Machine-Learning--Python/Turkey student analysis at master · sudheera96/Machine-Learning--Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

df=pd.read_csv("C:/Users/ADMIN/Desktop/turkiye-student-evaluation_R_Specific.csv")
df.shape
df.head
df.describe

X_questions = df.iloc[:,5:33]
question_means = X_questions.mean(axis = 0)
grand_mean = question_means.mean()

std_by_questions = question_means.std()
X = df.iloc[:,5:33]


from sklearn.decomposition import PCA
pca = PCA(n_components = 2, random_state=1)
X_pca = pca.fit_transform(X)
pca.explained_variance_ratio_.cumsum()[1]

from sklearn.cluster import KMeans
distortions = []
K_to_try = range(1, 6)

for i in K_to_try:
    model = KMeans(
            n_clusters=i,
            init='k-means++',

           random_state=1)
    model.fit(X_pca)
    distortions.append(model.inertia_)
plt.plot(K_to_try, distortions, marker='o')
plt.xlabel('Number of Clusters (k)')
plt.ylabel('Distortion')
plt.show()

model = KMeans(
    n_clusters=3,
    init='k-means++',

    random_state=1)

model = model.fit(X_pca)

y = model.predict(X_pca)

plt.scatter(X_pca[y == 0, 0], X_pca[y == 0, 1], s = 100, c = 'yellow', label = 'Cluster 1')
plt.scatter(X_pca[y == 1, 0], X_pca[y == 1, 1], s = 100, c = 'green', label = 'Cluster 2')
plt.scatter(X_pca[y == 2, 0], X_pca[y == 2, 1], s = 100, c = 'red', label = 'Cluster 3')

plt.scatter(model.cluster_centers_[:, 0], model.cluster_centers_[:, 1], s = 300, c = 'blue', label = 'Centroids')
plt.title('Clusters of students')
plt.xlabel('PCA1')
plt.ylabel('PCA2')
plt.legend()
plt.show()

import collections
print(collections.Counter(y))


import scipy.cluster.hierarchy as hier
dendrogram = hier.dendrogram(hier.linkage(X_pca, method = 'ward'))
plt.title('Dendrogram')
plt.xlabel('questions')
plt.ylabel('Euclidean distances')
plt.show()

from sklearn.cluster import AgglomerativeClustering

model = AgglomerativeClustering(n_clusters = 2,
                          affinity ='euclidean',
                          linkage ='ward')
y_hc = model.fit_predict(X_pca)

plt.scatter(X_pca[y_hc == 0, 0], X_pca[y_hc == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X_pca[y_hc== 1, 0], X_pca[y_hc == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')

plt.title('Clusters of customers')
plt.xlabel('PCA1')
plt.ylabel('PCA2')
plt.legend()
plt.show()

import collections
collections.Counter(y_hc)