from matplotlib import pyplot as plt
from sklearn import metrics
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline
import pandas as pd


def start():
    data = pd.read_csv('sberbank_data.csv', index_col='id')
    x = data[['timestamp', 'full_sq', 'floor', 'max_floor', 'build_year', 'num_room', 'material', 'kremlin_km']]
    y = data[['price_doc']]

    x = x.replace('NA', 0)
    x.fillna(0, inplace=True)

    col_date = []

    for val in x['timestamp']:
        col_date.append(val.split('-', 1)[0])

    x = x.drop(columns='timestamp')
    x['timestamp'] = col_date

    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.01, random_state=42)

    poly = Pipeline([('poly', PolynomialFeatures(degree=3)),
                     ('linear', LinearRegression())])
    poly.fit(x_train, y_train)

    y_mean = y['price_doc'].mean()
    y_predicted = poly.predict(x_test)
    for i, n in enumerate(y_predicted):
        if n < 10000:
            y_predicted[i] = y_mean

    print('Оценка обучения:')
    print(metrics.r2_score(y_test, y_predicted))

    plt.figure(1, figsize=(16, 9))
    plt.title('Сравнение результатов обучения')
    plt.scatter(x=[i for i in range(len(y_test))], y=y_test, c='g', s=5)
    plt.scatter(x=[i for i in range(len(y_test))], y=y_predicted, c='r', s=5)
    plt.show()


start()