Update modelLoanAPI.py

modelLoanAPI.py

@@ -1,6 +1,4 @@
-# -*- coding: utf-8 -*-
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import JSONResponse
+from fastapi import FastAPI, HTTPException, Query
 import pandas as pd
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
@@ -17,7 +15,7 @@ warnings.filterwarnings("ignore")
 app = FastAPI()
 
 @app.post("/predict_worker_earnings/")
-async def predict_worker_earnings(worker_id: int):
+async def predict_worker_earnings(worker_id: int = Query(...)):
     try:
         # Initialize result dictionary
         results = {
@@ -28,11 +26,10 @@ async def predict_worker_earnings(worker_id: int):
         }
 
         # Load data
-        df = pd.read_csv('extended_worker_dataset.csv')
+        df = pd.read_csv('/app/data/extended_worker_dataset.csv')
 
         # Filter for one worker_id
         df = df[df['worker_id'] == worker_id].copy()
-
         if df.empty:
             raise HTTPException(status_code=404, detail=f"No data found for worker_id {worker_id}")
 
@@ -47,7 +44,6 @@ async def predict_worker_earnings(worker_id: int):
         le = LabelEncoder()
         df['job_type_encoded'] = le.fit_transform(df['job_type'])
 
-        # Split data
         split_point = int(len(df) * 0.8)
         train_df = df.iloc[:split_point].copy()
         test_df = df.iloc[split_point:].copy()
@@ -62,14 +58,15 @@ async def predict_worker_earnings(worker_id: int):
         for subset in [train_df, test_df]:
             subset['dayofweek'] = subset['timestamp'].dt.dayofweek
             subset['month'] = subset['timestamp'].dt.month
+           Pin to content
             subset['year'] = subset['timestamp'].dt.year
             subset['dayofyear'] = subset['timestamp'].dt.dayofyear
             subset['is_weekend'] = subset['dayofweek'].isin([5, 6]).astype(int)
 
         # Train classifier
         X_train_class = train_df[['dayofweek', 'month', 'year', 'dayofyear',
-                                'is_weekend', 'job_type_encoded', 'feedback_score',
-                                'years_of_experience']]
+                                 'is_weekend', 'job_type_encoded', 'feedback_score',
+                                 'years_of_experience']]
         y_train_class = train_df['has_job']
 
         classifier = RandomForestClassifier(
@@ -80,8 +77,8 @@ async def predict_worker_earnings(worker_id: int):
         # Train regressor
         train_df_reg = train_df[train_df['has_job'] == 1].copy()
         X_train_reg = train_df_reg[['dayofweek', 'month', 'year', 'dayofyear',
-                                  'is_weekend', 'job_type_scaled', 'feedback_score',
-                                  'years_exp_scaled', 'job_exp_interaction']]
+                                   'is_weekend', 'job_type_scaled', 'feedback_score',
+                                   'years_exp_scaled', 'job_exp_interaction']]
         y_train_reg = train_df_reg['contracted_wage']
 
         regressor = RandomForestRegressor(
@@ -91,7 +88,7 @@ async def predict_worker_earnings(worker_id: int):
 
         # Prepare future dataframe
         future_df = test_df[['timestamp', 'job_type', 'job_type_encoded',
-                           'feedback_score', 'years_of_experience']].rename(columns={'timestamp': 'ds'})
+                            'feedback_score', 'years_of_experience']].rename(columns={'timestamp': 'ds'})
 
         future_df['dayofweek'] = future_df['ds'].dt.dayofweek
         future_df['month'] = future_df['ds'].dt.month
@@ -210,10 +207,10 @@ async def predict_worker_earnings(worker_id: int):
                 return obj.tolist()
             return obj
 
-        return JSONResponse(content=json.loads(json.dumps(results, default=convert_to_serializable)))
+        return json.loads(json.dumps(results, default=convert_to_serializable))
 
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        raise HTTPException(status_code=500, detail=f"Error processing request: {str(e)}")
 
 if __name__ == "__main__":
     import uvicorn