forked from kubapok/auta-public
41 lines
1.5 KiB
Python
41 lines
1.5 KiB
Python
|
import pandas as pd
|
||
|
|
from sklearn.linear_model import LinearRegression
|
||
|
|
|
||
|
|
def proces(data1):
|
||
|
|
data1 = pd.concat([data1, data1['engineType'].str.get_dummies().astype(bool)], axis=1)
|
||
|
|
data1 = data1.drop(['engineType', 'brand'], axis=1)
|
||
|
|
return data1
|
||
|
|
|
||
|
|
|
||
|
|
def dev():
|
||
|
|
data1_dev = pd.read_table('C:/Users/Ufnow/Desktop/Projekt/auta/auta-public/dev-0/in.tsv', error_bad_lines=False, header=None,
|
||
|
|
names=['mileage', 'year', 'brand', 'engineType', 'engineCap'])
|
||
|
|
data1_dev = proces(data1_dev)
|
||
|
|
data2_pred = model.predict(data1_dev)
|
||
|
|
data2_pred.tofile('C:/Users/Ufnow/Desktop/Projekt/auta/auta-public/dev-0/out.tsv', sep='\n')
|
||
|
|
|
||
|
|
|
||
|
|
def testA():
|
||
|
|
data1_test_A = pd.read_table('C:/Users/Ufnow/Desktop/Projekt/auta/auta-public/test-A/in.tsv', error_bad_lines=False, header=None,
|
||
|
|
names=['mileage', 'year', 'brand', 'engineType', 'engineCap'])
|
||
|
|
data1_test_A = proces(data1_test_A)
|
||
|
|
data2_pred_A = model.predict(data1_test_A)
|
||
|
|
data2_pred_A.tofile('C:/Users/Ufnow/Desktop/Projekt/auta/auta-public/test-A/out.tsv', sep='\n')
|
||
|
|
|
||
|
|
data = pd.read_table('C:/Users/Ufnow/Desktop/Projekt/auta/auta-public/train/train.tsv', error_bad_lines=False, header=None,
|
||
|
|
names=['price', 'mileage', 'year', 'brand', 'engineType', 'engineCap'])
|
||
|
|
data2_train = data['price']
|
||
|
|
data1_train = data.iloc[:, 1:]
|
||
|
|
data1_train = proces(data1_train)
|
||
|
|
|
||
|
|
model = LinearRegression()
|
||
|
|
model.fit(data1_train, data2_train)
|
||
|
|
|
||
|
|
def main():
|
||
|
|
dev()
|
||
|
|
testA()
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
main()
|