update

app.py

@@ -7,10 +7,16 @@ import pandas as pd
 # Initialize FastAPI app
 app = FastAPI()
 
-
-# Load the trained Gradient Boosting model
+# Load the trained Gradient Boosting model and encoder
 model = joblib.load('gradient_boosting_model.pkl')
 encoder = joblib.load("encoder.pkl")
+
+# Define categorical columns
+categorical_columns = [
+    "job", "marital", "education", "default", "housing", 
+    "loan", "contact", "month", "poutcome"
+]
+
 # Define the input data schema
 class PredictionInput(BaseModel):
     age: int
@@ -30,19 +36,6 @@ class PredictionInput(BaseModel):
     previous: int
     poutcome: str
 
-# Define the mapping for categorical variables (if encoded)
-categorical_mapping = {
-    "job": ['admin.', 'technician', 'blue-collar', 'management', 'retired', 'services', 'self-employed', 'entrepreneur', 'unemployed', 'housemaid', 'student', 'unknown'],
-    "marital": ['married', 'single', 'divorced'],
-    "education": ['secondary', 'tertiary', 'primary', 'unknown'],
-    "default": ['no', 'yes'],
-    "housing": ['no', 'yes'],
-    "loan": ['no', 'yes'],
-    "contact": ['unknown', 'telephone', 'cellular'],
-    "month": ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec'],
-    "poutcome": ['unknown', 'other', 'failure', 'success']
-}
-
 # Utility function to preprocess the input data
 def preprocess_input(data: PredictionInput):
     # Convert input data to a DataFrame for compatibility
@@ -64,17 +57,17 @@ def preprocess_input(data: PredictionInput):
         "previous": [data.previous],
         "poutcome": [data.poutcome],
     }
-    
     input_df = pd.DataFrame(input_df)
 
     # Apply OneHotEncoder to categorical columns
     encoded_features = encoder.transform(input_df[categorical_columns])
-    
+
     # Combine encoded features with numerical features
     numerical_features = input_df.drop(columns=categorical_columns).values
     final_features = np.concatenate([numerical_features, encoded_features], axis=1)
 
     return final_features
+
 # Define the GET endpoint to show the structure
 @app.get("/structure")
 async def get_structure():
@@ -98,16 +91,17 @@ async def get_structure():
         "poutcome": "success"
     }
     return example_data
+
 # Define a POST endpoint for predictions
 @app.post("/predict")
 async def predict(data: PredictionInput):
     # Preprocess the input
     input_data = preprocess_input(data)
-    
+
     # Make a prediction
     prediction = model.predict(input_data)
-    
+
     # Convert prediction to "yes"/"no"
     response = "yes" if prediction[0] == 1 else "no"
-    
+
     return {"prediction": response}