Homework 4:

Follow the steps below to:
- Read wine.csv in the data folder.
- The First Column contains the Wine Category. Don't use it in the models below. We are going to treat it as unsupervized learning and compare the results to the Wine column.
Try KMeans where n_clusters = 3 and compare the clusters to the Wine column.
Try PCA and see how much can you reduce the variable space.
- How many Components did you need to explain 99% of variance in this dataset?
- Plot the PCA variables to see if it brings out the clusters.
Try KMeans and Hierarchical Clustering using data from PCA and compare again the clusters to the Wine column.

Dataset

wine.csv is in data folder under homeworks



In [65]:

    
import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
%matplotlib inline

from sklearn.metrics import confusion_matrix, classification_report
from sklearn.cross_validation import cross_val_score,train_test_split

from scipy.spatial.distance import pdist, squareform

from sklearn.cluster import KMeans
from sklearn.decomposition import PCA



In [66]:

    
df = pd.read_csv("../data/wine.csv")

Try KMeans where n_clusters = 3 and compare the clusters to the Wine column.



In [68]:

    
km = KMeans(n_clusters=3)



In [69]:

    
X = df.drop('Wine', 1).values
Y = df['Wine'].values



In [70]:

    
km.fit(X)









    Out[70]:





KMeans(copy_x=True, init='k-means++', max_iter=300, n_clusters=3, n_init=10,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=0)



In [71]:

    
km.predict(X)









    Out[71]:





array([1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1,
       1, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 2, 2, 1, 1, 2, 2, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 0, 2, 0, 0, 2, 0, 0, 2,
       2, 2, 0, 0, 1, 2, 0, 0, 0, 2, 0, 0, 2, 2, 0, 0, 0, 0, 0, 2, 2, 0, 0,
       0, 0, 0, 2, 2, 0, 2, 0, 2, 0, 0, 0, 2, 0, 0, 0, 0, 2, 0, 0, 2, 0, 0,
       0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 2, 2, 2, 2, 0,
       0, 0, 2, 2, 0, 0, 2, 2, 0, 2, 2, 0, 0, 0, 0, 2, 2, 2, 0, 2, 2, 2, 0,
       2, 0, 2, 2, 0, 2, 2, 2, 2, 0, 0, 2, 2, 2, 2, 2, 0], dtype=int32)



In [72]:

    
Y









    Out[72]:





array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3,
       3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
       3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3])

Try PCA and see how much can you reduce the variable space.



In [90]:

    
#PCA
pca = PCA(2)



In [91]:

    
X2 = pca.fit_transform(X)



In [92]:

    
X2.shape









    Out[92]:





(178, 2)



In [93]:

    
X2[1]









    Out[93]:





array([-303.09741966,    5.36471768])



In [94]:

    
X[1]









    Out[94]:





array([  1.32000000e+01,   1.78000000e+00,   2.14000000e+00,
         1.12000000e+01,   1.00000000e+02,   2.65000000e+00,
         2.76000000e+00,   2.60000000e-01,   1.28000000e+00,
         4.38000000e+00,   1.05000000e+00,   3.40000000e+00,
         1.05000000e+03])



In [95]:

    
km2 = KMeans(3)



In [96]:

    
km2.fit(X2)









    Out[96]:





KMeans(copy_x=True, init='k-means++', max_iter=300, n_clusters=3, n_init=10,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=0)



In [97]:

    
km2.predict(X2)









    Out[97]:





array([1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1,
       1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 0, 2, 0, 2, 2, 0, 2, 2, 0,
       0, 0, 2, 2, 1, 0, 2, 2, 2, 0, 2, 2, 0, 0, 2, 2, 2, 2, 2, 0, 0, 2, 2,
       2, 2, 2, 0, 0, 2, 0, 2, 0, 2, 2, 2, 0, 2, 2, 2, 2, 0, 2, 2, 0, 2, 2,
       2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 0, 0, 0, 0, 2,
       2, 2, 0, 0, 2, 2, 0, 0, 2, 0, 0, 2, 2, 2, 2, 0, 0, 0, 2, 0, 0, 0, 2,
       0, 2, 0, 0, 2, 0, 0, 0, 0, 2, 2, 0, 0, 0, 0, 0, 2], dtype=int32)



In [98]:

    
plt.scatter(X2[:,0], X2[:,1], c=Y);



In [102]:

    
#that is not great, scale it
from sklearn.preprocessing import scale



In [116]:

    
scaled = scale(df.drop('Wine',1).values)



In [117]:

    
pca2 = PCA(2)



In [123]:

    
X3 = pca2.fit_transform(scaled)

Try KMeans and Hierarchical Clustering using data from PCA and compare again the clusters to the Wine column.



In [125]:

    
km3 = KMeans(3)



In [126]:

    
km3.fit(X3)









    Out[126]:





KMeans(copy_x=True, init='k-means++', max_iter=300, n_clusters=3, n_init=10,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=0)



In [128]:

    
km3.predict(X3)









    Out[128]:





array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2], dtype=int32)



In [131]:

    
Y









    Out[131]:





array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3,
       3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
       3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3])



In [134]:

    
plt.scatter(X3[:,0], X3[:,1], c=Y)









    Out[134]:





<matplotlib.collections.PathCollection at 0x10a5da190>



In [135]:

    
#Try KMeans and Hierarchical Clustering using data from PCA and compare again the clusters to the Wine column.