File size: 2,348 Bytes
60434a7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
# train_model.py
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn import tree
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
import joblib
class InsuranceClaimModelTrainer:
def __init__(self, data_path):
self.data_path = data_path
self.model = None
def load_data(self):
# Load the dataset
df = pd.read_csv(self.data_path)
# Separate features and target
X = df.drop(columns=['insuranceclaim'])
y = df['insuranceclaim']
return X, y
def preprocess_data(self, X):
# Define preprocessing for numerical features (scaling)
numerical_features = ['age', 'bmi', 'children', 'charges']
numerical_transformer = StandardScaler()
# Define preprocessing for categorical features (one-hot encoding)
categorical_features = ['sex', 'smoker', 'region']
categorical_transformer = OneHotEncoder(handle_unknown='ignore', drop='first')
# Combine preprocessing steps
preprocessor = ColumnTransformer(
transformers=[
('num', numerical_transformer, numerical_features),
('cat', categorical_transformer, categorical_features)
])
return preprocessor
def train_model(self):
# Load and preprocess the data
X, y = self.load_data()
preprocessor = self.preprocess_data(X)
# Create a preprocessing and modeling pipeline
self.model = Pipeline(steps=[
('preprocessor', preprocessor),
('classifier', tree.DecisionTreeClassifier(random_state=42))
])
# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=10)
# Train the model
self.model.fit(X_train, y_train)
# Save the preprocessor and the trained model using joblib
joblib.dump(self.model, 'model/insurance_claim_prediction_model.joblib')
print("Model trained and saved successfully!")
if __name__ == "__main__":
trainer = InsuranceClaimModelTrainer('dataset/insurance2.csv')
trainer.train_model()
|