-
Notifications
You must be signed in to change notification settings - Fork 3
/
augument.py
180 lines (150 loc) · 6.04 KB
/
augument.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
import argparse
import numpy as np
import pandas as pd
from library.constants import *
from library.helper import scale
from library.models.rnn import RNN
from library.models.rf import RandomForest,OldRandomForest
from library.utils import read_dataset_from_files,read_csv
parser = argparse.ArgumentParser(description='Training for different experiments with rf and rnn')
parser.add_argument('--restore', help='Required decision to restore weights',action='store_true')
args = parser.parse_args()
restore=args.restore
#----------------------------------------------------------------------------------------
#Durgapur
test_set=['./Data/Dgp/Device_2_merged.csv',
'./Data/Dgp/Device_3_merged.csv',
'./Data/Dgp/Device_1_merged.csv']
train_set=['./Data/Dgp/Device_4_merged.csv']
#Old Random Forest
dataset=read_dataset_from_files(train_set,old_features,label,window=None)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,old_features,label,window=None)
X_test=test_data["X"].values
y_test=test_data["y"].values
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
model=OldRandomForest()
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=None,batch_size=None)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/dgp_rf_old_aug.csv",index=False)
#Random forest
dataset=read_dataset_from_files(train_set,features,label,window=None)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,features,label,window=None)
X_test=test_data["X"].values
y_test=test_data["y"].values
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
model=RandomForest()
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=None,batch_size=None)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/dgp_rf_aug.csv",index=False)
#RNN
dataset=read_dataset_from_files(train_set,features,label,window=window)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,features,label,window=window)
X_test=test_data["X"]
y_test=test_data["y"]
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
X_train_scaled=X_train_scaled.reshape(-1,window,len(features))
X_test_scaled=X_test_scaled.reshape(-1,window,len(features))
model=RNN(checkpoint_filepath=f'./logs/model/dgp_rnn_aug_{i}',seed=seed,restore=restore)
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=epochs,batch_size=batch_size)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/dgp_rnn_aug.csv",index=False)
#------------------------------------------------------------------------------
#DELHI
test_set=['./Data/Delhi/Device_34_merged.csv',
'./Data/Delhi/Device_35_merged.csv',
'./Data/Delhi/Device_30_merged.csv',
'./Data/Delhi/Device_37_merged.csv',
'./Data/Delhi/Device_33_merged.csv',
'./Data/Delhi/Device_20_merged.csv']
train_set=['./Data/Delhi/Device_23_merged.csv',
'./Data/Delhi/Device_22_merged.csv',
'./Data/Delhi/Device_28_merged.csv',
'./Data/Delhi/Device_24_merged.csv',
'./Data/Delhi/Device_18_merged.csv',
'./Data/Delhi/Device_25_merged.csv']
#Old Random Forest
dataset=read_dataset_from_files(train_set,old_features,label,window=None)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,old_features,label,window=None)
X_test=test_data["X"].values
y_test=test_data["y"].values
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
model=OldRandomForest()
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=None,batch_size=None)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/delhi_rf_old_aug.csv",index=False)
#Random Forest
dataset=read_dataset_from_files(train_set,features,label,window=None)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,features,label,window=None)
X_test=test_data["X"].values
y_test=test_data["y"].values
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
model=RandomForest()
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=None,batch_size=None)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/delhi_rf_aug.csv",index=False)
#RNN
dataset=read_dataset_from_files(train_set,features,label,window=window)
X_train=dataset["X"]
y_train=dataset["y"]
l=[]
for i,f in enumerate(test_set):
print(i,f)
test_data=read_csv(f,features,label,window=window)
X_test=test_data["X"]
y_test=test_data["y"]
X_train_scaled,X_test_scaled,_=scale(X_train,X_test)
X_train_scaled=X_train_scaled.reshape(-1,window,len(features))
X_test_scaled=X_test_scaled.reshape(-1,window,len(features))
model=RNN(checkpoint_filepath=f'./logs/model/delhi_rnn_aug_{i}',seed=seed,restore=restore)
model.train(X_train_scaled,X_test_scaled,y_train,y_test,epochs=epochs,batch_size=batch_size)
l.append(model.metrics)
X_train=np.concatenate([X_train,X_test],axis=0)
annot=model.pred_fn(X_test_scaled)
y_train=np.concatenate([y_train,annot],axis=0)
df=pd.DataFrame(l)
df.to_csv("./logs/exp/delhi_rnn_aug.csv",index=False)