobRole_Research Scientist', 
-                         'JobRole_Sales Executive', 'JobRole_Laboratory Technician', 'JobRole_Manufacturing Director', 
-                         'JobRole_Healthcare Representative', 'JobRole_Manager', 'JobRole_Sales Representative', 
-                         'JobRole_Research Director', 'MaritalStatus_Married', 'MaritalStatus_Single', 'OverTime_Yes']
-    
-    def predict_survival(self, input_data: Dict[str, Any]) -> Any:
-        df = pd.DataFrame([input_data], columns=self.features)
-        survival_function = self.model.predict_survival_function(df)
-        return survival_function.T
+app = FastAPI()
 
 class AttritionInput(BaseModel):
     Age: int
@@ -58,12 +39,39 @@ class AttritionInput(BaseModel):
     MaritalStatus_Single: int
     OverTime_Yes: int
 
-app = FastAPI()
+class HRAttritionModel:
+    def __init__(self, model_path):
+        try:
+            self.model = joblib.load(model_path)
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Model loading failed: {str(e)}")
+
+    def predict(self, input_data):
+        try:
+            all_columns = [
+                'Age', 'DistanceFromHome', 'Education', 'NumCompaniesWorked', 'PercentSalaryHike',
+                'TotalWorkingYears', 'TrainingTimesLastYear', 'WorkLifeBalance', 'YearsInCurrentRole',
+                'YearsSinceLastPromotion', 'YearsWithCurrManager', 'BusinessTravel_Travel_Rarely',
+                'BusinessTravel_Travel_Frequently', 'Department_Research & Development', 'Department_Sales',
+                'EducationField_Life Sciences', 'EducationField_Medical', 'EducationField_Marketing',
+                'EducationField_Other', 'EducationField_Technical Degree', 'Gender_Male',
+                'JobRole_Research Scientist', 'JobRole_Sales Executive', 'JobRole_Laboratory Technician',
+                'JobRole_Manufacturing Director', 'JobRole_Healthcare Representative', 'JobRole_Manager',
+                'JobRole_Sales Representative', 'JobRole_Research Director', 'MaritalStatus_Married',
+                'MaritalStatus_Single', 'JobRole_Human Resources','OverTime_Yes'
+            ]
+
+            input_df = pd.DataFrame([input_data], columns=all_columns).fillna(0)
+            survival_function = self.model.predict_survival_function(input_df)
+            survival_values = survival_function.iloc[:, 0].tolist()  # Get survival values for the first instance
+            return survival_values
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Prediction failed: {str(e)}")
 
 model = HRAttritionModel('cox_model.pkl')
 
 @app.post("/predict")
-def predict(attrition_input: AttritionInput):
-    input_data = attrition_input.dict()
-    prediction = model.predict_survival(input_data)
-    return {"prediction": prediction.tolist()}
+def predict(input_data: AttritionInput):
+    input_dict = input_data.dict()
+    prediction = model.predict(input_dict)
+    return {"prediction": prediction}

request.py

@@ -0,0 +1,76 @@
+import requests
+import matplotlib.pyplot as plt
+
+# Define the URL for the prediction service
+url = "http://localhost:8960/predict"
+
+# Prepare the data for the prediction
+data = {
+    "Age": 35,
+    "DistanceFromHome": 10,
+    "Education": 2,
+    "NumCompaniesWorked": 3,
+    "PercentSalaryHike": 15,
+    "TotalWorkingYears": 10,
+    "TrainingTimesLastYear": 3,
+    "WorkLifeBalance": 2,
+    "YearsInCurrentRole": 4,
+    "YearsSinceLastPromotion": 1,
+    "YearsWithCurrManager": 2,
+    "BusinessTravel_Travel_Rarely": 1,
+    "BusinessTravel_Travel_Frequently": 0,
+    "Department_Research": 1,
+    "Department_Sales": 0,
+    "EducationField_Life_Sciences": 1,
+    "EducationField_Medical": 0,
+    "EducationField_Marketing": 0,
+    "EducationField_Other": 0,
+    "EducationField_Technical_Degree": 0,
+    "Gender_Male": 1,
+    "JobRole_Research_Scientist": 1,
+    "JobRole_Sales_Executive": 0,
+    "JobRole_Laboratory_Technician": 0,
+    "JobRole_Manufacturing_Director": 0,
+    "JobRole_Healthcare_Representative": 0,
+    "JobRole_Manager": 0,
+    "JobRole_Sales_Representative": 0,
+    "JobRole_Research_Director": 0,
+    "MaritalStatus_Married": 1,
+    "MaritalStatus_Single": 0,
+    "OverTime_Yes": 0
+}
+
+# Make the POST request
+try:
+    response = requests.post(url, json=data)
+    response.raise_for_status()  # Raise an error for bad responses
+    prediction = response.json()  # Parse the JSON response
+
+    # Check if the prediction contains the expected key and is a list
+    if isinstance(prediction, dict) and 'prediction' in prediction and isinstance(prediction['prediction'], list):
+        survival_probabilities = prediction['prediction']
+    else:
+        raise ValueError("Unexpected response format: {}".format(prediction))
+
+    # Create a list of years based on the number of predictions
+    years = list(range(1, len(survival_probabilities) + 1))
+
+    # Plot the data
+    plt.figure(figsize=(10, 6))
+    plt.plot(years, survival_probabilities, marker='o', linestyle='-', color='b')
+    plt.xlabel('Years')
+    plt.ylabel('Survival Probability')
+    plt.title('Employee Survival Probability Over Time')
+    plt.grid(True)
+    plt.xticks(years)
+    plt.ylim(0, 1)
+
+    # Show the plot
+    plt.show()
+
+except requests.exceptions.RequestException as e:
+    print("An error occurred while making the request:", e)
+except ValueError as ve:
+    print("Value error:", ve)
+except Exception as ex:
+    print("An unexpected error occurred:", ex)