-
Notifications
You must be signed in to change notification settings - Fork 2
/
all_models.py
355 lines (305 loc) · 13.6 KB
/
all_models.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
import pandas as pd
import numpy as np
import warnings
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, f1_score, confusion_matrix, average_precision_score, \
r2_score, mean_squared_error
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.linear_model import SGDClassifier, PassiveAggressiveClassifier, RidgeClassifier, \
LinearRegression, RANSACRegressor, ARDRegression, HuberRegressor, LogisticRegression, \
LogisticRegressionCV, SGDRegressor, TheilSenRegressor, PassiveAggressiveRegressor
from sklearn.neural_network import MLPClassifier, MLPRegressor
from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier, RandomForestClassifier, \
RandomForestRegressor, AdaBoostRegressor, BaggingRegressor
from sklearn import svm
from xgboost import XGBClassifier, XGBRegressor
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis, LinearDiscriminantAnalysis
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier, DecisionTreeRegressor, \
ExtraTreeRegressor
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
from lightgbm import LGBMClassifier, LGBMRegressor
warnings.filterwarnings("ignore", category=FutureWarning)
np.random.seed(3)
# Overview
# This code contains different classification adn regression models
class ClassificationModels:
def __init__(self, data, label):
self.data = data
self.label = label
# Label encoding the target values.
def preprocessing(self):
x = self.data
y = self.label
lb = LabelEncoder()
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=0,
shuffle=True)
lb.fit(list(y_train))
y_test = lb.transform(y_test)
y_train = lb.transform(y_train)
y_train = np.array(y_train)
y_test = np.array(y_test)
return x_train, x_test, y_train, y_test
def printing(self, y_test, y_pred, name):
acc = accuracy_score(y_test, y_pred)
print('{} Classifier:- {}%'.format(name, round(acc * 100, 4)))
conf = confusion_matrix(y_test, y_pred)
f1 = f1_score(y_test, y_pred, average='micro')
print('{} f1 score- {}'.format(name, round(f1, 4)))
print('{} confusion matrix: \n{}'.format(name, conf))
# bagging classifier
def bag(self):
x_train, x_test, y_train, y_test = self.preprocessing()
classifier = BaggingClassifier()
y_pred = classifier.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Bagging')
# Light GBM classifier
def lgbm(self):
x_train, x_test, y_train, y_test = self.preprocessing()
classifier = LGBMClassifier()
y_pred = classifier.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Light GBM')
# XG boost classifier
def xg(self):
x_train, x_test, y_train, y_test = self.preprocessing()
classifier = XGBClassifier()
y_pred = classifier.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'XG Boost')
# Ridge classifier
def ridge(self):
x_train, x_test, y_train, y_test = self.preprocessing()
classifier = RidgeClassifier()
y_pred = classifier.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Ridge')
# Passive aggressive classifer
def passive(self):
x_train, x_test, y_train, y_test = self.preprocessing()
classifier = PassiveAggressiveClassifier()
y_pred = classifier.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Passive')
# Extra tree classifier
def extra_tree(self):
x_train, x_test, y_train, y_test = self.preprocessing()
extra_tree_model = ExtraTreeClassifier()
y_pred = extra_tree_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Extra Tree')
# Gaussian
def gauss_model(self):
x_train, x_test, y_train, y_test = self.preprocessing()
gaussian_model = GaussianNB()
y_pred = gaussian_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Gaussian')
# Binomial
def bino_model(self):
x_train, x_test, y_train, y_test = self.preprocessing()
binomial_model = BernoulliNB()
y_pred = binomial_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Binomial')
# Multinomial
def multi_model(self):
x_train, x_test, y_train, y_test = self.preprocessing()
multinomial_model = MultinomialNB()
y_pred = multinomial_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Multinomial')
# Stochastic gradient descent
def stoc_model(self):
x_train, x_test, y_train, y_test = self.preprocessing()
stochastic_model = SGDClassifier(loss='modified_huber', shuffle=True, random_state=101,
max_iter=1000)
y_pred = stochastic_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Stochastic Gradient Descent')
# Decision tree
def dec_tree(self):
x_train, x_test, y_train, y_test = self.preprocessing()
dt_model = DecisionTreeClassifier(criterion='entropy', min_samples_leaf=7)
y_pred = dt_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Decision Tree')
# Random Forest
def rand_forest(self):
x_train, x_test, y_train, y_test = self.preprocessing()
rf_model = RandomForestClassifier(n_jobs=2, criterion='entropy', n_estimators=55,
random_state=23)
y_pred = rf_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Random Forest')
# K nearest neighbors
def k_nearest(self):
x_train, x_test, y_train, y_test = self.preprocessing()
knn = KNeighborsClassifier(n_neighbors=5)
y_pred = knn.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'KNN')
# logistic regression
def log_reg(self):
x_train, x_test, y_train, y_test = self.preprocessing()
lr = LogisticRegression(C=0.50, multi_class='ovr', max_iter=10000, solver='lbfgs')
y_pred = lr.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Logistic Regression')
# SVM with linear kernel
def svm_linear(self):
x_train, x_test, y_train, y_test = self.preprocessing()
svL = svm.SVC(kernel='linear', gamma='auto')
y_pred = svL.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'SVM Linear')
# SVM with rbf kernel
def svm_rbf(self):
x_train, x_test, y_train, y_test = self.preprocessing()
svR = svm.SVC(kernel='rbf', gamma='auto')
y_pred = svR.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'SVM RBF')
# SVM with poly kernel
def svm_poly(self):
x_train, x_test, y_train, y_test = self.preprocessing()
svP = svm.SVC(kernel='poly', gamma='auto')
y_pred = svP.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'SVM Poly')
# Adaboost
def adaboost_model(self):
x_train, x_test, y_train, y_test = self.preprocessing()
ada_model = AdaBoostClassifier()
y_pred = ada_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Adaboost')
# MultiLayer perceptron
def mlpc_nn(self):
x_train, x_test, y_train, y_test = self.preprocessing()
mlpc_model = MLPClassifier()
y_pred = mlpc_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'mlpc')
# Quadratic Discriminant Analysis
def qda(self):
x_train, x_test, y_train, y_test = self.preprocessing()
QDA_model = QuadraticDiscriminantAnalysis()
y_pred = QDA_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'QDA')
# Linear Discriminant Analysis
def lda(self):
x_train, x_test, y_train, y_test = self.preprocessing()
LDA_model = LinearDiscriminantAnalysis()
y_pred = LDA_model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'LDA')
class RegressionModels:
def __init__(self, data, label):
self.data = data
self.label = label
def preprocessing(self):
x = self.data
y = self.label
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=0,
shuffle=True)
y_train = np.array(y_train)
y_test = np.array(y_test)
return x_train, x_test, y_train, y_test
def printing(self, y_test, y_pred, name):
mape = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
print('{} RMSE- {}'.format(name, round(rmse, 4)))
print('{} MAPE- {}%'.format(name, round(mape, 4)))
r2 = r2_score(y_test, y_pred)
print('{} R2 Score- {}'.format(name, round(r2, 4)))
# Adaboost
def adaboost_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = AdaBoostRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Adaboost')
# Linear
def linear_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = LinearRegression()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Linear Regression')
# Stochastic
def sgd_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = SGDRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Stochastic Gradient Descent')
# Decision Tree
def dec_tree_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = DecisionTreeRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Decision Tree')
# Random Forest
def random_forest_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = RandomForestRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Random Forest')
# RANSAC
def ransac_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = RANSACRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'RANSAC')
# ARD
def ard_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = ARDRegression()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'ARD')
# Huber
def huber_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = HuberRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Huber')
# Theilsen
def theilsen_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = TheilSenRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Theilsen')
# Passive Aggressive
def passive_aggressive_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = PassiveAggressiveRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Passive Aggressive')
# MLP
def mlp_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = MLPRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Multi Layer Perceptron')
# Bagging
def bagging_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = BaggingRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Bagging')
# XG Boost
def xgb_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = XGBRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'XG Boost')
# Light GBM
def lgb_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = LGBMRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Light GBM')
# KNN
def knn_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = KNeighborsRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'KNN')
# Extra Tree
def extra_tree_regressor(self):
x_train, x_test, y_train, y_test = self.preprocessing()
model = ExtraTreeRegressor()
y_pred = model.fit(x_train, y_train).predict(x_test)
self.printing(y_test, y_pred, 'Extra Tree')
if __name__ == '__main__':
# from sklearn import datasets
#
# bh = datasets.load_iris()
# data = bh.data
# labels = bh.target
# obj = ClassificationModels(data, labels)
# obj.dec_tree()
# obj.rand_forest()
# obj.lgbm()
# obj.gauss_model()