lab3

import pandas as pd
import pydotplus
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import ElasticNet
from sklearn.model_selection import train_test_split

all = pd.read_csv('winequalityN.csv', header=0)
all.isnull().any()
all = all.fillna(method='ffill')

print(all.shape[0])

mask = all['type'] == "white"
white, red = all[mask], all[~mask]
print(all)

df = all
x = df.values[:, 1:12]
y = df.values[:, 12:13]

x_norm = (x - x.min()) / (x.max() - x.min())
x_norm = x_norm.astype('float')
print(x_norm.round(3))
y = y.astype('float')
print("Все вина = ", y.shape[0])

for k in range(10):

    X_train, X_test, y_train, y_test = train_test_split(x_norm, y, test_size=0.3, random_state=0)
    print("y_test = ", y_test.shape[0])
    regressor = LinearRegression()
    regressor.fit(X_train, y_train)

    y_pred = regressor.predict(X_test)
    summ = 0
    for i in range(y_pred.shape[0]):
        summ = summ + abs(y_test[i] - y_pred[i])
    mistake = summ / y_pred.shape[0]
    good = 1 - mistake
    print(good)