pavankumarhm commited on
Commit
c549103
·
1 Parent(s): 164fdd5
~/tensorflow_datasets/imdb_reviews/.config/metadata.json DELETED
@@ -1 +0,0 @@
1
- {"default_config_name": "plain_text"}
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/dataset_info.json DELETED
@@ -1,140 +0,0 @@
1
- {
2
- "citation": "@InProceedings{maas-EtAl:2011:ACL-HLT2011,\n author = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher},\n title = {Learning Word Vectors for Sentiment Analysis},\n booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},\n month = {June},\n year = {2011},\n address = {Portland, Oregon, USA},\n publisher = {Association for Computational Linguistics},\n pages = {142--150},\n url = {http://www.aclweb.org/anthology/P11-1015}\n}",
3
- "configDescription": "Plain text",
4
- "configName": "plain_text",
5
- "description": "Large Movie Review Dataset.\nThis is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. We provide a set of 25,000 highly polar movie reviews for training, and 25,000 for testing. There is additional unlabeled data for use as well.",
6
- "downloadSize": "84125825",
7
- "fileFormat": "tfrecord",
8
- "location": {
9
- "urls": [
10
- "http://ai.stanford.edu/~amaas/data/sentiment/"
11
- ]
12
- },
13
- "moduleName": "tensorflow_datasets.text.imdb",
14
- "name": "imdb_reviews",
15
- "releaseNotes": {
16
- "1.0.0": "New split API (https://tensorflow.org/datasets/splits)"
17
- },
18
- "schema": {
19
- "feature": [
20
- {
21
- "name": "label",
22
- "type": "INT"
23
- },
24
- {
25
- "name": "text",
26
- "type": "BYTES"
27
- }
28
- ]
29
- },
30
- "sizeInBytes": "84125825",
31
- "splits": [
32
- {
33
- "filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
34
- "name": "train",
35
- "numBytes": "34057750",
36
- "shardLengths": [
37
- "25000"
38
- ],
39
- "statistics": {
40
- "features": [
41
- {
42
- "name": "label",
43
- "numStats": {
44
- "commonStats": {
45
- "numNonMissing": "25000"
46
- },
47
- "max": 1.0
48
- }
49
- },
50
- {
51
- "bytesStats": {
52
- "commonStats": {
53
- "numNonMissing": "25000"
54
- }
55
- },
56
- "name": "text",
57
- "type": "BYTES"
58
- }
59
- ],
60
- "numExamples": "25000"
61
- }
62
- },
63
- {
64
- "filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
65
- "name": "test",
66
- "numBytes": "33275595",
67
- "shardLengths": [
68
- "25000"
69
- ],
70
- "statistics": {
71
- "features": [
72
- {
73
- "name": "label",
74
- "numStats": {
75
- "commonStats": {
76
- "numNonMissing": "25000"
77
- },
78
- "max": 1.0
79
- }
80
- },
81
- {
82
- "bytesStats": {
83
- "commonStats": {
84
- "numNonMissing": "25000"
85
- }
86
- },
87
- "name": "text",
88
- "type": "BYTES"
89
- }
90
- ],
91
- "numExamples": "25000"
92
- }
93
- },
94
- {
95
- "filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
96
- "name": "unsupervised",
97
- "numBytes": "68806612",
98
- "shardLengths": [
99
- "50000"
100
- ],
101
- "statistics": {
102
- "features": [
103
- {
104
- "name": "label",
105
- "numStats": {
106
- "commonStats": {
107
- "numNonMissing": "50000"
108
- },
109
- "max": -1.0,
110
- "min": -1.0
111
- }
112
- },
113
- {
114
- "bytesStats": {
115
- "commonStats": {
116
- "numNonMissing": "50000"
117
- }
118
- },
119
- "name": "text",
120
- "type": "BYTES"
121
- }
122
- ],
123
- "numExamples": "50000"
124
- }
125
- }
126
- ],
127
- "supervisedKeys": {
128
- "tuple": {
129
- "items": [
130
- {
131
- "featureKey": "text"
132
- },
133
- {
134
- "featureKey": "label"
135
- }
136
- ]
137
- }
138
- },
139
- "version": "1.0.0"
140
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/features.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "pythonClassName": "tensorflow_datasets.core.features.features_dict.FeaturesDict",
3
- "featuresDict": {
4
- "features": {
5
- "text": {
6
- "pythonClassName": "tensorflow_datasets.core.features.text_feature.Text",
7
- "text": {}
8
- },
9
- "label": {
10
- "pythonClassName": "tensorflow_datasets.core.features.class_label_feature.ClassLabel",
11
- "classLabel": {
12
- "numClasses": "2"
13
- }
14
- }
15
- }
16
- }
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/imdb_reviews-test.tfrecord-00000-of-00001 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5102d5b92e30ba2bc678da78f31e5b6320d71ad7bf072b1ae06cf6033db7d52f
3
- size 33675595
 
 
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/imdb_reviews-train.tfrecord-00000-of-00001 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:054a66c814775566ad3e00660e37def57ff1c10e9e0a822493150d1139c87acd
3
- size 34457750
 
 
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/imdb_reviews-unsupervised.tfrecord-00000-of-00001 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1341a1eb64c70cf9a96734ba505038b28e4903f89220a72f0038a1e895697885
3
- size 69606612
 
 
 
 
~/tensorflow_datasets/imdb_reviews/plain_text/1.0.0/label.labels.txt DELETED
@@ -1,2 +0,0 @@
1
- neg
2
- pos