#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue May 14 14:55:14 2019

@author: student
"""
#















from sklearn.datasets.samples_generator import make_blobs
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
from pandas import DataFrame

X,y= make_blobs(n_samples=1000, centers=4
                  ,random_state=0)

kmeans = KMeans(n_clusters = 4)
kmeans.fit(X)
y_kmeans = kmeans.predict(X)

plt.figure()
plt.scatter(X[:,0],X[:,1],c=y_kmeans)
plt.show


from sklearn.datasets import make_moons

X, y = make_moons(200,noise=.05)


kmeans = KMeans(n_clusters = 2)
kmeans.fit(X)
y_kmeans = kmeans.predict(X)

plt.figure()
plt.scatter(X[:,0],X[:,1],c=y_kmeans)
plt.show




# generate 2d classification dataset
X, y = make_moons(n_samples=100, noise=0.1)
# scatter plot, dots colored by class value
df = DataFrame(dict(x=X[:,0], y=X[:,1], label=y))
colors = {0:'red', 1:'blue'}
fig, ax = plt.subplots()
grouped = df.groupby('label')
for key, group in grouped:
    group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
plt.show()




from scipy.cluster import hierarchy
import matplotlib.pyplot as plt

Z = hierarchy.linkage(X, 'ward')
plt.figure()
dn = hierarchy.dendrogram(Z, p=12, truncate_mode='lastp')



#
#   Zadanie 4
#
#import matplotlib.pyplot as plt
#from mpl_toolkits.mplot3d import Axes3D
#from sklearn import datasets
#from sklearn.decomposition import PCA
#
## import some data to play with
#iris = datasets.load_iris()
#X = iris.data[:, :2]  # we only take the first two features.
#y = iris.target
#
#x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
#y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
#
#plt.figure(2, figsize=(8, 6))
#plt.clf()
#
## Plot the training points
#plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1,
#            edgecolor='k')
#plt.xlabel('Sepal length')
#plt.ylabel('Sepal width')
#
#plt.xlim(x_min, x_max)
#plt.ylim(y_min, y_max)
#plt.xticks(())
#plt.yticks(())
#
## To getter a better understanding of interaction of the dimensions
## plot the first three PCA dimensions
#fig = plt.figure(1, figsize=(8, 6))
#ax = Axes3D(fig, elev=-150, azim=110)
#X_reduced = PCA(n_components=3).fit_transform(iris.data)
#ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=y,
#           cmap=plt.cm.Set1, edgecolor='k', s=40)
#ax.set_title("First three PCA directions")
#ax.set_xlabel("1st eigenvector")
#ax.w_xaxis.set_ticklabels([])
#ax.set_ylabel("2nd eigenvector")
#ax.w_yaxis.set_ticklabels([])
#ax.set_zlabel("3rd eigenvector")
#ax.w_zaxis.set_ticklabels([])











# Zadanie 5