kddcup2017/utils.py at master · Engineering-Course/kddcup2017 · GitHub

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
import tensorflow as tf
import numpy as np
import os

def load_train_travel_data(batch_files, window):
    x_ = []
    y_ = []
    for id_ in xrange(len(batch_files)):
        filename = 'dataset/dataSets/data_training/travel_{}_{}.txt'.format(window, batch_files[id_][:-1])
        with open(filename, 'r') as fr:
            line_ = fr.readline()
        data_ = line_.split(' ')
        item_x = [float(tt) for tt in data_]
        item_y = [item_x[window+1]]
        del item_x[window+1]
        x_.append(item_x)
        y_.append(item_y)

    return np.array(x_), np.array(y_)


def load_test_travel_data(batch_id):
    x_ = []
    filename = 'dataset/dataSets/testing_six/travel_{}.txt'.format(batch_id)
    with open(filename, 'r') as fr:
        line_ = fr.readline()
    data_ = line_.split(' ')
    item_x = [float(tt) for tt in data_]
    x_.append(item_x)

    return np.array(x_)


def load_train_zero_data(batch_files, window):
    x_ = []
    y_ = []
    for id_ in xrange(len(batch_files)):
        filename = 'dataset/dataSets/{}_data_zero_training/travel_{}.txt'.format(window, batch_files[id_][:-1])
        with open(filename, 'r') as fr:
            line_ = fr.readline()
        data_ = line_.split(' ')
        item_x = [float(tt) for tt in data_]
        item_y = [item_x[window+1]]
        del item_x[window+1]
        x_.append(item_x)
        y_.append(item_y)

    return np.array(x_), np.array(y_)

def save(saver, sess, logdir, step):
    '''Save weights.
    Args:
     saver: TensorFlow Saver object.
     sess: TensorFlow session.
     logdir: path to the snapshots directory.
     step: current training step.
    '''
    if not os.path.exists(logdir):
        os.makedirs(logdir)
    model_name = 'model.ckpt'
    checkpoint_path = os.path.join(logdir, model_name)

    if not os.path.exists(logdir):
      os.makedirs(logdir)
    saver.save(sess, checkpoint_path, global_step=step)
    #print('The checkpoint has been created.')

def load(saver, sess, ckpt_path):
    '''Load trained weights.

    Args:
      saver: TensorFlow saver object.
      sess: TensorFlow session.
      ckpt_path: path to checkpoint file with parameters.
    '''
    ckpt = tf.train.get_checkpoint_state(ckpt_path)
    if ckpt and ckpt.model_checkpoint_path:
        ckpt_name = os.path.basename(ckpt.model_checkpoint_path)
        saver.restore(sess, os.path.join(ckpt_path, ckpt_name))
        print("Restored model parameters from {}".format(ckpt_name))
        return True
    else:
        return False


#
#def load_train_travel_data_six(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_6_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_6_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[7]]
#        del item_x[7]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)
#
#def load_train_travel_data_five(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_5_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_5_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[6]]
#        del item_x[6]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)
#
#def load_train_travel_data_four(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_4_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_4_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[5]]
#        del item_x[5]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)
#
#def load_train_travel_data_three(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_3_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_3_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[4]]
#        del item_x[4]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)
#
#def load_train_travel_data_two(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_2_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_2_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[3]]
#        del item_x[3]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)
#
#def load_train_travel_data_one(idx, BATCH_SIZE):
#    x_ = []
#    y_ = []
#    ID_FILE = 'dataset/dataSets/train_1_id.txt'
#    with open(ID_FILE, 'r') as list_file:
#        data_list = list_file.readlines()
#    batch_files = data_list[idx*BATCH_SIZE:(idx+1)*BATCH_SIZE]
#    for id_ in xrange(len(batch_files)):
#        filename = 'dataset/dataSets/multi_train_data/travel_1_{}.txt'.format(batch_files[id_][:-1])
#        with open(filename, 'r') as fr:
#            line_ = fr.readline()
#        data_ = line_.split(' ')
#        item_x = [float(tt) for tt in data_]
#        item_y = [item_x[2]]
#        del item_x[2]
#        x_.append(item_x)
#        y_.append(item_y)
#    return np.array(x_), np.array(y_)