forked from andresantonioriveros/pyRF
/
parallel.py
283 lines (205 loc) · 9.89 KB
/
parallel.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
# coding=utf-8
# Métodos para paralelizar
# -------------------------------------------------------------------------------------------------
import pandas as pd
from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
import tree
import utils
import metrics
def train_tree(path, feature_filter=None, train_index=None):
data = pd.read_csv(path, index_col=0)
data, y = utils.filter_data(data, feature_filter=feature_filter)
train_X = data.iloc[train_index]
train_y = y.iloc[train_index]
clf = None
clf = tree.Tree('gain', max_depth=10, min_samples_split=20)
clf.fit(train_X, train_y)
return clf
def fit_montecarlo_tree(path_index, paths = None, index_filter=None, class_filter=None,
feature_filter=None, folds=10):
"""A diferencia de fit tree, este metodo recibe todos los paths. Entrena solo con uno, indicado
por path index. Pero luego por orden, voy abriendo todos los sets para clasificar.
"""
data = pd.read_csv(paths[path_index], index_col=0)
data, y = utils.filter_data(data, index_filter, class_filter, feature_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
for train_index, test_index in skf:
train_X = data.iloc[train_index]
train_y = y.iloc[train_index]
clf = None
clf = tree.Tree('gain', max_depth=10, min_samples_split=20)
clf.fit(train_X, train_y)
# result = clf.predict_table(test_X, test_y)
# results.append(result)
# Ahora clasifico con este arbol para todos los datasets
for path in paths:
data = pd.read_csv(path, index_col=0)
data, y = utils.filter_data(data, index_filter, class_filter, feature_filter)
return pd.concat(results)
def fit_tree(path, index_filter=None, class_filter=None, feature_filter=None, folds=10,
inverse=False, max_depth=10, min_samples_split=20, lc_filter=None):
"""
path: Dirección del dataset a ocupar para entrenar
index_filter: Pandas index para filtrar las filas del dataset que se quieren utilizar
class_filter: Lista de clases que se quiere utilizar
feature_filter: Lista de features que se quiere utilizar
"""
data = pd.read_csv(path, index_col=0)
data, y = utils.filter_data(data, index_filter, class_filter, feature_filter, lc_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
for train_index, test_index in skf:
if inverse:
aux = train_index
train_index = test_index
test_index = aux
train_X, test_X = data.iloc[train_index], data.iloc[test_index]
train_y, test_y = y.iloc[train_index], y.iloc[test_index]
clf = None
clf = tree.Tree('gain', max_depth=max_depth, min_samples_split=min_samples_split)
clf.fit(train_X, train_y)
results.append(clf.predict_table(test_X, test_y))
return pd.concat(results)
def fit_sktree(path, index_filter=None, class_filter=None, feature_filter=None, folds=10,
inverse=False, max_depth=10, min_samples_split=20, lc_filter=None):
data = pd.read_csv(path, index_col=0)
data, y = utils.filter_data(data, index_filter, class_filter, feature_filter, lc_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
for train_index, test_index in skf:
if inverse:
aux = train_index
train_index = test_index
test_index = aux
train_X, test_X = data.iloc[train_index], data.iloc[test_index]
train_y, test_y = y.iloc[train_index], y.iloc[test_index]
clf = None
clf = DecisionTreeClassifier(criterion='entropy', max_depth=max_depth,
min_samples_split=min_samples_split)
clf.fit(train_X, train_y)
results.append(metrics.predict_table(clf, test_X, test_y))
return pd.concat(results)
def fit_rf(path, index_filter=None, class_filter=None, feature_filter=None, folds=10,
inverse=False, lc_filter=None):
"""
path: Dirección del dataset a ocupar para entrenar
index_filter: Pandas index para filtrar las filas del dataset que se quieren utilizar
class_filter: Lista de clases que se quiere utilizar
feature_filter: Lista de features que se quiere utilizar
"""
data = pd.read_csv(path, index_col=0)
data, y = utils.filter_data(data, index_filter, class_filter, feature_filter, lc_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
for train_index, test_index in skf:
if inverse:
aux = train_index
train_index = test_index
test_index = aux
train_X, test_X = data.iloc[train_index], data.iloc[test_index]
train_y, test_y = y.iloc[train_index], y.iloc[test_index]
clf = None
clf = RandomForestClassifier(n_estimators=100, criterion='entropy', max_depth=14,
min_samples_split=5)
clf.fit(train_X, train_y)
results.append(metrics.predict_table(clf, test_X, test_y))
return pd.concat(results)
def fit_means_tree(train_path, test_path, index_filter=None, class_filter=None, feature_filter=None, folds=10):
"""
train_path: Dirección del dataset a ocupar para entrenar
test_path: Dirección del dataset a ocupar para testear
index_filter: Pandas index para filtrar las filas del dataset que se quieren utilizar
class_filter: Lista de clases que se quiere utilizar
feature_filter: Lista de features que se quiere utilizar
"""
train_data = pd.read_csv(train_path, index_col=0)
test_data = pd.read_csv(test_path, index_col=0)
# Elimino curvas que estan repetidas
test_data = utils.remove_duplicate_index(test_data)
train_data = utils.remove_duplicate_index(train_data)
if index_filter:
train_data = train_data.loc[index_filter]
test_data = test_data.loc[index_filter]
if class_filter:
train_data = train_data[train_data['class'].apply(lambda x: True if x in class_filter else False)]
test_data = test_data[test_data['class'].apply(lambda x: True if x in class_filter else False)]
train_data = train_data.dropna(axis=0, how='any')
test_data = test_data.dropna(axis=0, how='any')
# Me aseguro que los datasets sean de los mismos datos
common_index = list(set(test_data.index.tolist()) & set(train_data.index.tolist()))
test_data = test_data.loc[common_index]
train_data = train_data.loc[common_index]
train_data = train_data.sort_index()
test_data = test_data.sort_index()
# Separo features de las clases
train_y = train_data['class']
train_X = train_data.drop('class', axis=1)
test_y = test_data['class']
test_X = test_data.drop('class', axis=1)
if feature_filter:
train_X = train_X[feature_filter]
test_X = test_X[feature_filter]
skf = cross_validation.StratifiedKFold(train_y, n_folds=folds)
results = []
for train_index, test_index in skf:
fold_train_X = train_X.iloc[train_index]
fold_train_y = train_y.iloc[train_index]
fold_test_X = test_X.iloc[test_index]
fold_test_y = test_y.iloc[test_index]
clf = None
clf = tree.Tree('gain', max_depth=10, min_samples_split=20)
clf.fit(fold_train_X, fold_train_y)
result = clf.predict_table(fold_test_X, fold_test_y)
results.append(result)
return pd.concat(results)
def fit_means_rf(train_path, test_path, index_filter=None, class_filter=None, feature_filter=None, folds=10):
"""
train_path: Dirección del dataset a ocupar para entrenar
test_path: Dirección del dataset a ocupar para testear
index_filter: Pandas index para filtrar las filas del dataset que se quieren utilizar
class_filter: Lista de clases que se quiere utilizar
feature_filter: Lista de features que se quiere utilizar
"""
train_data = pd.read_csv(train_path, index_col=0)
test_data = pd.read_csv(test_path, index_col=0)
# Elimino curvas que estan repetidas
test_data = utils.remove_duplicate_index(test_data)
train_data = utils.remove_duplicate_index(train_data)
if index_filter:
train_data = train_data.loc[index_filter]
test_data = test_data.loc[index_filter]
if class_filter:
train_data = train_data[train_data['class'].apply(lambda x: True if x in class_filter else False)]
test_data = test_data[test_data['class'].apply(lambda x: True if x in class_filter else False)]
train_data = train_data.dropna(axis=0, how='any')
test_data = test_data.dropna(axis=0, how='any')
# Me aseguro que los datasets sean de los mismos datos
common_index = list(set(test_data.index.tolist()) & set(train_data.index.tolist()))
test_data = test_data.loc[common_index]
train_data = train_data.loc[common_index]
train_data = train_data.sort_index()
test_data = test_data.sort_index()
# Separo features de las clases
train_y = train_data['class']
train_X = train_data.drop('class', axis=1)
test_y = test_data['class']
test_X = test_data.drop('class', axis=1)
if feature_filter:
train_X = train_X[feature_filter]
test_X = test_X[feature_filter]
skf = cross_validation.StratifiedKFold(train_y, n_folds=folds)
results = []
for train_index, test_index in skf:
fold_train_X = train_X.iloc[train_index]
fold_train_y = train_y.iloc[train_index]
fold_test_X = test_X.iloc[test_index]
fold_test_y = test_y.iloc[test_index]
clf = None
clf = RandomForestClassifier(n_estimators=100, criterion='entropy', max_depth=14,
min_samples_split=5)
clf.fit(fold_train_X, fold_train_y)
results.append(metrics.predict_table(clf, fold_test_X, fold_test_y))
return pd.concat(results)