|
|
import joblib
|
|
|
import numpy as np
|
|
|
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
|
|
|
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
|
|
|
|
|
|
class LoanApprovalModel:
|
|
|
def __init__(self, model_type='random_forest'):
|
|
|
self.model_type = model_type
|
|
|
self.model = self._get_model()
|
|
|
self.preprocessor = None
|
|
|
self.feature_names = None
|
|
|
|
|
|
def _get_model(self):
|
|
|
if self.model_type == 'random_forest':
|
|
|
return RandomForestClassifier(n_estimators=100, random_state=42)
|
|
|
elif self.model_type == 'gradient_boosting':
|
|
|
return GradientBoostingClassifier(random_state=42)
|
|
|
else:
|
|
|
raise ValueError(f"Unsupported model type: {self.model_type}")
|
|
|
|
|
|
def train(self, preprocessor, X_train, y_train, feature_names=None):
|
|
|
"""Train the model"""
|
|
|
self.preprocessor = preprocessor
|
|
|
self.feature_names = feature_names
|
|
|
|
|
|
|
|
|
X_train_processed = preprocessor.fit_transform(X_train)
|
|
|
|
|
|
|
|
|
self.model.fit(X_train_processed, y_train)
|
|
|
|
|
|
def predict(self, X):
|
|
|
"""Make predictions"""
|
|
|
X_processed = self.preprocessor.transform(X)
|
|
|
return self.model.predict(X_processed)
|
|
|
|
|
|
def predict_proba(self, X):
|
|
|
"""Get prediction probabilities"""
|
|
|
X_processed = self.preprocessor.transform(X)
|
|
|
return self.model.predict_proba(X_processed)
|
|
|
|
|
|
def evaluate(self, X_test, y_test):
|
|
|
"""Evaluate model performance"""
|
|
|
y_pred = self.predict(X_test)
|
|
|
y_proba = self.predict_proba(X_test)[:, 1]
|
|
|
|
|
|
metrics = {
|
|
|
'accuracy': accuracy_score(y_test, y_pred),
|
|
|
'precision': precision_score(y_test, y_pred),
|
|
|
'recall': recall_score(y_test, y_pred),
|
|
|
'f1': f1_score(y_test, y_pred),
|
|
|
'roc_auc': roc_auc_score(y_test, y_proba)
|
|
|
}
|
|
|
|
|
|
return metrics
|
|
|
|
|
|
def save_model(self, filepath):
|
|
|
"""Save model to disk"""
|
|
|
model_data = {
|
|
|
'model': self.model,
|
|
|
'preprocessor': self.preprocessor,
|
|
|
'feature_names': self.feature_names,
|
|
|
'model_type': self.model_type
|
|
|
}
|
|
|
joblib.dump(model_data, filepath)
|
|
|
|
|
|
@classmethod
|
|
|
def load_model(cls, filepath):
|
|
|
"""Load model from disk"""
|
|
|
model_data = joblib.load(filepath)
|
|
|
|
|
|
model_instance = cls(model_type=model_data['model_type'])
|
|
|
model_instance.model = model_data['model']
|
|
|
model_instance.preprocessor = model_data['preprocessor']
|
|
|
model_instance.feature_names = model_data['feature_names']
|
|
|
|
|
|
return model_instance |
