-
-
Save Bomberus/36dbfb3266551d2332fd33bae44ecd7c to your computer and use it in GitHub Desktop.
w2v Validation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
stopwords: | |
'too','was','where','just','how','have','so','this','has','into','or','what','now', 'about', 'when', 'their','will','some','off','all','can','your','his','you','over', 'no','out','more','not','who','its', 'up','it','be', 'after','that','are','by','but', 'from','an', 'as', 'at','with', 'is','on','and','for','of','to','in','a','the' | |
labels: | |
['Arts' 'Business' 'Health' 'Opinion' 'Politics' 'Science' 'Sports' 'Style' 'Technology'] | |
Title (min 35 Character) : | |
Train : 7204 | |
Test : 1802 | |
Text | |
Train: 8010 | |
Test: 991 | |
Training : {'Technology': 897, 'Politics': 889, 'Science': 899, 'Health': 882, 'Business': 905, 'Opinion': 898, 'Style': 893, 'Arts': 867, 'Sports': 880} | |
================================================================================================================================= | |
Word2Vec + title | |
0.600998890122 | |
precision recall f1-score support | |
Arts 0.55 0.52 0.53 215 | |
Business 0.62 0.59 0.60 200 | |
Health 0.64 0.69 0.67 209 | |
Opinion 0.46 0.61 0.52 189 | |
Politics 0.80 0.69 0.74 212 | |
Science 0.64 0.55 0.59 208 | |
Sports 0.64 0.64 0.64 198 | |
Style 0.54 0.59 0.57 187 | |
Technology 0.58 0.52 0.54 184 | |
avg / total 0.61 0.60 0.60 1802 | |
0.551147612883 | |
array([[111, 12, 4, 21, 4, 18, 12, 20, 13], | |
[ 14, 118, 11, 16, 3, 4, 13, 10, 11], | |
[ 4, 10, 144, 10, 7, 9, 10, 7, 8], | |
[ 8, 4, 13, 115, 6, 6, 4, 20, 13], | |
[ 5, 11, 13, 15, 147, 6, 9, 1, 5], | |
[ 20, 7, 9, 18, 5, 115, 8, 14, 12], | |
[ 10, 11, 9, 18, 3, 10, 127, 8, 2], | |
[ 19, 12, 6, 23, 1, 3, 6, 111, 6], | |
[ 12, 6, 15, 16, 8, 9, 10, 13, 95]]) | |
================================================================================================================================= | |
Word2Vec + text | |
0.860746720484 | |
precision recall f1-score support | |
Arts 0.89 0.88 0.88 133 | |
Business 0.79 0.79 0.79 95 | |
Health 0.87 0.88 0.87 119 | |
Opinion 0.76 0.80 0.78 102 | |
Politics 0.87 0.90 0.89 112 | |
Science 0.82 0.81 0.82 99 | |
Sports 0.97 0.98 0.97 121 | |
Style 0.89 0.84 0.86 106 | |
Technology 0.86 0.83 0.84 104 | |
avg / total 0.86 0.86 0.86 991 | |
0.843118495678 | |
array([[117, 1, 1, 5, 0, 2, 0, 5, 2], | |
[ 1, 75, 2, 4, 0, 3, 1, 3, 6], | |
[ 0, 2, 105, 2, 3, 5, 0, 1, 1], | |
[ 5, 4, 4, 82, 4, 1, 0, 0, 2], | |
[ 2, 1, 3, 5, 101, 0, 0, 0, 0], | |
[ 2, 2, 4, 5, 3, 80, 0, 0, 3], | |
[ 0, 1, 0, 0, 0, 1, 118, 1, 0], | |
[ 4, 4, 2, 3, 0, 3, 1, 89, 0], | |
[ 1, 5, 0, 2, 5, 2, 2, 1, 86]]) | |
================================================================================================================================= | |
Glove 50d + Titel | |
0.57935627081 | |
precision recall f1-score support | |
Arts 0.53 0.52 0.52 215 | |
Business 0.58 0.56 0.57 200 | |
Health 0.57 0.66 0.61 209 | |
Opinion 0.43 0.51 0.47 189 | |
Politics 0.74 0.67 0.70 212 | |
Science 0.61 0.51 0.56 208 | |
Sports 0.63 0.69 0.66 198 | |
Style 0.60 0.60 0.60 187 | |
Technology 0.56 0.48 0.52 184 | |
avg / total 0.58 0.58 0.58 1802 | |
0.526658624682 | |
array([[111, 9, 14, 16, 3, 15, 17, 23, 7], | |
[ 11, 111, 15, 21, 5, 7, 14, 10, 6], | |
[ 5, 11, 138, 10, 9, 8, 9, 7, 12], | |
[ 13, 12, 17, 97, 8, 8, 8, 10, 16], | |
[ 4, 10, 16, 18, 143, 6, 7, 4, 4], | |
[ 26, 4, 12, 22, 12, 107, 7, 7, 11], | |
[ 14, 9, 8, 13, 1, 6, 136, 5, 6], | |
[ 12, 8, 9, 20, 1, 8, 8, 112, 9], | |
[ 14, 16, 14, 11, 12, 9, 9, 10, 89]]) | |
================================================================================================================================= | |
Glove 50d + Text | |
0.835519677094 | |
precision recall f1-score support | |
Arts 0.88 0.86 0.87 133 | |
Business 0.73 0.80 0.76 95 | |
Health 0.84 0.85 0.85 119 | |
Opinion 0.72 0.79 0.75 102 | |
Politics 0.84 0.84 0.84 112 | |
Science 0.88 0.78 0.82 99 | |
Sports 0.97 0.95 0.96 121 | |
Style 0.87 0.85 0.86 106 | |
Technology 0.77 0.76 0.76 104 | |
avg / total 0.84 0.84 0.84 991 | |
0.814743199368 | |
array([[115, 3, 0, 2, 2, 3, 0, 6, 2], | |
[ 1, 76, 3, 4, 0, 0, 2, 2, 7], | |
[ 0, 2, 101, 4, 4, 4, 1, 1, 2], | |
[ 5, 4, 5, 81, 5, 0, 0, 0, 2], | |
[ 0, 3, 2, 9, 94, 0, 0, 0, 4], | |
[ 2, 3, 5, 6, 1, 77, 0, 1, 4], | |
[ 0, 1, 0, 2, 0, 0, 115, 2, 1], | |
[ 6, 3, 2, 1, 0, 2, 0, 90, 2], | |
[ 1, 9, 2, 4, 6, 2, 0, 1, 79]]) | |
================================================================================================================================= | |
Glove 200d + Titel | |
0.620976692564 | |
precision recall f1-score support | |
Arts 0.57 0.52 0.54 215 | |
Business 0.57 0.57 0.57 200 | |
Health 0.63 0.70 0.67 209 | |
Opinion 0.46 0.54 0.50 189 | |
Politics 0.81 0.74 0.77 212 | |
Science 0.65 0.59 0.62 208 | |
Sports 0.68 0.71 0.70 198 | |
Style 0.61 0.67 0.64 187 | |
Technology 0.62 0.53 0.57 184 | |
avg / total 0.63 0.62 0.62 1802 | |
0.573537233536 | |
array([[111, 12, 13, 14, 2, 18, 13, 25, 7], | |
[ 13, 115, 13, 19, 4, 9, 9, 9, 9], | |
[ 4, 13, 147, 14, 4, 6, 8, 6, 7], | |
[ 13, 13, 12, 103, 6, 11, 5, 13, 13], | |
[ 3, 10, 10, 13, 157, 5, 9, 3, 2], | |
[ 17, 6, 10, 19, 6, 122, 8, 9, 11], | |
[ 10, 11, 7, 15, 2, 5, 141, 6, 1], | |
[ 14, 9, 7, 13, 1, 3, 6, 125, 9], | |
[ 11, 11, 14, 13, 12, 8, 8, 9, 98]]) | |
================================================================================================================================= | |
Glove 200d + Text | |
0.855701311806 | |
precision recall f1-score support | |
Arts 0.90 0.88 0.89 133 | |
Business 0.77 0.83 0.80 95 | |
Health 0.84 0.86 0.85 119 | |
Opinion 0.81 0.81 0.81 102 | |
Politics 0.87 0.88 0.87 112 | |
Science 0.85 0.83 0.84 99 | |
Sports 0.97 0.95 0.96 121 | |
Style 0.87 0.85 0.86 106 | |
Technology 0.80 0.79 0.79 104 | |
avg / total 0.86 0.86 0.86 991 | |
0.837472044774 | |
================================================================================================================================= | |
Glove 300d + Title | |
0.617092119867 | |
precision recall f1-score support | |
Arts 0.58 0.55 0.57 215 | |
Business 0.59 0.61 0.60 200 | |
Health 0.64 0.71 0.67 209 | |
Opinion 0.47 0.51 0.49 189 | |
Politics 0.80 0.72 0.76 212 | |
Science 0.65 0.58 0.61 208 | |
Sports 0.68 0.68 0.68 198 | |
Style 0.57 0.65 0.61 187 | |
Technology 0.59 0.53 0.56 184 | |
avg / total 0.62 0.62 0.62 1802 | |
0.569163771336 | |
array([[118, 10, 11, 13, 2, 19, 11, 24, 7], | |
[ 12, 123, 9, 18, 3, 9, 8, 11, 7], | |
[ 5, 12, 148, 10, 4, 6, 8, 5, 11], | |
[ 12, 15, 9, 97, 6, 11, 7, 16, 16], | |
[ 3, 8, 14, 17, 153, 5, 7, 3, 2], | |
[ 17, 6, 13, 15, 5, 120, 9, 11, 12], | |
[ 11, 11, 8, 12, 5, 5, 134, 10, 2], | |
[ 14, 11, 8, 10, 1, 4, 7, 121, 11], | |
[ 10, 12, 13, 15, 12, 7, 7, 10, 98]]) | |
================================================================================================================================= | |
Glove 300d + Text | |
0.862764883956 | |
precision recall f1-score support | |
Arts 0.88 0.89 0.88 133 | |
Business 0.77 0.81 0.79 95 | |
Health 0.86 0.87 0.86 119 | |
Opinion 0.83 0.80 0.82 102 | |
Politics 0.88 0.89 0.89 112 | |
Science 0.86 0.82 0.84 99 | |
Sports 0.97 0.95 0.96 121 | |
Style 0.88 0.87 0.87 106 | |
Technology 0.81 0.84 0.82 104 | |
avg / total 0.86 0.86 0.86 991 | |
0.845401185392 | |
array([[118, 2, 0, 4, 1, 1, 0, 6, 1], | |
[ 2, 77, 1, 3, 0, 2, 1, 2, 7], | |
[ 0, 3, 103, 2, 3, 5, 0, 2, 1], | |
[ 6, 4, 5, 82, 2, 1, 0, 0, 2], | |
[ 1, 2, 4, 2, 100, 1, 0, 0, 2], | |
[ 1, 2, 4, 3, 1, 81, 0, 1, 6], | |
[ 1, 1, 0, 2, 0, 0, 115, 1, 1], | |
[ 5, 3, 2, 0, 0, 2, 1, 92, 1], | |
[ 0, 6, 1, 1, 6, 1, 1, 1, 87]]) | |
====== | |
Memory-Usage | |
Google : 3.000.000 words * 300 features * 4bytes/feature ~ 3,6GB | |
Glove 50d : 400.000 * 50 features * 4bytes/feature ~ 0.08GB | |
Glove 200d : 400.000 * 200 features * 4bytes/feature ~ 0.32GB | |
Glove 300d : 400.000 * 300 features * 4bytes/feature ~ 0.48GB |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment