import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import scipy as sp
from scipy.io import arff
from scipy import stats

from sklearn.datasets import make_moons
from sklearn.ensemble import AdaBoostClassifier
from sklearn.datasets import make_classification

from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.metrics import accuracy_score, confusion_matrix, f1_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score

import warnings
warnings.filterwarnings("ignore")

#zad1
dane=pd.read_csv('autos.csv')
#print(dane)
dane1=arff.loadarff('autos.arff')
#print(dane1)

ramka=pd.DataFrame(data=dane)
print(ramka)

#zad2
marki=dane.groupby('make')
marki_paliwo_miasto=marki['citympg'].mean()
print('miasto')
print(marki_paliwo_miasto)

marki_paliwo_autostrada=marki['highwaympg'].mean()
print('autostrada')
print(marki_paliwo_autostrada)

#zad8
X=np.linspace(-1.5, 1.5, 50)
Y=np.linspace(-1.5, 1.5, 50)

XX, YY = np.meshgrid(X, Y)

Z=(XX**2 + YY**2 - 1)**3 - XX**2*YY**3
plt.contour(X, Y, Z)
plt.show()

#zad 3
X,y=make_moons(n_samples=1000, shuffle=True, noise=0.5, random_state=None)
#XU, XT, yu, yt = train_test_split(X, y, test_size=0.5, random_state=0)
#zad 4
clf = AdaBoostClassifier(n_estimators=100, base_estimator=DecisionTreeClassifier(max_depth=3))
model = clf.fit(X, y)
#zad 5
y_pred = model.predict(X)

print("Dokladnosc :",metrics.accuracy_score(y, y_pred))
print("Macierz konfuzji:")
print(confusion_matrix(y, y_pred))

#zad 6
plt.scatter(X[:, 0], X[:, 1], c=y)
XX, YY = np.meshgrid(np.linspace(np.min(X[:, 0]), np.max(X[:, 0]), 200), np.linspace(np.min(X[:, 1]), np.max(X[:, 1]), 200))
Z = clf.predict(np.vstack([XX.ravel(), YY.ravel()]).T)
plt.contour(XX, YY, np.reshape(Z, (200, 200)))
plt.show()
#zad 7
print(np.mean(cross_val_score(clf, X, y, scoring="f1")))