-
Notifications
You must be signed in to change notification settings - Fork 1
/
dataset.py
277 lines (242 loc) · 10.8 KB
/
dataset.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
import numpy as np
import pandas as pd
import lmdb
import torch.utils.data
from tqdm import tqdm
from torch.utils.data import Dataset
import math
import shutil
import struct
from collections import defaultdict
from functools import lru_cache
from pathlib import Path
class Movielens1MDataset(Dataset):
def __init__(self, data_dir='./dataset/ml-1m/train.txt'):
data = pd.read_csv(data_dir, header=None).to_numpy()
self.field = data[:,:-1]
self.label = data[:,-1]
self.field_dims = np.max(self.field, axis=0) + 1
def __len__(self):
return len(self.label)
def __getitem__(self, item):
field = self.field[item]
label = self.label[item]
return field, label
import shutil
import struct
from collections import defaultdict
from pathlib import Path
class AvazuDataset(Dataset):
"""
Avazu Click-Through Rate Prediction Dataset
Dataset preparation
Remove the infrequent features (appearing in less than threshold instances) and treat them as a single feature
:param dataset_path: avazu train path
:param cache_path: lmdb cache path
:param rebuild_cache: If True, lmdb cache is refreshed
:param min_threshold: infrequent feature threshold
Reference
https://www.kaggle.com/c/avazu-ctr-prediction
"""
def __init__(self, dataset_path=None, cache_path='.avazu', rebuild_cache=False, min_threshold=4):
self.NUM_FEATS = 22
self.min_threshold = min_threshold
if rebuild_cache or not Path(cache_path).exists():
shutil.rmtree(cache_path, ignore_errors=True)
if dataset_path is None:
raise ValueError('create cache: failed: dataset_path is None')
self.__build_cache(dataset_path, cache_path)
self.env = lmdb.open(cache_path, create=False, lock=False, readonly=True)
with self.env.begin(write=False) as txn:
self.length = txn.stat()['entries'] - 1
self.field_dims = np.frombuffer(txn.get(b'field_dims'), dtype=np.uint32)
def __getitem__(self, index):
with self.env.begin(write=False) as txn:
np_array = np.frombuffer(
txn.get(struct.pack('>I', index)), dtype=np.uint32).astype(dtype=np.compat.long)
return np_array[1:], np_array[0]
def __len__(self):
return self.length
def __build_cache(self, path, cache_path):
feat_mapper, defaults = self.__get_feat_mapper(path)
with lmdb.open(cache_path, map_size=int(1e11)) as env:
field_dims = np.zeros(self.NUM_FEATS, dtype=np.uint32)
for i, fm in feat_mapper.items():
field_dims[i - 1] = len(fm) + 1
with env.begin(write=True) as txn:
txn.put(b'field_dims', field_dims.tobytes())
for buffer in self.__yield_buffer(path, feat_mapper, defaults):
with env.begin(write=True) as txn:
for key, value in buffer:
txn.put(key, value)
def __get_feat_mapper(self, path):
feat_cnts = defaultdict(lambda: defaultdict(int))
with open(path) as f:
f.readline()
pbar = tqdm(f, mininterval=1, smoothing=0.1)
pbar.set_description('Create avazu dataset cache: counting features')
for line in pbar:
values = line.rstrip('\n').split(',')
if len(values) != self.NUM_FEATS + 2:
continue
for i in range(1, self.NUM_FEATS + 1):
feat_cnts[i][values[i + 1]] += 1
feat_mapper = {i: {feat for feat, c in cnt.items() if c >= self.min_threshold} for i, cnt in feat_cnts.items()}
feat_mapper = {i: {feat: idx for idx, feat in enumerate(cnt)} for i, cnt in feat_mapper.items()}
defaults = {i: len(cnt) for i, cnt in feat_mapper.items()}
return feat_mapper, defaults
def __yield_buffer(self, path, feat_mapper, defaults, buffer_size=int(1e5)):
item_idx = 0
buffer = list()
with open(path) as f:
f.readline()
pbar = tqdm(f, mininterval=1, smoothing=0.1)
pbar.set_description('Create avazu dataset cache: setup lmdb')
for line in pbar:
values = line.rstrip('\n').split(',')
if len(values) != self.NUM_FEATS + 2:
continue
np_array = np.zeros(self.NUM_FEATS + 1, dtype=np.uint32)
np_array[0] = int(values[1])
for i in range(1, self.NUM_FEATS + 1):
np_array[i] = feat_mapper[i].get(values[i+1], defaults[i])
buffer.append((struct.pack('>I', item_idx), np_array.tobytes()))
item_idx += 1
if item_idx % buffer_size == 0:
yield buffer
buffer.clear()
yield buffer
class CriteoDataset(Dataset):
"""
Criteo Display Advertising Challenge Dataset
Data prepration:
* Remove the infrequent features (appearing in less than threshold instances) and treat them as a single feature
* Discretize numerical values by log2 transformation which is proposed by the winner of Criteo Competition
:param dataset_path: criteo train.txt path.
:param cache_path: lmdb cache path.
:param rebuild_cache: If True, lmdb cache is refreshed.
:param min_threshold: infrequent feature threshold.
Reference:
https://labs.criteo.com/2014/02/kaggle-display-advertising-challenge-dataset
https://www.csie.ntu.edu.tw/~r01922136/kaggle-2014-criteo.pdf
"""
def __init__(self, dataset_path=None, cache_path='.criteo', rebuild_cache=False, min_threshold=10):
self.NUM_FEATS = 39
self.NUM_INT_FEATS = 13
self.min_threshold = min_threshold
if rebuild_cache or not Path(cache_path).exists():
shutil.rmtree(cache_path, ignore_errors=True)
if dataset_path is None:
raise ValueError('create cache: failed: dataset_path is None')
self.__build_cache(dataset_path, cache_path)
self.env = lmdb.open(cache_path, create=False, lock=False, readonly=True)
with self.env.begin(write=False) as txn:
self.length = txn.stat()['entries'] - 1
self.field_dims = np.frombuffer(txn.get(b'field_dims'), dtype=np.uint32)
def __getitem__(self, index):
with self.env.begin(write=False) as txn:
np_array = np.frombuffer(
txn.get(struct.pack('>I', index)), dtype=np.uint32).astype(dtype=np.long)
return np_array[1:], np_array[0]
def __len__(self):
return self.length
def __build_cache(self, path, cache_path):
feat_mapper, defaults = self.__get_feat_mapper(path)
with lmdb.open(cache_path, map_size=int(1e11)) as env:
field_dims = np.zeros(self.NUM_FEATS, dtype=np.uint32)
for i, fm in feat_mapper.items():
field_dims[i - 1] = len(fm) + 1
with env.begin(write=True) as txn:
txn.put(b'field_dims', field_dims.tobytes())
for buffer in self.__yield_buffer(path, feat_mapper, defaults):
with env.begin(write=True) as txn:
for key, value in buffer:
txn.put(key, value)
def __get_feat_mapper(self, path):
feat_cnts = defaultdict(lambda: defaultdict(int))
with open(path) as f:
pbar = tqdm(f, mininterval=1, smoothing=0.1)
pbar.set_description('Create criteo dataset cache: counting features')
for line in pbar:
values = line.rstrip('\n').split('\t')
if len(values) != self.NUM_FEATS + 1:
continue
for i in range(1, self.NUM_INT_FEATS + 1):
feat_cnts[i][convert_numeric_feature(values[i])] += 1
for i in range(self.NUM_INT_FEATS + 1, self.NUM_FEATS + 1):
feat_cnts[i][values[i]] += 1
feat_mapper = {i: {feat for feat, c in cnt.items() if c >= self.min_threshold} for i, cnt in feat_cnts.items()}
feat_mapper = {i: {feat: idx for idx, feat in enumerate(cnt)} for i, cnt in feat_mapper.items()}
defaults = {i: len(cnt) for i, cnt in feat_mapper.items()}
return feat_mapper, defaults
def __yield_buffer(self, path, feat_mapper, defaults, buffer_size=int(1e5)):
item_idx = 0
buffer = list()
with open(path) as f:
pbar = tqdm(f, mininterval=1, smoothing=0.1)
pbar.set_description('Create criteo dataset cache: setup lmdb')
for line in pbar:
values = line.rstrip('\n').split('\t')
if len(values) != self.NUM_FEATS + 1:
continue
np_array = np.zeros(self.NUM_FEATS + 1, dtype=np.uint32)
np_array[0] = int(values[0])
for i in range(1, self.NUM_INT_FEATS + 1):
np_array[i] = feat_mapper[i].get(convert_numeric_feature(values[i]), defaults[i])
for i in range(self.NUM_INT_FEATS + 1, self.NUM_FEATS + 1):
np_array[i] = feat_mapper[i].get(values[i], defaults[i])
buffer.append((struct.pack('>I', item_idx), np_array.tobytes()))
item_idx += 1
if item_idx % buffer_size == 0:
yield buffer
buffer.clear()
yield buffer
@lru_cache(maxsize=None)
def convert_numeric_feature(val: str):
if val == '':
return 'NULL'
v = int(val)
if v > 2:
return str(int(math.log(v) ** 2))
else:
return str(v - 2)
def count_vals(x):
vals = np.unique(x)
occ = np.zeros(shape = vals.shape)
for i in range(vals.size):
occ[i] = np.sum(x == vals[i])
return occ
def entropy(x):
n = float(x.shape[0])
ocurrence = count_vals(x)
px = ocurrence / n
return -1* np.sum(px*np.log2(px))
def symmetricalUncertain(x,y):
n = float(y.shape[0])
vals = np.unique(y)
# Computing Entropy for the feature x.
Hx = entropy(x)
# Computing Entropy for the feature y.
Hy = entropy(y)
#Computing Joint entropy between x and y.
partial = np.zeros(shape = (vals.shape[0]))
for i in range(vals.shape[0]):
partial[i] = entropy(x[y == vals[i]])
partial[np.isnan(partial)==1] = 0
py = count_vals(y).astype(dtype = 'float64') / n
Hxy = np.sum(py[py > 0]*partial)
IG = Hx-Hxy
return 2*IG/(Hx+Hy)
def suGroup(x, n):
m = x.shape[0]
x = np.reshape(x, (n,m/n)).T
m = x.shape[1]
SU_matrix = np.zeros(shape = (m,m))
for j in range(m-1):
x2 = x[:,j+1::]
y = x[:,j]
temp = np.apply_along_axis(symmetricalUncertain, 0, x2, y)
for k in range(temp.shape[0]):
SU_matrix[j,j+1::] = temp
SU_matrix[j+1::,j] = temp
return 1/float(m-1)*np.sum(SU_matrix, axis = 1)