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('loan.csv')
    x = data[['ApplicantIncome', 'Credit_History', 'Education', 'Married', 'Self_Employed']]
    y = data[['LoanAmount']]

    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=42)

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

    y_predicted = poly.predict(x_test)

    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(x_test))], y=y_test, c='green', s=5)
    plt.scatter(x=[i for i in range(len(x_test))], y=y_predicted, c='red', s=5)
    plt.show()


start()