s434788_auta-public/Auta.py

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import PolynomialFeatures

col_names = ["Price","Mileage","Year","Brand","EngineType","EngineCapacity"]



def prepareData(df):
    df["Age"] = 2018 - df["Year"]
    df["SqrtAge"] = df.Age**0.5
    df = pd.concat([df, df['EngineType'].str.get_dummies()], axis = 1 )
    df = df.drop(['EngineType','Brand'], axis = 1)
    df["SqrtMileage"] = df.Mileage ** 0.5
    df["SqrtEngineCapacity"] = df.EngineCapacity ** 0.5
    poly = PolynomialFeatures(2, interaction_only=True)
    df = poly.fit_transform(df)
    return df

def main():

    df =pd.read_csv('train/train.tsv', sep="\t", names=col_names)
    y_dev =pd.read_csv('dev-0/expected.tsv', sep="\t", names=["Price"])
    x_dev =pd.read_csv('dev-0/in.tsv', sep="\t", names=["Mileage","Year","Brand","EngineType","EngineCapacity"])
    x_test =pd.read_csv('test-A/in.tsv', sep="\t", names=["Mileage","Year","Brand","EngineType","EngineCapacity"])

    y_train = df.Price
    x_train = df.drop('Price', axis=1)

    x_train = prepareData(x_train)

    linReg = LinearRegression()
    linReg.fit(x_train, y_train)

    x_dev = prepareData(x_dev)
    x_test = prepareData(x_test)

    #Score modelu dla zbioru dev
    score = linReg.score(x_dev, y_dev)
    print(score)

    #Wartość RMSE dla zbioru dev
    y_pred = linReg.predict(x_dev)
    data = {'Price':y_pred}
    y_pred = pd.DataFrame(data)

    y_pred.to_csv(r'dev-0/out.tsv', sep='\t', index=False,  header=False)

    rmse = mean_squared_error(y_dev, y_pred, squared=False)
    print(rmse)

    #predict dla test-A
    y_pred_test = linReg.predict(x_test)
    data = {'Price':y_pred_test}
    y_pred_test = pd.DataFrame(data)

    y_pred_test.to_csv(r'test-A/out.tsv', sep='\t', index=False,  header=False)


if __name__ == "__main__":
    main()