diff --git a/.gitignore b/.gitignore index 2c11409..c949f6f 100644 --- a/.gitignore +++ b/.gitignore @@ -111,4 +111,3 @@ venv.bak/ # Ignore experiment folder experiments/ -data/ diff --git a/bin/run-joint.sh b/bin/run-joint.sh index 857276f..6504c14 100755 --- a/bin/run-joint.sh +++ b/bin/run-joint.sh @@ -19,7 +19,9 @@ do exp_dir=$(prepare_experiment_dir $topic ${exp_id}) # Write down parameters that'll be on the html file write_experiment_params ${exp_dir} weight 1 - + python -m cartograph.draw.zpop_creator \ + --experiment ${exp_dir} \ + --popularity_score data/${topic}/popularity_score.csv # Step 2: run UMAP python -m cartograph.xy_embed.umap_embed \ --map_directory ${exp_dir} \ @@ -47,13 +49,18 @@ do --cluster_groups /key_phrases_cluster_groups.csv \ --output_file /key_phrases_top_labels.csv \ --label_source key_phrases \ - --num_top_labels ${labels_num} # number of top keyphrases labels + --num_top_labels ${labels_num} # number of top keyphrases labels #Step 5: Fetch hierarchical categories from key phrases python -m cartograph.h_cat_fetcher \ --experiment ${exp_dir} \ --isSumInKeyPhrase ${isSumInKeyPhrase} + #Step 5.5 generate zpop + python -m cartograph.draw.zpop_creator \ + --experiment ${exp_dir} \ + --popularity_score data/${topic}/popularity_score.csv + # Step 6 python -m cartograph.user_study_label \ --experiment ${exp_dir} \ diff --git a/cartograph/draw/zpop_creator.py b/cartograph/draw/zpop_creator.py new file mode 100644 index 0000000..c75928b --- /dev/null +++ b/cartograph/draw/zpop_creator.py @@ -0,0 +1,47 @@ +# Transform popularity score from wikipedia to a score that looks good on cartograph +# Author: Rock Pang, +# Reference: https://github.com/shilad/cartograph/blob/develop-simple/cartograph/CalculateZPop.py + +import pandas as pd +import numpy as np +import argparse + + +def log4(x): + return np.log2(x) / np.log2(4) + + +def main(experiment_directory, popularity_score_df, new_xy_embeddings_df): + assert(popularity_score_df.shape[0] != 0) # check if popularity score df is not empty + new_rows = [] + pop_dic = {} + for row in popularity_score_df.itertuples(): + pop_dic[row.article_id] = row.popularity_score + + for row in new_xy_embeddings_df.itertuples(): + val = 0 + if row.article_id in pop_dic: + val = pop_dic[row.article_id] + new_rows.append({"article_id":row.article_id, "popularity_score": val}) + + df = pd.DataFrame(new_rows) + + sorted_score = df.sort_values(by='popularity_score', ascending=False) + + sorted_score['zpop'] = log4(np.arange(sorted_score.shape[0]) / 2.0 + 1.0) + sorted_score = sorted_score.drop("popularity_score", axis=1) + sorted_score.to_csv(experiment_directory + "/zpop_score.csv", index=False) + + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + parser.add_argument('--experiment', required=True) + parser.add_argument('--popularity_score', required=True) + args = parser.parse_args() + + experiment_directory = args.experiment + popularity_score = args.popularity_score + new_xy_embedding = experiment_directory + "/new_xy_embeddings.csv" + + + main(experiment_directory, pd.read_csv(popularity_score), pd.read_csv(new_xy_embedding)) diff --git a/data/article_vectors.csv b/data/article_vectors.csv new file mode 100644 index 0000000..4573736 --- /dev/null +++ b/data/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0575ea101047433970070ec5fbaf45c5af8dcc87bc2cdcfef1a59fa75c98c2 +size 8666 diff --git a/data/education/article_hierarchical_categories.csv b/data/education/article_hierarchical_categories.csv new file mode 100644 index 0000000..4fa4867 --- /dev/null +++ b/data/education/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e95887d3a588a5c8aec19d577bf2f623ef5c2e5cdaf79d5f4a5cfa19a7c9c0d9 +size 2341361 diff --git a/data/education/article_keyphrases.csv b/data/education/article_keyphrases.csv new file mode 100644 index 0000000..3873700 --- /dev/null +++ b/data/education/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:188aad95ce44491d9281f9c154f3e999284004b2c2728d0b93dbe7f315b53271 +size 11939742 diff --git a/data/education/article_keywords.csv b/data/education/article_keywords.csv new file mode 100644 index 0000000..2a6a08d --- /dev/null +++ b/data/education/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6da73de5ae0ec89bc40095b78fd46b62fc8904843be70c8d6007a6fe990d61d +size 21850347 diff --git a/data/education/article_labels_combined.csv b/data/education/article_labels_combined.csv new file mode 100644 index 0000000..cfcd105 --- /dev/null +++ b/data/education/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453d3400eaa71ea8d45ba98fa75b795a5ebcb41938403bbf483aad1ea2298d8e +size 25612341 diff --git a/data/education/article_lda_labels.csv b/data/education/article_lda_labels.csv new file mode 100644 index 0000000..f9437ab --- /dev/null +++ b/data/education/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a84ece3f7253e09b30c00295685d61bac8e31558f3f404b711609cd7f461d5 +size 34246058 diff --git a/data/education/article_links.csv b/data/education/article_links.csv new file mode 100644 index 0000000..8d2bc82 --- /dev/null +++ b/data/education/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d1bd0cfb14e6702ca6b4b8579b9671d1031d7782bf2fd17ec8200009b66744 +size 715572 diff --git a/data/education/article_text.csv b/data/education/article_text.csv new file mode 100644 index 0000000..f4b0e89 --- /dev/null +++ b/data/education/article_text.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24e3d77bf1b3736443bf64d94a6be89ff242707e6b5199380d9ee3f03b0553d7 +size 76047633 diff --git a/data/education/article_text_gloss.csv b/data/education/article_text_gloss.csv new file mode 100644 index 0000000..75592cb --- /dev/null +++ b/data/education/article_text_gloss.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a338ac119384d6a10d7dcce1f9988fe025845f0775882f892574a119957153 +size 9046808 diff --git a/data/education/article_topic_distribution.csv b/data/education/article_topic_distribution.csv new file mode 100644 index 0000000..d3a8e1d --- /dev/null +++ b/data/education/article_topic_distribution.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30030e2a447b446cea17a1911526f778ac73d66da02528c2bc6d9dbb38a539ad +size 1193727 diff --git a/data/education/article_vectors.csv b/data/education/article_vectors.csv new file mode 100644 index 0000000..ac7fa28 --- /dev/null +++ b/data/education/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c38ea883e5d356117cbeef43f88f6f78a16d73f10003b6fbb1dc34115d1210 +size 4528733 diff --git a/data/education/combined_label_names.csv b/data/education/combined_label_names.csv new file mode 100644 index 0000000..9d5f782 --- /dev/null +++ b/data/education/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47de3df260660cc92418b8634a92f9072cc74dd29abf488b5e06c5aec3ce346 +size 9521823 diff --git a/data/education/domain_concept.csv b/data/education/domain_concept.csv new file mode 100644 index 0000000..9d15886 --- /dev/null +++ b/data/education/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfdac24f279b3cadd4b7bcb5b02ebeb465be3d044bd08a59527b98dc0a9e402 +size 359005 diff --git a/data/education/hierarchical_category_names.csv b/data/education/hierarchical_category_names.csv new file mode 100644 index 0000000..338ec3a --- /dev/null +++ b/data/education/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d4364281506bc983d58c2ec5085abb098d493a6ac569647c02e9677169d099 +size 2219888 diff --git a/data/education/keyphrases_names.csv b/data/education/keyphrases_names.csv new file mode 100644 index 0000000..f71dc01 --- /dev/null +++ b/data/education/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e36fb127831fae2c0a8aca2dbcc380117b8912fe8aab8fb271a68e75cd15b9 +size 635141 diff --git a/data/education/keyword_names.csv b/data/education/keyword_names.csv new file mode 100644 index 0000000..395b77d --- /dev/null +++ b/data/education/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ef2506511c29ef4b88a55f399bc1a0ac07a303c5cd7705c670d815bcc01860 +size 2744002 diff --git a/data/education/labels/LDA_labels/LDA_labels.csv b/data/education/labels/LDA_labels/LDA_labels.csv new file mode 100644 index 0000000..3b7640b --- /dev/null +++ b/data/education/labels/LDA_labels/LDA_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e39daab2754f8da906a8f25399963900c08fb5dce187b4da203f9651d667a3 +size 5491 diff --git a/data/education/lda_label_names.csv b/data/education/lda_label_names.csv new file mode 100644 index 0000000..e6bbd94 --- /dev/null +++ b/data/education/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd24f695a59fcd27931747654bcaee16202a30afbf0804cd55309ebf021256c4 +size 2462 diff --git a/data/education/link_names.csv b/data/education/link_names.csv new file mode 100644 index 0000000..d9a6008 --- /dev/null +++ b/data/education/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d5c6c9a22d61443f817a0542711226818cade412bf4d9e75441df6be3f7788 +size 906117 diff --git a/data/education/popularity_score.csv b/data/education/popularity_score.csv new file mode 100644 index 0000000..351d5ea --- /dev/null +++ b/data/education/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb4b37048087e3159144ebfecc56a96d920a603eebac4f10d7c9e6c32363dd0 +size 118423 diff --git a/data/education/topic_model b/data/education/topic_model new file mode 100644 index 0000000..b49130b --- /dev/null +++ b/data/education/topic_model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf6a8efc55cc6cf608fb19b1c7de8e61f0cfb83528b2e9691bb1297ffe7464f +size 248747 diff --git a/data/education/topic_model.expElogbeta.npy b/data/education/topic_model.expElogbeta.npy new file mode 100644 index 0000000..148ecbc --- /dev/null +++ b/data/education/topic_model.expElogbeta.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d50e04167d8f22ba6f3cec9b015e105a1000b52ec97af67668f3ff9e0dc5f6 +size 1706588 diff --git a/data/education/topic_model.id2word b/data/education/topic_model.id2word new file mode 100644 index 0000000..94e0522 --- /dev/null +++ b/data/education/topic_model.id2word @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462e7c2b5115f4c05ce8c0befe25ab29bdbc02f2a9de13f893862425f46f32d4 +size 2697969 diff --git a/data/education/topic_model.state b/data/education/topic_model.state new file mode 100644 index 0000000..fbe1c7d --- /dev/null +++ b/data/education/topic_model.state @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca1ee372c8505e5e3e0ccfe800e4be007aba60b2a0556e17a2d472b930a8160 +size 2599060 diff --git a/data/food/article_categories.csv b/data/food/article_categories.csv new file mode 100644 index 0000000..8aaf8a3 --- /dev/null +++ b/data/food/article_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25edf90accf125311175bda521e0678e6e85a6355715a3965506ccea1ebb06e8 +size 278982 diff --git a/data/food/article_hierarchical_categories.csv b/data/food/article_hierarchical_categories.csv new file mode 100644 index 0000000..66a0bcc --- /dev/null +++ b/data/food/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c3a242a955e8a80ea69157bcb027dfa6bd2d2f99e97ee62b9e1c7376406b39 +size 2683841 diff --git a/data/food/article_keyphrases.csv b/data/food/article_keyphrases.csv new file mode 100644 index 0000000..0f9f5b5 --- /dev/null +++ b/data/food/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cfef0d7927e90ea11debbe56a2162ded26543a56339bbbf15e466bdc0cc744f +size 5760059 diff --git a/data/food/article_keywords.csv b/data/food/article_keywords.csv new file mode 100644 index 0000000..f0e6e42 --- /dev/null +++ b/data/food/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91343e58eba336ef6191d7c0774fe88672cef3d1e7777490b19f99ba81655784 +size 1286001 diff --git a/data/food/article_labels_combined.csv b/data/food/article_labels_combined.csv new file mode 100644 index 0000000..1edb3e1 --- /dev/null +++ b/data/food/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983aab91f5f70d7e524c16d765f39162406d90613ce92500da11b102ab2aa531 +size 13365218 diff --git a/data/food/article_lda_labels.csv b/data/food/article_lda_labels.csv new file mode 100644 index 0000000..e20e639 --- /dev/null +++ b/data/food/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4deb0bbfd0152acb09cf748212b27618c5684d1682f4077fcc6df21b3cdfe5 +size 14164908 diff --git a/data/food/article_links.csv b/data/food/article_links.csv new file mode 100644 index 0000000..8d4ee8e --- /dev/null +++ b/data/food/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:023daf64b2eb2f5d6e13f9d33a4265d6d2679f7ae5a7f4c1a9a58553806c82b6 +size 503901 diff --git a/data/food/article_text.csv b/data/food/article_text.csv new file mode 100644 index 0000000..e69de29 diff --git a/data/food/article_text_gloss.csv b/data/food/article_text_gloss.csv new file mode 100644 index 0000000..cb010d6 --- /dev/null +++ b/data/food/article_text_gloss.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2c5edd9caf963a4b9dbea5506d47577908f86348196ec88b4c6bf032ba4c96 +size 3956058 diff --git a/data/food/article_vectors.csv b/data/food/article_vectors.csv new file mode 100644 index 0000000..c458085 --- /dev/null +++ b/data/food/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d18e8fefdef821aff0586a340e3a0eb1ce91c1ab7bcf85bcbce9964037d30c51 +size 3810540 diff --git a/data/food/category_names.csv b/data/food/category_names.csv new file mode 100644 index 0000000..0ea0264 --- /dev/null +++ b/data/food/category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b8e265695b2bf64e2ecb5200b51a374cfc7e150773b791017b846d6531eeaf +size 401133 diff --git a/data/food/combined_label_names.csv b/data/food/combined_label_names.csv new file mode 100644 index 0000000..a584ba6 --- /dev/null +++ b/data/food/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfe1ce6e1a9d50cd4a40e025fa3df6375f73d93cba3ca9d80eaa30ae85a5e6a +size 6150936 diff --git a/data/food/domain_concept.csv b/data/food/domain_concept.csv new file mode 100644 index 0000000..584b71f --- /dev/null +++ b/data/food/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d25c4ec069361139642d77f2d649aa3384a8c69b1f4ccfb4eb30d1786f346a8 +size 102108 diff --git a/data/food/hierarchical_category_names.csv b/data/food/hierarchical_category_names.csv new file mode 100644 index 0000000..1744ff7 --- /dev/null +++ b/data/food/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2f18b9e307f2ba054185e98b3f8f247e7510575ad95946d8dd3cb244f264c2 +size 1644453 diff --git a/data/food/keyphrases_names.csv b/data/food/keyphrases_names.csv new file mode 100644 index 0000000..0071527 --- /dev/null +++ b/data/food/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dee85e574e3c0ddf145eb6e6762cd0cb261607ad1ef72eeb76c974db3c9ab9a +size 436768 diff --git a/data/food/keyword_names.csv b/data/food/keyword_names.csv new file mode 100644 index 0000000..29c16c2 --- /dev/null +++ b/data/food/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ede7d910c5df55a2b81b78e30ed8bf95287a9f2f8109b92925cbb4f399b0aed +size 345707 diff --git a/data/food/lda_label_names.csv b/data/food/lda_label_names.csv new file mode 100644 index 0000000..93c071d --- /dev/null +++ b/data/food/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25828a5acb7f54d6f7ebbe6cb75dd7dd982e8cb717376f631b2bce7a1763b3a2 +size 2417 diff --git a/data/food/link_names.csv b/data/food/link_names.csv new file mode 100644 index 0000000..08ff91c --- /dev/null +++ b/data/food/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee4821afc99a12b0b45c3691561f8fbb1a287bc3a2a8d6ba7740a57fd74f5a1 +size 497597 diff --git a/data/food/popularity_score.csv b/data/food/popularity_score.csv new file mode 100644 index 0000000..95ef75f --- /dev/null +++ b/data/food/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936c64882a8e30d02616d9e050e02beb592499f4dae3d46c1e84a6be6e780392 +size 53522 diff --git a/data/food/topic/article_topic_distribution.csv b/data/food/topic/article_topic_distribution.csv new file mode 100644 index 0000000..812adce --- /dev/null +++ b/data/food/topic/article_topic_distribution.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58f04dad19eefa6fc9b588425c23898bb45c00d7ef08c2e04f3e80d1ba06eba +size 518755 diff --git a/data/food/topic/topic_label_distribution.csv b/data/food/topic/topic_label_distribution.csv new file mode 100644 index 0000000..e6feeac --- /dev/null +++ b/data/food/topic/topic_label_distribution.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed87287f19913018460f3313390946bc9f96380ebbb38f5594d85ac02fd6786c +size 1126 diff --git a/data/food/vanilla_vectors.csv b/data/food/vanilla_vectors.csv new file mode 100644 index 0000000..335f195 --- /dev/null +++ b/data/food/vanilla_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2822265d8667509fe2f208c2ed86c18a53bae896685bf0c04df214d0fd6961ec +size 3853750 diff --git a/data/georgraphy/article_hierarchical_categories.csv b/data/georgraphy/article_hierarchical_categories.csv new file mode 100644 index 0000000..e1ae3f7 --- /dev/null +++ b/data/georgraphy/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596f8dad8748d5b23af0c81a6048c99e5ac7102230e8b91053d03071d4292ae7 +size 6489120 diff --git a/data/georgraphy/article_keyphrases.csv b/data/georgraphy/article_keyphrases.csv new file mode 100644 index 0000000..fb8c622 --- /dev/null +++ b/data/georgraphy/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c340f67a1efdd445e4605b514d02967cb8aef2e205081b98b1f566a6424264 +size 40773036 diff --git a/data/georgraphy/article_keywords.csv b/data/georgraphy/article_keywords.csv new file mode 100644 index 0000000..d6ed02b --- /dev/null +++ b/data/georgraphy/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8631b68b9c76fa35cd52b032524eb5a6cc3f7c860e52ce1f18ee296db0a96a +size 9160073 diff --git a/data/georgraphy/article_lda_labels.csv b/data/georgraphy/article_lda_labels.csv new file mode 100644 index 0000000..cc70ae4 --- /dev/null +++ b/data/georgraphy/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60498cd08261ab4f435e783a648ef5a560888eed3085ad9d7015300238c939bf +size 214451193 diff --git a/data/georgraphy/article_links.csv b/data/georgraphy/article_links.csv new file mode 100644 index 0000000..fcfee05 --- /dev/null +++ b/data/georgraphy/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af60e3a36c8f21533ce9fd010e17d18be7f9ab1528bf783854666a7d9d56308 +size 5989901 diff --git a/data/georgraphy/article_text b/data/georgraphy/article_text new file mode 100644 index 0000000..e3daadc --- /dev/null +++ b/data/georgraphy/article_text @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e220509e07ff71b1b77f43aeff416d920b0f1d9f10c2d15683d2fb6120a684d7 +size 80889451 diff --git a/data/georgraphy/article_text_gloss.csv b/data/georgraphy/article_text_gloss.csv new file mode 100644 index 0000000..d096425 --- /dev/null +++ b/data/georgraphy/article_text_gloss.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25be05d09f3f96cd30aacf31fbefa3bff441f6f245c233d2428348b8f2a1ece8 +size 29725281 diff --git a/data/georgraphy/article_topic_distribution.csv b/data/georgraphy/article_topic_distribution.csv new file mode 100644 index 0000000..5e50040 --- /dev/null +++ b/data/georgraphy/article_topic_distribution.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94bc1ad730da384f969e72608d60bf974ca1cf99211443ea5480601c87268165 +size 13671437 diff --git a/data/georgraphy/article_vectors.csv b/data/georgraphy/article_vectors.csv new file mode 100644 index 0000000..52979e0 --- /dev/null +++ b/data/georgraphy/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11afe001a3feed81fec042c3f14cfc1931ba4ab91536162f172defcace3d7e0a +size 4171774 diff --git a/data/georgraphy/domain_concept.csv b/data/georgraphy/domain_concept.csv new file mode 100644 index 0000000..08f29b1 --- /dev/null +++ b/data/georgraphy/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e79b67c16dd2a26fb05befbd0863e96c8da18dbe3f569ff84d5c57e8c022e40 +size 1928329 diff --git a/data/georgraphy/hierarchical_category_names.csv b/data/georgraphy/hierarchical_category_names.csv new file mode 100644 index 0000000..460c8b8 --- /dev/null +++ b/data/georgraphy/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b34d6b2970ac152b26812ebbef298ace062ebd204167077daa1feb0b2ee04b5 +size 1303231 diff --git a/data/georgraphy/keyphrases_names.csv b/data/georgraphy/keyphrases_names.csv new file mode 100644 index 0000000..921a677 --- /dev/null +++ b/data/georgraphy/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c88fe4b1ce0f629d25b300e8276f072544728a5ef3cf164a63ab1981252231 +size 1255621 diff --git a/data/georgraphy/keyword_names.csv b/data/georgraphy/keyword_names.csv new file mode 100644 index 0000000..753b0b2 --- /dev/null +++ b/data/georgraphy/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e776c390fa166feb754c0bfa7e7868d3965b73ff6e5d3c201c7ee98beadfc11 +size 1096616 diff --git a/data/georgraphy/labels/LDA_labels/LDA_labels.csv b/data/georgraphy/labels/LDA_labels/LDA_labels.csv new file mode 100644 index 0000000..103b56b --- /dev/null +++ b/data/georgraphy/labels/LDA_labels/LDA_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6e283e0efcfbc7ca9f33b06d67d2abe66714a7b0dcccab0b4d073d39ee6e89 +size 2444 diff --git a/data/georgraphy/lda_label_names.csv b/data/georgraphy/lda_label_names.csv new file mode 100644 index 0000000..a9c3e31 --- /dev/null +++ b/data/georgraphy/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139f8c6d455c135ee288ec7e2a2f5a6b2cd8b49e3312e2b9e616e6e0b1637df0 +size 1872 diff --git a/data/georgraphy/link_names.csv b/data/georgraphy/link_names.csv new file mode 100644 index 0000000..67b9e59 --- /dev/null +++ b/data/georgraphy/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82aafdbc9609ac6994059b4c88543c04186a384fa6d1b18f2c3681074bc1aac0 +size 1949334 diff --git a/data/georgraphy/popularity_score.csv b/data/georgraphy/popularity_score.csv new file mode 100644 index 0000000..9425ae0 --- /dev/null +++ b/data/georgraphy/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbce0f7b34a047a67700a4bb0a1749ea34e89069a38ef3b367e828bbb7e6122b +size 834916 diff --git a/data/georgraphy/topic_model b/data/georgraphy/topic_model new file mode 100644 index 0000000..4541039 --- /dev/null +++ b/data/georgraphy/topic_model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d753528444a9ac66cc5cc64634d46d12d39aa01723d77675c50134a347e867 +size 120274 diff --git a/data/georgraphy/topic_model.expElogbeta.npy b/data/georgraphy/topic_model.expElogbeta.npy new file mode 100644 index 0000000..b16d8b1 --- /dev/null +++ b/data/georgraphy/topic_model.expElogbeta.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3937bcfe8b303ab0dce283696777211fe072c1a179e6c9d8981b0c33669062 +size 807732 diff --git a/data/georgraphy/topic_model.id2word b/data/georgraphy/topic_model.id2word new file mode 100644 index 0000000..fa882e8 --- /dev/null +++ b/data/georgraphy/topic_model.id2word @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15af70586a44a2dccaf871d61dc8a06ab369b07570d934ca5f88c05e29f27ed +size 1242655 diff --git a/data/georgraphy/topic_model.state b/data/georgraphy/topic_model.state new file mode 100644 index 0000000..4aadfa6 --- /dev/null +++ b/data/georgraphy/topic_model.state @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087f05be6d0d2792bbd062b2d7ec7e011ae0419495d548a98b777eb13bc2a772 +size 1225488 diff --git a/data/h_cat_from_top_labels.pkl b/data/h_cat_from_top_labels.pkl new file mode 100644 index 0000000..0dd7c83 --- /dev/null +++ b/data/h_cat_from_top_labels.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a799f401fac3d86884f043d349e2a84f04c906b2a4476c3d376b43c3780ba9 +size 543949 diff --git a/data/h_cat_from_top_labels_one_level.pkl b/data/h_cat_from_top_labels_one_level.pkl new file mode 100644 index 0000000..aa37a26 --- /dev/null +++ b/data/h_cat_from_top_labels_one_level.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b09e68cddc6fdf73b3e99fbf6d7206c7144a76b051805389a667a9c797d6cc +size 460549 diff --git a/data/internet/article_categories.csv b/data/internet/article_categories.csv new file mode 100644 index 0000000..c74f029 --- /dev/null +++ b/data/internet/article_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182d473dc460911ade10bba4ffd8f189e0f073dff8d7ad6bbf633c83c1454628 +size 2670737 diff --git a/data/internet/article_hierarchical_categories.csv b/data/internet/article_hierarchical_categories.csv new file mode 100644 index 0000000..5a4f7f9 --- /dev/null +++ b/data/internet/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a551aaa232c2f69d72f064d933031a1d47f0e176af05073193fcf714f5aac02d +size 2528819 diff --git a/data/internet/article_keyphrases.csv b/data/internet/article_keyphrases.csv new file mode 100644 index 0000000..973454c --- /dev/null +++ b/data/internet/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448a1259313af95fe2b5e8cb68eb4390bfb6f10f901694468592663563371c7c +size 2553565 diff --git a/data/internet/article_keywords.csv b/data/internet/article_keywords.csv new file mode 100644 index 0000000..b0d2c57 --- /dev/null +++ b/data/internet/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b840f5644201e4f8ff619ed9340437c4cdc692da513eddbfbb57b2ca995a0535 +size 8945206 diff --git a/data/internet/article_labels_combined.csv b/data/internet/article_labels_combined.csv new file mode 100644 index 0000000..87fd2c2 --- /dev/null +++ b/data/internet/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c5f7cda862b6e954e65692431cc0f41bc5649c04d0eda204eb2072c71742252 +size 9837328 diff --git a/data/internet/article_lda_labels.csv b/data/internet/article_lda_labels.csv new file mode 100644 index 0000000..fffd024 --- /dev/null +++ b/data/internet/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5724b4d05ff4eec1b96c47445c5380e8967e6b52ebcdf83740b66e1fd3b11871 +size 12240540 diff --git a/data/internet/article_links.csv b/data/internet/article_links.csv new file mode 100644 index 0000000..8e58643 --- /dev/null +++ b/data/internet/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee14f95ba79b3cd3fb4d083d41656f09ea20d614168c9651a6ccb4ba2f51b45 +size 326968 diff --git a/data/internet/article_text.csv b/data/internet/article_text.csv new file mode 100644 index 0000000..5846661 --- /dev/null +++ b/data/internet/article_text.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d028584c4d3852490a6bbccaa1b283bb181c61b27c91b464a0496484ca14ee1d +size 30480939 diff --git a/data/internet/article_text_summary_don_forget_delete.csv b/data/internet/article_text_summary_don_forget_delete.csv new file mode 100644 index 0000000..44c3b10 --- /dev/null +++ b/data/internet/article_text_summary_don_forget_delete.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b93b08d2cfb8b1e94ba650997c6a8f1e68898dc7d435819a00fabdc5339bd3 +size 3522779 diff --git a/data/internet/article_vectors.csv b/data/internet/article_vectors.csv new file mode 100644 index 0000000..040cc0d --- /dev/null +++ b/data/internet/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42fadeefe15b338422666f8119ee7bae91c989a55dad6960a9ecf8b01b36f8a5 +size 2469747 diff --git a/data/internet/category_names.csv b/data/internet/category_names.csv new file mode 100644 index 0000000..cb5a8b4 --- /dev/null +++ b/data/internet/category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef317f51f97839d1d436fd93f13b1e01a70fc79d3c5e0938961069b2b1b4e3b +size 998507 diff --git a/data/internet/combined_label_names.csv b/data/internet/combined_label_names.csv new file mode 100644 index 0000000..f6b65ce --- /dev/null +++ b/data/internet/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7454adb6526b660c76d11d869383fced4cc7e76e482cafb1b538fd7bc806ca +size 3781635 diff --git a/data/internet/domain_concept.csv b/data/internet/domain_concept.csv new file mode 100644 index 0000000..1a988a3 --- /dev/null +++ b/data/internet/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a7a18d939ac013c55b84c4a367784b75a80ec9f1eda5aceb5d4c01cc67d15e +size 112447 diff --git a/data/internet/hierarchical_category_names.csv b/data/internet/hierarchical_category_names.csv new file mode 100644 index 0000000..51e5f6b --- /dev/null +++ b/data/internet/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ce025138340ca75c2fdc7ed59b20f22ea20c5f4d5c7025aad765c95d63e2fb +size 977664 diff --git a/data/internet/keyphrases_names.csv b/data/internet/keyphrases_names.csv new file mode 100644 index 0000000..572bcc0 --- /dev/null +++ b/data/internet/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f5118f2975412e3d97ab5ec51990b3e50543160c98509bc229848e64b2af573 +size 1030923 diff --git a/data/internet/keyword_names.csv b/data/internet/keyword_names.csv new file mode 100644 index 0000000..86cd2e7 --- /dev/null +++ b/data/internet/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d2519ee9227af338c05f4b0142e8019fcd91fc3e9630255dd8dc0505fa01cc +size 1365909 diff --git a/data/internet/lda_label_names.csv b/data/internet/lda_label_names.csv new file mode 100644 index 0000000..a305cdb --- /dev/null +++ b/data/internet/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0efb99e2305d969a58bc9469217c656b3311ad75e10b3497a51308f158ba997e +size 2179 diff --git a/data/internet/link_names.csv b/data/internet/link_names.csv new file mode 100644 index 0000000..f5de7c9 --- /dev/null +++ b/data/internet/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aefcfdb9a691dca28d29a1c04adbc8736b8286dc0faf68a26b104a30aa2cae81 +size 363396 diff --git a/data/internet/popularity_score.csv b/data/internet/popularity_score.csv new file mode 100644 index 0000000..52c7613 --- /dev/null +++ b/data/internet/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fddb62d093d63491480aae6211c4c65c5f86c6675cfa351ebafc99437ff0eb0 +size 48501 diff --git a/data/media/article_categories.csv b/data/media/article_categories.csv new file mode 100644 index 0000000..a5961f9 --- /dev/null +++ b/data/media/article_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5335a85fb05d989daa66146f61b31d504163e7dc91ec41d28645767252b74692 +size 2414085 diff --git a/data/media/article_hierarchical_categories.csv b/data/media/article_hierarchical_categories.csv new file mode 100644 index 0000000..9c4995b --- /dev/null +++ b/data/media/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b926a8672ed78b1d95bfd8882a2b7ad4cfee8c535da72b462c3745bbbe09abf0 +size 1648736 diff --git a/data/media/article_keyphrases.csv b/data/media/article_keyphrases.csv new file mode 100644 index 0000000..9e66b18 --- /dev/null +++ b/data/media/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39371a3d7bdfb984d2796bec56b798f90d3f818f7e000819d9d3b27a51dd19ad +size 6863569 diff --git a/data/media/article_keywords.csv b/data/media/article_keywords.csv new file mode 100644 index 0000000..c71f2a7 --- /dev/null +++ b/data/media/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb0933a4cc912d8e1230fbaf39084b01b2c17239173f838d98b9e559a53a0b1 +size 1637515 diff --git a/data/media/article_labels_combined.csv b/data/media/article_labels_combined.csv new file mode 100644 index 0000000..779a9d5 --- /dev/null +++ b/data/media/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2b9141f316da889d0b14f30c256d1c41dc879e7d82d1c7637af1af34a6ba35 +size 6583832 diff --git a/data/media/article_lda_labels.csv b/data/media/article_lda_labels.csv new file mode 100644 index 0000000..18f8ef1 --- /dev/null +++ b/data/media/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fdf09cc242aa96992149c331bae82a80cfbfb7d7f93c5485825e08780d90479 +size 7112272 diff --git a/data/media/article_links.csv b/data/media/article_links.csv new file mode 100644 index 0000000..8416d7c --- /dev/null +++ b/data/media/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbb3936331254782fd9d35f330079d57cbb23f5df538c4136c3fcada1a253d8 +size 222321 diff --git a/data/media/article_text.csv b/data/media/article_text.csv new file mode 100644 index 0000000..1734273 --- /dev/null +++ b/data/media/article_text.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06c3481c98209970d6fb43fa0fff673aebd63e447c6c1fcf3146c76d47cdf93 +size 24310860 diff --git a/data/media/article_vectors.csv b/data/media/article_vectors.csv new file mode 100644 index 0000000..3f2773f --- /dev/null +++ b/data/media/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc206f025a578a388a9621878a867554f60bd81d14375791276ba2cb03a7f923 +size 1451925 diff --git a/data/media/category_names.csv b/data/media/category_names.csv new file mode 100644 index 0000000..147750e --- /dev/null +++ b/data/media/category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb3e28e3257baf609e65e37c87d8c81a70f63186542896ea57e1461d5813417 +size 1510232 diff --git a/data/media/combined_label_names.csv b/data/media/combined_label_names.csv new file mode 100644 index 0000000..96c9a77 --- /dev/null +++ b/data/media/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b21f16cdfcc46731477b7a8e82c4555ea0e5d4efe7647bac18f2dba5e5a098 +size 3624681 diff --git a/data/media/domain_concept.csv b/data/media/domain_concept.csv new file mode 100644 index 0000000..186eea6 --- /dev/null +++ b/data/media/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f675b853d53935b2f9f9d338f0cdc479d797715edcb5d71f8b48b299cc4348 +size 59939 diff --git a/data/media/hierarchical_category_names.csv b/data/media/hierarchical_category_names.csv new file mode 100644 index 0000000..5e985df --- /dev/null +++ b/data/media/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d330f2322029bc7707b1a297b91e9823f460cb8fb8792a3920d5bdd5bb3b695 +size 1369038 diff --git a/data/media/keyphrases_names.csv b/data/media/keyphrases_names.csv new file mode 100644 index 0000000..17ac6bb --- /dev/null +++ b/data/media/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45cc5068e1b345a8c1d81c2f00336b42c27f4dde80b3dcb98de949cf3493fdf4 +size 1906720 diff --git a/data/media/keyword_names.csv b/data/media/keyword_names.csv new file mode 100755 index 0000000..72bc26e --- /dev/null +++ b/data/media/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c0b0675f5058469eb425363656688be34afaf7f6a358e5de76ad51ed4e4cf2 +size 1121785 diff --git a/data/media/lda_label_names.csv b/data/media/lda_label_names.csv new file mode 100644 index 0000000..3e8d7ec --- /dev/null +++ b/data/media/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5c47a4e98680eaa2cc7a7a998e707c246ea411876ecc342cc4312c30a6a523 +size 2604 diff --git a/data/media/link_names.csv b/data/media/link_names.csv new file mode 100644 index 0000000..5e3b864 --- /dev/null +++ b/data/media/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0427f4a8c287e11ca9973f3638129b2a5f5d86eccae08fc5117cfded33b325 +size 312771 diff --git a/data/media/popularity_score.csv b/data/media/popularity_score.csv new file mode 100644 index 0000000..fa65ac6 --- /dev/null +++ b/data/media/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beee372da812b18cfc199b149c6c98c412e8d9d0e09282ebb81233b65211ed13 +size 25446 diff --git a/data/original_nav_vectors.txt b/data/original_nav_vectors.txt new file mode 100644 index 0000000..7184481 --- /dev/null +++ b/data/original_nav_vectors.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de19ff63cda5373ea1a143d1576f4072a8f64f4794ee182c443264c27ae1e9f2 +size 1770504334 diff --git a/data/politics/domain_concept.csv b/data/politics/domain_concept.csv new file mode 100644 index 0000000..11763ae --- /dev/null +++ b/data/politics/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9dbd77efdf88f34714afbad1cf8c771019f0ee6c38d912f6a4e5c7d93af1af +size 116055 diff --git a/data/science/article_categories.csv b/data/science/article_categories.csv new file mode 100644 index 0000000..97790ac --- /dev/null +++ b/data/science/article_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6acbde6a6510980c88d1dbd1fd570e3f8bbdd4d6668da51440760bcbad3b923a +size 1481321 diff --git a/data/science/article_hierarchical_categories.csv b/data/science/article_hierarchical_categories.csv new file mode 100644 index 0000000..239015d --- /dev/null +++ b/data/science/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f61a86f442b6f074a1deac3a6409d9e3f4e99318f3e10cc81b805b19f58dcfd +size 1192302 diff --git a/data/science/article_keyphrases.csv b/data/science/article_keyphrases.csv new file mode 100644 index 0000000..46f42e9 --- /dev/null +++ b/data/science/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47344a0ac75426a0bbf23604e740fc5cc38e2c1f5b07c1caf00cedeec3d977d9 +size 5136601 diff --git a/data/science/article_keywords.csv b/data/science/article_keywords.csv new file mode 100644 index 0000000..f4c3d34 --- /dev/null +++ b/data/science/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6707a9a5717e3c6196b6e9ac6240c5a5395cf270a0b097447403d6042c974cb6 +size 3917059 diff --git a/data/science/article_labels_combined.csv b/data/science/article_labels_combined.csv new file mode 100644 index 0000000..65ad0df --- /dev/null +++ b/data/science/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c584650a7ac4383812f9d537f7676b37da0839a00ebf3e80c3b9d47cc4c56f02 +size 4375307 diff --git a/data/science/article_lda_labels.csv b/data/science/article_lda_labels.csv new file mode 100644 index 0000000..b4ab4d1 --- /dev/null +++ b/data/science/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7a5956f78196c7df7449fdd2c0bb3aa865cb9c8c7acca8ae858f470b98e9d0 +size 7961249 diff --git a/data/science/article_links.csv b/data/science/article_links.csv new file mode 100644 index 0000000..fa6c50a --- /dev/null +++ b/data/science/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d49163b0a82067e8a7002922579c4d3facc7e2b9d23aa50214771b4d61b417d +size 141902 diff --git a/data/science/article_text.csv b/data/science/article_text.csv new file mode 100644 index 0000000..b1a118a --- /dev/null +++ b/data/science/article_text.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b7479c88fbad3ea089ecc58434cce5f6858f8d9b5c20b0aa406bc8c54e31cc +size 14352891 diff --git a/data/science/article_vectors.csv b/data/science/article_vectors.csv new file mode 100644 index 0000000..6ae4975 --- /dev/null +++ b/data/science/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9027b0037191130072ab120dd318fbb7cab7c9d078d96cd28a65cc88803495e4 +size 792425 diff --git a/data/science/category_names.csv b/data/science/category_names.csv new file mode 100644 index 0000000..23ee5f1 --- /dev/null +++ b/data/science/category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b41411727f783130728151ce99daa82d4ba8df5369229b581ca63a78ed65fa +size 988365 diff --git a/data/science/combined_label_names.csv b/data/science/combined_label_names.csv new file mode 100644 index 0000000..488c386 --- /dev/null +++ b/data/science/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65144d10eacac151195753d87326eef2bcfb381c2c1e56125fc5b14c7a0ae410 +size 2492290 diff --git a/data/science/domain_concept.csv b/data/science/domain_concept.csv new file mode 100644 index 0000000..b37588a --- /dev/null +++ b/data/science/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1895670b8bc9dc69a75e2b137396580223f7eca49d0ebfab3d0b60731741e1 +size 107338 diff --git a/data/science/hierarchical_category_names.csv b/data/science/hierarchical_category_names.csv new file mode 100644 index 0000000..0614ea7 --- /dev/null +++ b/data/science/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c60e2f27d8bb436a47c4ed1df290a9ac718de3fbd036496daa540eeb639c589 +size 942882 diff --git a/data/science/keyphrases_names.csv b/data/science/keyphrases_names.csv new file mode 100644 index 0000000..6b47d75 --- /dev/null +++ b/data/science/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12861159e09ea2bfc576d52007a4142b1081ebbd3465359f60d388f320eefe77 +size 1372036 diff --git a/data/science/keyword_names.csv b/data/science/keyword_names.csv new file mode 100644 index 0000000..c213581 --- /dev/null +++ b/data/science/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7457341e3e5b65c328d72fd37ae8ab4432cd61abac16fe24113a4dfcceb15859 +size 739642 diff --git a/data/science/lda_label_names.csv b/data/science/lda_label_names.csv new file mode 100644 index 0000000..8afa512 --- /dev/null +++ b/data/science/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcfc9ae8a5da6a698d7b0bac2fc75ea957102b2d9428185b02f8659970a3a89 +size 3290 diff --git a/data/science/link_names.csv b/data/science/link_names.csv new file mode 100644 index 0000000..dbd3178 --- /dev/null +++ b/data/science/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd100e29b26019e94fc8565a41d4599f39b26a382082730ccb532a7df9cf37fd +size 248815 diff --git a/data/science/popularity_score.csv b/data/science/popularity_score.csv new file mode 100644 index 0000000..3c00c59 --- /dev/null +++ b/data/science/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d5c01cae00cd1ba9d665ebeb6a95166945c9af118aabb376b23a0c1ee1d38c +size 29025 diff --git a/data/technology/article_categories.csv b/data/technology/article_categories.csv new file mode 100644 index 0000000..82cbab2 --- /dev/null +++ b/data/technology/article_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce016045f1a230eb3c9dbc2626aa8a82a444ff300bb4a75e9896d028ca9561f1 +size 2119110 diff --git a/data/technology/article_hierarchical_categories.csv b/data/technology/article_hierarchical_categories.csv new file mode 100644 index 0000000..0a79f77 --- /dev/null +++ b/data/technology/article_hierarchical_categories.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88b9adb57fee54d476bd538106e7f8e055a874e1c8f05d89ba40d8c2804f9cd +size 2020710 diff --git a/data/technology/article_keyphrases.csv b/data/technology/article_keyphrases.csv new file mode 100644 index 0000000..a29433f --- /dev/null +++ b/data/technology/article_keyphrases.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f454139d0f6a3c221a902bb12d272e62b48d2a6d2d822efbaa1bf26431fcb5ed +size 14208263 diff --git a/data/technology/article_keywords.csv b/data/technology/article_keywords.csv new file mode 100644 index 0000000..3e6c5de --- /dev/null +++ b/data/technology/article_keywords.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b679b3b267734d4f4808c721609b7b7bc2eebd20dced17944be5fd2f95947d +size 15951222 diff --git a/data/technology/article_labels_combined.csv b/data/technology/article_labels_combined.csv new file mode 100644 index 0000000..4cef964 --- /dev/null +++ b/data/technology/article_labels_combined.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a805b030092f9fa4c94485706859a37ec60cd5010ed452c5d5f4720c8160256b +size 12909528 diff --git a/data/technology/article_lda_labels.csv b/data/technology/article_lda_labels.csv new file mode 100644 index 0000000..c527e38 --- /dev/null +++ b/data/technology/article_lda_labels.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4e885c5ff5d0df6f3d9d1c06208509a040d6a181f541af2ac66b5c7bc42bb9 +size 13517949 diff --git a/data/technology/article_links.csv b/data/technology/article_links.csv new file mode 100644 index 0000000..6754aff --- /dev/null +++ b/data/technology/article_links.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f52bd5dd329c4fefb01fa50c2cda6d6f6f63142906960541ea54e1ede180f4 +size 470827 diff --git a/data/technology/article_text.csv b/data/technology/article_text.csv new file mode 100644 index 0000000..39cbc35 --- /dev/null +++ b/data/technology/article_text.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2140cb2ff7f9a9897a5bfc01403df0150a867bae6246fac617ba51103dca8a2e +size 58459178 diff --git a/data/technology/article_vectors.csv b/data/technology/article_vectors.csv new file mode 100644 index 0000000..8cac239 --- /dev/null +++ b/data/technology/article_vectors.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:340ed995a0d37e1ccada9b50ee71b7b0fc2ff70e04475164a866e34c08f58cdc +size 3586773 diff --git a/data/technology/category_names.csv b/data/technology/category_names.csv new file mode 100644 index 0000000..8e01573 --- /dev/null +++ b/data/technology/category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94485f2cfae5c22199f3c0ec7f48219079fde068f41378881a22e97df0150ab +size 1161324 diff --git a/data/technology/combined_label_names.csv b/data/technology/combined_label_names.csv new file mode 100644 index 0000000..b7976df --- /dev/null +++ b/data/technology/combined_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdca01af97819c964cc073f5d6660266bed735cbd4587d52173f14219fbccb1 +size 5787701 diff --git a/data/technology/domain_concept.csv b/data/technology/domain_concept.csv new file mode 100644 index 0000000..6ebc085 --- /dev/null +++ b/data/technology/domain_concept.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff414559ffb0274106b085e3453227fc58ffec22ef369a53d375be0321d261dd +size 113411 diff --git a/data/technology/hierarchical_category_names.csv b/data/technology/hierarchical_category_names.csv new file mode 100644 index 0000000..f512e46 --- /dev/null +++ b/data/technology/hierarchical_category_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f46dd56be9817a2b172567114fccbb2d98f7a82d6641e96641ff962aef5073f +size 1138088 diff --git a/data/technology/keyphrases_names.csv b/data/technology/keyphrases_names.csv new file mode 100644 index 0000000..e7e9653 --- /dev/null +++ b/data/technology/keyphrases_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35536cc6ae0f7d6b6f64d8ee318a831fe970fafa1e501ba8fccba0208a59b56d +size 3278601 diff --git a/data/technology/keyword_names.csv b/data/technology/keyword_names.csv new file mode 100644 index 0000000..7630ade --- /dev/null +++ b/data/technology/keyword_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571a254610c1c4708aa7712afbed58eb9e69b234a7ff3394f64195dcac38892f +size 697663 diff --git a/data/technology/lda_label_names.csv b/data/technology/lda_label_names.csv new file mode 100644 index 0000000..56104dc --- /dev/null +++ b/data/technology/lda_label_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f854dd6b8da88a02846526f159f0937f14d4113dbae475bfcfa66706f85ab6 +size 2336 diff --git a/data/technology/link_names.csv b/data/technology/link_names.csv new file mode 100644 index 0000000..a1963f5 --- /dev/null +++ b/data/technology/link_names.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b4f83a701faa108d8424ec7dd7272052fad0fe452c0928ee9a98c4a1d23b9b +size 578104 diff --git a/data/technology/popularity_score.csv b/data/technology/popularity_score.csv new file mode 100644 index 0000000..265d8bc --- /dev/null +++ b/data/technology/popularity_score.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4231f654264848bf263d4226796fe592827f92b28f9dc31e96dcd5da763e15 +size 51276