-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathclassification.py
More file actions
240 lines (186 loc) · 8.09 KB
/
classification.py
File metadata and controls
240 lines (186 loc) · 8.09 KB
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
#
# Copyright 2019 GridGain Systems, Inc. and Contributors.
#
# Licensed under the GridGain Community Edition License (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.gridgain.com/products/software/community-edition/gridgain-community-edition-license
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Decision Tree classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import DecisionTreeClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = DecisionTreeClassificationTrainer()
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# Decision Tree classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import DecisionTreeClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = DecisionTreeClassificationTrainer()
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# ANN classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import ANNClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = ANNClassificationTrainer()
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# ANN classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import ANNClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = ANNClassificationTrainer()
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# KNN classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import KNNClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = KNNClassificationTrainer()
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# KNN classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import KNNClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = KNNClassificationTrainer()
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# LogReg classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import LogRegClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = LogRegClassificationTrainer()
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# LogReg classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import LogRegClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = LogRegClassificationTrainer()
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# SVM classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import SVMClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = SVMClassificationTrainer()
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# SVM classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import SVMClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = SVMClassificationTrainer()
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# Random Forest classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.classification import RandomForestClassificationTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
trainer = RandomForestClassificationTrainer(features=20)
model = trainer.fit(x_train, y_train)
accuracy_score(y_test, model.predict(x_test))
# Random Forest classification with Ignite ML (cache).
import numpy as np
from sklearn.datasets import make_classification
from ggml.core import Ignite
from ggml.model_selection import train_test_split
from ggml.metrics import accuracy_score
from ggml.classification import RandomForestClassificationTrainer
with Ignite("example-ignite.xml") as ignite:
cache = ignite.create_cache("my-cache")
for i, row in enumerate(np.column_stack(make_classification())):
cache.put(i, row)
train_cache, test_cache = train_test_split(cache)
trainer = RandomForestClassificationTrainer(features=20)
model = trainer.fit(train_cache)
print(accuracy_score(test_cache, model))
# MLP classification with Ignite ML (local).
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from ggml.regression import MLPArchitecture
from ggml.regression import MLPRegressionTrainer
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
def encode_label(x):
if x:
return [0, 1]
else:
return [1, 0]
def decode_label(x):
if x[0] > x[1]:
return 0
else:
return 1
trainer = MLPRegressionTrainer(MLPArchitecture(input_size=20).with_layer(neurons=2, activator='sigmoid'))
model = trainer.fit(x_train, [encode_label(x) for x in y_train])
accuracy_score(y_test, [decode_label(x) for x in model.predict(x_test)])