import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split

boston_dataset = load_boston()

#zad1
print("Zad 1")
print(boston_dataset.keys())
bos = pd.DataFrame(boston_dataset.data)
bos.columns = boston_dataset.feature_names
bos['MEDV'] = boston_dataset.target
print(bos.head(10))
print(bos.tail(10))

#zad2
print("Zad 2")
print(bos.info(verbose=True))

#zad3
print("Zad 3")
print(bos.describe())
# a) 3.613524 i 8.601545
# b) 5.000000 i 50.000000
# c) 11.360000

#zad4
sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.distplot(bos['MEDV'], bins=30)
plt.show()

#zad5
correlation_matrix = bos.corr().round(2)
sns.heatmap(data=correlation_matrix, annot=True)
plt.show()
# a) RM - liczba pokoi
# b) LSTAT - % ludzi o nizszym stanie
# c) RAD-TAX - dostepnosc autostrad, podatek od nierucomosci

# dodanio skolerowane - RM
ax1 = sns.regplot(x=bos['MEDV'], y=bos['RM'], data=boston_dataset)
plt.show()
# ujemnie skolerowane - LSTAT
ax2 = sns.regplot(x=bos['MEDV'], y=bos['LSTAT'], data=boston_dataset)
plt.show()
# najmniej skolerowane - CHAS
ax3 = sns.regplot(x=bos['MEDV'], y=bos['CHAS'], data=boston_dataset)
plt.show()

#zad6
print("Zad 6")
X = pd.DataFrame(np.c_[bos['LSTAT'], bos['RM']], columns = ['LSTAT','RM'])
Y = bos['MEDV']

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state=5)
print(X_train.shape)
print(X_test.shape)
print(Y_train.shape)
print(Y_test.shape)

#zad7

from sklearn.linear_model import LinearRegression

lm = LinearRegression()
lm.fit(X_train, Y_train)

#a
Y_train_predict = lm.predict(X_train)
plt.scatter(Y_train, Y_train_predict)
plt.xlabel("Train Prices: $Y_i$")
plt.ylabel("Predicted train prices: $\hat{Y}_i$")
plt.title("Train rices vs Predicted train prices: $Y_i$ vs $\hat{Y}_i$")
plt.show()

#b
Y_test_predict = lm.predict(X_test)
plt.scatter(Y_test, Y_test_predict)
plt.xlabel("Test prices: $Y_i$")
plt.ylabel("Predicted test prices: $\hat{Y}_i$")
plt.title("Test prices vs Predicted test prices: $Y_i$ vs $\hat{Y}_i$")
plt.show()

#zad8

from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_squared_error

print("Zad 8")
rmse = (np.sqrt(mean_squared_error(Y_train, Y_train_predict)))
mae = mean_absolute_error(Y_train, Y_train_predict)

print("The model performance for training set")
print("--------------------------------------")
print('RMSE is {}'.format(rmse))
print('MAE  is {}'.format(mae))
print("\n")

rmse = (np.sqrt(mean_squared_error(Y_test, Y_test_predict)))
mae = mean_absolute_error(Y_test, Y_test_predict)

print("The model performance for testing set")
print("--------------------------------------")
print('RMSE is {}'.format(rmse))
print('MAE  is {}'.format(mae))