File size: 1,379 Bytes
e0a433a |
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 |
from src.preprocessing import Preprocessing
from src.model import ModelBuilder
from tests import test2direct
import pandas as pd
import pickle
import os
def main():
# Load the dataset
data = pd.read_csv("data/bengaluru_house_prices.csv")
# Preprocess the data
print("Starting Data Preprocessing...")
preprocessor = Preprocessing(data)
preprocessor.clean_data()
preprocessor.feature_engineering()
preprocessor.remove_bhk_outliers()
preprocessor.encode_features()
preprocessor.scale_features()
preprocessor.handle_missing_values()
print("Preprocessing completed!")
# Build and evaluate the model
print("Starting Model Building and Evaluation...")
model_builder = ModelBuilder(data=preprocessor.data)
X_train, X_test, y_train, y_test = model_builder.split_data(target_column='price')
model_builder.train_model(X_train, y_train)
mse, r2 = model_builder.evaluate_model(X_test, y_test)
#print(f"Model Evaluation:\nMean Squared Error: {mse}\nR2 Score: {r2}")
# Save the trained model
print("Trained model saved successfully!")
# Save the trained model as a pickle file
model_builder.save_model_as_pickle()
# Save the feature names as a pickle file
model_builder.save_features_as_pickle(data=preprocessor.data)
test2direct.main()
if __name__ == "__main__":
main()
|