from sklearn import datasets, linear_model
from sklearn.metrics import r2_score, mean_squared_error
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import Pipeline
from sklearn.model_selection import cross_val_score
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

## подкл выборку

x_train = pd.read_table ("tic/ticdata2000.txt", header = None).iloc [0:4000, 0:85]
x_test = x_train.iloc[0:4000, 84]


y_train = pd.read_table ("tic/ticeval2000.txt", header = None)
y_test = pd.read_table ("tic/tictgts2000.txt", header = None)


## обучение выборки
regression = linear_model.LinearRegression()
regression.fit (x_train, y_train)


train_predict = regression.predict (x_train)

print('Коэффициенты: \n', regression.coef_)
print("Cреднеквадратичная ошибка: %.2f" % mean_squared_error(y_train, train_predict))
print('Оценка отклонения: %.2f' % r2_score(y_train, train_predict))

## Проверка точности модели по тестовой выборке и запись в результирующий файл
y_pr = pd.DataFrame(train_predict)
y_test = y_test.reset_index(drop = True)
res = pd.concat([y_pr, y_test], axis=1)
res.to_csv("result.txt", index = False)