def __init__(self, min_publications_per_author, topics_per_author):
self.load_data()
self.get_computed_TOM()
self.min_publications_per_author = min_publications_per_author
self.n_topics_per_author = topics_per_author
feature_names = zip(*sorted(self.topic_model.corpus.vocabulary.items(), key=lambda a: a[0]))[1]
self.dict_topic_top_words, \
self.dict_doc_top_topics, \
self.dict_topic_top_docs = nmf_clustering(data=None, doc_topic_mat=self.topic_model.document_topic_matrix,
topic_token_mat=self.topic_model.topic_word_matrix,
feature_names=feature_names)
def __init__(self, min_publications_per_author, topics_per_author):
self.load_data()
self.get_computed_TOM()
self.min_publications_per_author = min_publications_per_author
self.n_topics_per_author = topics_per_author
feature_names = zip(*sorted(self.topic_model.corpus.vocabulary.items(),
key=lambda a: a[0]))[1]
self.dict_topic_top_words, \
self.dict_doc_top_topics, \
self.dict_topic_top_docs = nmf_clustering(data=None, doc_topic_mat=self.topic_model.document_topic_matrix,
topic_token_mat=self.topic_model.topic_word_matrix,
feature_names=feature_names)
def create_nmf_graph():
one_pages = load_text_data("../../input/pdfs/1page/", "txt")
dict_topics = nmf_clustering(one_pages)
import pprint
pprint.pprint(dict_topics)
d3js_dict = defaultdict(list)
# import snap as sn
# G = sn.TUNGraph.New()
# for topic_idx, topic in dict_topics.iteritems():
pass
def __init__(self, theta, min_n_papers_per_author, n_topics_per_author, topic_topic=False):
self.load_computed_topics()
# self.dict_topic_top_words, self.dict_doc_top_topics, self.dict_topic_top_docs = nmf_clustering(self.one_pages)
feature_names = zip(*sorted(self.topic_model.corpus.vocabulary.items(), key=lambda a: a[0]))[1]
self.dict_topic_top_words, \
self.dict_doc_top_topics, \
self.dict_topic_top_docs = nmf_clustering(data=None, doc_topic_mat=self.topic_model.document_topic_matrix,
topic_token_mat=self.topic_model.topic_word_matrix,
feature_names=feature_names)
# return dict_topic_top_words, dict_doc_top_topics, dict_topic_top_docs
self.load_data()
self.theta = theta
self.min_publications_per_author = min_n_papers_per_author
self.n_topics_per_author = n_topics_per_author
self.topic_topic_recomms = topic_topic
def get_1page_topics():
one_pages = load_text_data("../../input/pdfs/1page/", "txt")
return nmf_clustering(one_pages)
def get_abstract_and_title_topics():
egc_df = get_EGC_articles(load_data_egc("../../input/RNTI_articles_export_fixed1347_ids.txt"))
egc_df["title+abstract"] = egc_df["title"] + " " + egc_df["abstract"].fillna("")
data = dict(zip(egc_df["id"].tolist(), egc_df["title+abstract"].tolist()))
return nmf_clustering(data, k=15)
def get_1page_topics():
one_pages = load_text_data("../../input/pdfs/1page/", "txt")
return nmf_clustering(one_pages)
def get_abstract_and_title_topics():
egc_df = get_EGC_articles(load_data_egc("../../input/RNTI_articles_export_fixed1347_ids.txt"))
egc_df["title+abstract"] = egc_df["title"] + " " + egc_df["abstract"].fillna("")
data = dict(zip(egc_df["id"].tolist(), egc_df["title+abstract"].tolist()))
return nmf_clustering(data, k=15)