src/train_model.py

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
import pickle
import os

# Get the project root directory
project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

# Load the dataset
data_path = os.path.join(project_root, 'data', 'loan_approval_dataset.csv')
print(f"Loading data from: {data_path}")
df = pd.read_csv(data_path)

# Clean column names (remove leading/trailing spaces)
df.columns = df.columns.str.strip()

# Clean string values (remove leading/trailing spaces)
for col in df.select_dtypes(include=['object']).columns:
    df[col] = df[col].str.strip()

# Identify numerical and categorical columns
numerical_features = ['no_of_dependents', 'income_annum', 'loan_amount', 'loan_term', 
                     'cibil_score', 'residential_assets_value', 'commercial_assets_value', 
                     'luxury_assets_value', 'bank_asset_value']
categorical_features = ['education', 'self_employed']

# Prepare features and target
X = df[numerical_features + categorical_features]
y = df['loan_status'].map({'Approved': 1, 'Rejected': 0})

# Create preprocessing pipeline
numeric_transformer = Pipeline(steps=[
    ('scaler', StandardScaler())
])

categorical_transformer = Pipeline(steps=[
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

preprocessor = ColumnTransformer(
    transformers=[
        ('num', numeric_transformer, numerical_features),
        ('cat', categorical_transformer, categorical_features)
    ])

# Create full pipeline
model = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(n_estimators=100, random_state=42))
])

# Split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Fit the model
model.fit(X_train, y_train)

# Evaluate the model
train_score = model.score(X_train, y_train)
test_score = model.score(X_test, y_test)
print(f"Train accuracy: {train_score:.3f}")
print(f"Test accuracy: {test_score:.3f}")

# Save the model
models_dir = os.path.join(project_root, 'models')
os.makedirs(models_dir, exist_ok=True)

# Save as pickle file
with open(os.path.join(models_dir, 'loan_model.pkl'), 'wb') as f:
    pickle.dump(model, f)

print("Model saved successfully as loan_model.pkl!")