import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression

data = pd.read_csv("data6.tsv", sep="\t")

x = data.iloc[:, 0].values
y = data.iloc[:, 1].values

x = x.reshape(-1, 1)

two_dim = PolynomialFeatures(degree=2)
five_dim = PolynomialFeatures(degree=5)

X_two_dim = two_dim.fit_transform(x)
X_five_dim = five_dim.fit_transform(x)

one_dim_reg = LinearRegression()
one_dim_reg.fit(x, y)

two_dim_reg = LinearRegression()
two_dim_reg.fit(X_two_dim, y)

five_dim_reg = LinearRegression()
five_dim_reg.fit(X_five_dim, y)

myline = np.linspace(min(x), max(x), 100).reshape(-1, 1)

one_dim_pred = one_dim_reg.predict(x)
two_dim_pred = two_dim_reg.predict(two_dim.fit_transform(myline))
five_dim_pred = five_dim_reg.predict(five_dim.fit_transform(myline))


fig1 = plt.figure(figsize=(6, 10))
ax1 = fig1.add_subplot(3, 1, 1)
ax1.set_title('Regresja pierwszego stopnia')
ax1.scatter(x, y)
ax1.plot(x, one_dim_pred, color="red")

ax2 = fig1.add_subplot(3, 1, 2)
ax2.set_title('Regresja drugiego stopnia')
ax2.scatter(x, y)
ax2.plot(myline, two_dim_pred, color="green")

ax3 = fig1.add_subplot(3, 1, 3)
ax3.set_title('Regresja piątego stopnia')
ax3.scatter(x, y)
ax3.plot(myline, five_dim_pred, color="orange")

plt.tight_layout()
plt.show()