/
svm_hw.py
407 lines (321 loc) · 12.2 KB
/
svm_hw.py
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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
import numpy as np
from sklearn import svm
from sklearn.linear_model import LogisticRegression
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib import style
from sklearn.neighbors import KNeighborsClassifier
from sklearn.grid_search import GridSearchCV
style.use("ggplot")
path = "/MSAN_USF/courses_spring/630_AdvMachinelearning/code/data/svm-hw/"
def plot_linear_svm(filename, title):
df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
# df = pd.read_csv(path+"P3_outliar.txt", names=['x1','x2','y'], header=None)
columns_ls = []
for column in df.columns:
columns_ls.append(column)
X = df[columns_ls[0:len(columns_ls)-1]].values
Y = df[columns_ls[len(columns_ls)-1]].values
fig = plt.figure()
fig.suptitle(title, fontsize=20)
clf = svm.SVC(kernel='linear')
clf.fit(X, Y)
w = clf.coef_[0]
print "Weights SVM W0=%.2f and W1=%.2f"%(w[0], w[1])
a = -w[0]/w[1]
xx =np.linspace(-12, 34)
yy = a*xx-clf.intercept_[0]/w[1]
# plot the parallels to the separating hyperplane that pass through the
# support vectors
b = clf.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = clf.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])
# plot the line, the points, and the nearest vectors to the plane
# plt.plot(xx, yy, 'k-')
plt.text(0, 10, "Y=+1", fontsize=12)
plt.text(10, 0, "Y=-1", fontsize=12)
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.plot(xx,yy,color="black", label ="svm decision boundary")
model = LogisticRegression()
model.fit(X, Y)
w = model.coef_[0]
a = -w[0]/w[1]
print "Weights Logistic W0=%.2f and W1=%.2f"%(w[0], w[1])
xx = np.linspace(-12, 34)
yy = a*xx-model.intercept_[0]/w[1]
plt.plot(xx,yy, label ="logistic decision boundary")
clf_lda = LinearDiscriminantAnalysis()
clf_lda.fit(X, Y)
w = clf_lda.coef_[0]
a = -w[0]/w[1]
print "Weights LDA W0=%.2f and W1=%.2f"%(w[0], w[1])
xx = np.linspace(-12, 34)
yy = a*xx-clf_lda.intercept_[0]/w[1]
plt.plot(xx,yy, color="blue", label ="LDA decision boundary")
# plt.scatter(X[:,0], X[:,1], c=Y)
# print clf.support_vectors_[:, 0]
# print clf.support_vectors_[:, 1]
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=80, color='b')
plt.scatter(X[:, 0], X[:, 1], c=Y)#, cmap=plt.cm.Paired
plt.xlabel('X1', fontsize=18)
plt.ylabel('X2', fontsize=16)
plt.axis('tight')
plt.legend()
plt.show()
# print clf.predict([.5, .7])
def high_dimensional():
df_tr = pd.read_csv(path+"P4_train.txt", header=None)
df_te = pd.read_csv(path+"P4_test.txt", header=None)
columns_ls = []
for column in df_tr.columns:
columns_ls.append(column)
X_train = df_tr[columns_ls[0:len(columns_ls)-1]].values
y_train = df_tr[columns_ls[len(columns_ls)-1]].values
X_test = df_te[columns_ls[0:len(columns_ls)-1]].values
y_test = df_te[columns_ls[len(columns_ls)-1]].values
C_range = np.arange(.01, 1., .2)
gamma_range = np.arange(.1, 1., .2)
kern = ['poly']
param_grid = dict(gamma=gamma_range, C=C_range, kernel=kern)
grid = GridSearchCV(svm.SVC(), param_grid=param_grid,cv=None)
grid.fit(X_train, y_train)
print("The best parameters are %s with a score of %0.2f"
% (grid.best_params_, grid.best_score_))
y_pred = grid.predict(X_test)
accScore = accuracy_score(y_test, y_pred)
print ("Accuracy score for Quadratic Kernel is %.2f"%(accScore))
kern_rbf = ['rbf']
param_grid_rbf = dict(gamma=gamma_range, C=C_range, kernel=kern_rbf)
grid_rbf = GridSearchCV(svm.SVC(), param_grid=param_grid_rbf, cv=5)
grid_rbf.fit(X_train, y_train)
#
print("The best parameters are %s with a score of %0.2f"
% (grid_rbf.best_params_, grid_rbf.best_score_))
y_pred_rbf = grid_rbf.predict(X_test)
accScoreRbf = accuracy_score(y_test, y_pred_rbf)
print ("Accuracy score for Guassian Kernel is %.2f"%(accScoreRbf))
k = range(1,10,1)
parameter = {'n_neighbors': k}
knn = KNeighborsClassifier()
knn_clf = GridSearchCV(knn, parameter, cv=5)
knn_clf.fit(X_train, y_train)
print("The best parameters for knn %s with a score of %0.2f"
% (knn_clf.best_params_, knn_clf.best_score_))
knn_y_pred = knn_clf.predict(X_test)
knn_accScore = accuracy_score(y_test, knn_y_pred)
print ("Accuracy score for KNN is %.2f"%(knn_accScore))
def plot_linear_svm_only(filename, title, filename_fig):
df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
# df = pd.read_csv(path+"P3_outliar.txt", names=['x1','x2','y'], header=None)
fig = plt.figure()
fig.suptitle(title, fontsize=20)
columns_ls = []
for column in df.columns:
columns_ls.append(column)
X = df[columns_ls[0:len(columns_ls)-1]].values
# X1 =df[columns_ls[0]].values
#
#
# X2 = df[columns_ls[1]].values
# print np.min(X1), np.max(X1)
# print np.min(X2), np.max(X2)
Y = df[columns_ls[len(columns_ls)-1]].values
clf = svm.SVC(kernel='linear')
clf.fit(X, Y)
w = clf.coef_[0]
print "Weights W0 %.2f and W1%.2f"%(w[0], w[1])
a = -w[0]/w[1]
xx =np.linspace(-12, 34)
yy = a*xx-clf.intercept_[0]/w[1]
# plot the parallels to the separating hyperplane that pass through the
# support vectors
b = clf.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = clf.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])
# plot the line, the points, and the nearest vectors to the plane
# plt.plot(xx, yy, 'k-')
plt.text(0, 10, "Y=+1", fontsize=12)
plt.text(10, 0, "Y=-1", fontsize=12)
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.plot(xx,yy,color="black", label ="svm decision boundary")
plt.xlabel('X1', fontsize=18)
plt.ylabel('X2', fontsize=16)
# fig.savefig(filename_fig)
# model = LogisticRegression()
# model.fit(X, Y)
# w = model.coef_[0]
# a = -w[0]/w[1]
#
# xx = np.linspace(-12, 34)
# yy = a*xx-model.intercept_[0]/w[1]
#
# plt.plot(xx,yy, label ="logistic decision boundary")
#
# clf_lda = LinearDiscriminantAnalysis()
# clf_lda.fit(X, Y)
# w = clf_lda.coef_[0]
# a = -w[0]/w[1]
#
# xx = np.linspace(-12, 34)
# yy = a*xx-clf_lda.intercept_[0]/w[1]
# plt.plot(xx,yy, color="blue", label ="LDA decision boundary")
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=80, color='b')
plt.scatter(X[:, 0], X[:, 1], c=Y)
plt.axis('tight')
plt.legend()
plt.show()
def plot_lda_only(filename, title, filename_fig):
df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
fig = plt.figure()
fig.suptitle(title, fontsize=20)
columns_ls = []
for column in df.columns:
columns_ls.append(column)
X = df[columns_ls[0:len(columns_ls)-1]].values
Y = df[columns_ls[len(columns_ls)-1]].values
clf_lda = LinearDiscriminantAnalysis()
clf_lda.fit(X, Y)
w = clf_lda.coef_[0]
a = -w[0]/w[1]
xx = np.linspace(-12, 34)
yy = a*xx-clf_lda.intercept_[0]/w[1]
plt.plot(xx,yy, color="blue", label ="LDA decision boundary")
print "Weights W0 %.2f and W1%.2f"%(w[0], w[1])
plt.text(0, 0, "Y=+1", fontsize=12)
plt.text(10, -20, "Y=-1", fontsize=12)
# plt.plot(xx, yy_down, 'k--')
# plt.plot(xx, yy_up, 'k--')
# plt.plot(xx,yy,color="black", label ="svm decision boundary")
plt.xlabel('X1', fontsize=18)
plt.ylabel('X2', fontsize=16)
# fig.savefig(filename_fig)
# model = LogisticRegression()
# model.fit(X, Y)
# w = model.coef_[0]
# a = -w[0]/w[1]
#
# xx = np.linspace(-12, 34)
# yy = a*xx-model.intercept_[0]/w[1]
#
# plt.plot(xx,yy, label ="logistic decision boundary")
#
# clf_lda = LinearDiscriminantAnalysis()
# clf_lda.fit(X, Y)
# w = clf_lda.coef_[0]
# a = -w[0]/w[1]
#
# xx = np.linspace(-12, 34)
# yy = a*xx-clf_lda.intercept_[0]/w[1]
# plt.plot(xx,yy, color="blue", label ="LDA decision boundary")
# plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
# s=80, color='b')
plt.scatter(X[:, 0], X[:, 1], c=Y)
plt.axis('tight')
plt.legend()
plt.show()
def plot_svm_logistic(filename, title):
df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
columns_ls = []
for column in df.columns:
columns_ls.append(column)
X = df[columns_ls[0:len(columns_ls)-1]].values
Y = df[columns_ls[len(columns_ls)-1]].values
fig = plt.figure()
fig.suptitle(title, fontsize=20)
clf = svm.SVC(kernel='linear')
clf.fit(X, Y)
w = clf.coef_[0]
print "Weights of SVM W0 = %.2f and W1 = %.2f"%(w[0], w[1])
a = -w[0]/w[1]
xx =np.linspace(-12, 34)
yy = a*xx-clf.intercept_[0]/w[1]
# plot the parallels to the separating hyperplane that pass through the
# support vectors
b = clf.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = clf.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])
plt.text(0, 10, "Y=+1", fontsize=12)
plt.text(10, 0, "Y=-1", fontsize=12)
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.plot(xx,yy,color="black", label ="svm decision boundary")
model = LogisticRegression()
model.fit(X, Y)
w = model.coef_[0]
a = -w[0]/w[1]
print "Weights of Logistic regression W0 = %.2f and W1 = %.2f"%(w[0], w[1])
xx = np.linspace(-12, 34)
yy = a*xx-model.intercept_[0]/w[1]
plt.plot(xx,yy, label ="logistic decision boundary")
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=80, color='b')
plt.scatter(X[:, 0], X[:, 1], c=Y)
plt.xlabel('X1', fontsize=18)
plt.ylabel('X2', fontsize=16)
plt.axis('tight')
plt.legend()
plt.show()
# print clf.predict([.5, .7])
def plot_linear_svm_lda(filename, title):
df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
columns_ls = []
for column in df.columns:
columns_ls.append(column)
X = df[columns_ls[0:len(columns_ls)-1]].values
Y = df[columns_ls[len(columns_ls)-1]].values
fig = plt.figure()
fig.suptitle(title, fontsize=20)
clf = svm.SVC(kernel='linear')
clf.fit(X, Y)
w = clf.coef_[0]
print "Weights SVM W0=%.2f and W1=%.2f"%(w[0], w[1])
a = -w[0]/w[1]
xx =np.linspace(-12, 34)
yy = a*xx-clf.intercept_[0]/w[1]
b = clf.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = clf.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])
# plot the line, the points, and the nearest vectors to the plane
# plt.plot(xx, yy, 'k-')
plt.text(0, 10, "Y=+1", fontsize=12)
plt.text(10, 0, "Y=-1", fontsize=12)
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.plot(xx,yy,color="black", label ="svm decision boundary")
clf_lda = LinearDiscriminantAnalysis()
clf_lda.fit(X, Y)
w = clf_lda.coef_[0]
a = -w[0]/w[1]
print "Weights LDA W0=%.2f and W1=%.2f"%(w[0], w[1])
xx = np.linspace(-12, 34)
yy = a*xx-clf_lda.intercept_[0]/w[1]
plt.plot(xx,yy, color="blue", label ="LDA decision boundary")
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=80, color='b')
plt.scatter(X[:, 0], X[:, 1], c=Y)
plt.xlabel('X1', fontsize=18)
plt.ylabel('X2', fontsize=16)
plt.axis('tight')
plt.legend()
plt.show()
plot_linear_svm_only("P3.txt", "Linear SVM", "Linear_SVM.jpg")
plot_linear_svm_only("P3_outliar.txt", "Linear SVM with outlier", "Linear_SVM_outlier.jpg")
plot_lda_only("P3.txt", "LDA classifier", "LDA_SVM.jpg")
plot_lda_only("P3_outliar.txt", "LDA Classifier With Outliers", "LDA_SVM.jpg")
plot_linear_svm_lda("P3.txt", "SVM with LDA comparision")
plot_linear_svm_lda("P3_outliar.txt", "SVM vs LDA with Outliers")
plot_svm_logistic("P3.txt", "SVM vs Logistic Regression")
plot_svm_logistic("P3_outliar.txt", "SVM vs Logistic Regression with Outliers")
plot_linear_svm("P3.txt", "SVM vs Logistic vs LDA")
plot_linear_svm("P3_outliar.txt", "SVM vs Logistic vs LDA with Outlier")
high_dimensional()