GitHub - jy00295005/ML: Project documents clusteirng

ML

==

silhouette_score_curve.py

采用不同k值计算数据的kmeans聚类轮廓系数，找出最优的k值

==

nuclear_physics_nsf_fp_fulltable.py

使用最优k值聚类，计算两个机构比例，入库

print group_count #聚类结构两个资助机构比例

## 将聚类结果写入数据库，需要时打开
# insert_results_into_mysql(doc_label_list, insert_table_name)

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
.idea		.idea
test_scripts		test_scripts
README.md		README.md
alchemy_cluster_kw.py		alchemy_cluster_kw.py
alchemyapi.py		alchemyapi.py
alchemyapi.pyc		alchemyapi.pyc
api_key.txt		api_key.txt
cluster_kw.py		cluster_kw.py
cluster_kw_test.py		cluster_kw_test.py
example.py		example.py
get_keywords_from api.py		get_keywords_from api.py
get_kw_api.py		get_kw_api.py
get_solr_data.py		get_solr_data.py
grid_search_term_words.py		grid_search_term_words.py
helper.py		helper.py
helper.pyc		helper.pyc
kw_tidif.py		kw_tidif.py
ngram_test.py		ngram_test.py
nlp_api.py		nlp_api.py
nuclear_physics_nsf_fp_fulltable.py		nuclear_physics_nsf_fp_fulltable.py
plot_pie.py		plot_pie.py
recompete_clustering.py		recompete_clustering.py
sci_clustering.py		sci_clustering.py
silhouette_score_curve.py		silhouette_score_curve.py
term_clustering_particle.py		term_clustering_particle.py
test.py		test.py
test_vect.py		test_vect.py
tests.py		tests.py

jy00295005/ML