Machine-Learning-SVM-algorithm/SVM-census.py at master · bsdharshini/Machine-Learning-SVM-algorithm · 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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
#!/usr/bin/env python
# coding: utf-8

# 1


import pandas as pd
import numpy as np

# 2


original_data =pd.read_csv(
    "adult.csv",
    names=[
        "Age","Workclass","fnlwgt","Education","Education-Num","Marital Status",
        "Occupation","Relationship","Race","Gender","Capital Gain","Capital Loss",
        "Hours per week","Country","Target"],
    sep=r'\s*,\s*',
    engine='python',
    na_values='?')
original_data.head()


# 3


import matplotlib.pyplot as plt
import math
get_ipython().run_line_magic('matplotlib', 'inline')

fig = plt.figure(figsize=(20,20))
cols=3
rows=math.ceil(float(original_data.shape[1])/cols)

for i,column in enumerate(['Age','Workclass','Education','Occupation','Race','Gender']):
    ax=fig.add_subplot(rows,cols,i+1)
    ax.set_title(column)
    if original_data.dtypes[column] ==np.object:
        original_data[column].value_counts().plot(kind="bar",axes=ax)
    else:
        original_data[column].hist(axes=ax)
        plt.xticks(rotation='vertical')
plt.subplots_adjust(hspace=0.7, wspace=0.2)
plt.show()


# 4

import sklearn.preprocessing as preprocessing
le=preprocessing.LabelEncoder()
original_data['Occupation']=le.fit_transform(original_data['Occupation'].astype(str))
original_data.head()


# 5


original_data['Target']=le.fit_transform(original_data['Target'].astype(str))
original_data.tail()


# 6

original_data.groupby('Education-Num').Target.mean().plot(kind='bar')
plt.show()

# 7


from sklearn.model_selection import train_test_split
X=original_data[['Education-Num','Occupation']]
Y=original_data['Target']
X_train,x_test,Y_train,y_test=train_test_split(X,Y,test_size=0.2,random_state=0)

# 8


from sklearn.svm import SVC
classifier=SVC()
classifier.fit(X_train,Y_train)
score=classifier.score(x_test,y_test)
print(score)


# 9


import seaborn as sns
corrmat=original_data.corr()
f,ax=plt.subplots(figsize=(7,7))
sns.heatmap(corrmat,vmax=.8, square=True);
plt.show()


# 10


original_data['Race']=le.fit_transform(original_data['Race'].astype(str))
original_data['Gender']=le.fit_transform(original_data['Gender'].astype(str))
original_data['Marital Status']=le.fit_transform(original_data['Marital Status'].astype(str))
original_data['Education']=le.fit_transform(original_data['Education'].astype(str))


# 11


corrmat=original_data.corr()
f,ax=plt.subplots(figsize=(7,7))
sns.heatmap(corrmat,vmax=.8, square=True);
plt.show()


# 12


f,ax=plt.subplots(figsize=(7,7))
sns.heatmap(corrmat,vmax=.8,square=True,annot=True,fmt='.2f')
plt.show()

# 13


X=original_data[['Education-Num','Occupation','Age','Gender']]
Y=original_data['Target']
X_train,x_test,Y_train,y_test=train_test_split(X,Y,test_size=0.2,random_state=0)
classifier=SVC()
classifier.fit(X_train,Y_train)
score=classifier.score(x_test,y_test)
print(score)


# 14


classifier =SVC(kernel='rbf', C=1.0)
classifier.fit(X_train,Y_train)
score=classifier.score(x_test,y_test)
print(score)


# 15


classifier =SVC(kernel='linear', C=10.0)
classifier.fit(X_train,Y_train)
score=classifier.score(x_test,y_test)
print(score)