linreg.py

@@ -1,37 +0,0 @@
-import pandas as pd
-from sklearn.linear_model import LinearRegression
-from sklearn.metrics import mean_squared_error
-from math import sqrt
-
-# trenowanie
-train_data = pd.read_csv('train/train.tsv', sep='\t', names=['price', 'mileage', 'year', 'brand', 'engine_type', 'engine_capacity'])
-train_y = train_data[['price']]
-train_x = train_data[['mileage', 'year', 'engine_capacity']]
-lin_reg = LinearRegression()
-lin_reg.fit(train_x, train_y)
-
-# predykcja dev-0
-dev_data = pd.read_csv('dev-0/in.tsv', sep='\t', names=['mileage', 'year', 'brand', 'engine_type', 'engine_capacity'])
-dev_x = dev_data[['mileage', 'year', 'engine_capacity']]
-dev_prediction = lin_reg.predict(dev_x)
-
-# ewaluacja dev-0 przy pomocy rmse
-dev_y = pd.read_csv('dev-0/expected.tsv', sep='\n', header=None)
-dev_rmse = sqrt(mean_squared_error(dev_y, dev_prediction))
-print(dev_rmse)
-
-# predycja test-A
-test_data = pd.read_csv('test-A/in.tsv', sep='\t', names=['mileage', 'year', 'brand', 'engine_type', 'engine_capacity'])
-test_x = test_data[['mileage', 'year', 'engine_capacity']]
-test_prediction = lin_reg.predict(test_x)
-
-# zapisane predykcji do plików out
-with open('test-A/out.tsv', 'w') as test_output:
-    for prediction in test_prediction:
-        test_output.write(str(prediction[0]) + '\n')
-
-with open('dev-0/out.tsv', 'w') as dev_output:
-    for prediction in dev_prediction:
-        dev_output.write(str(prediction[0]) + '\n')
-
-