self.articles_bytopic_permonth(outfile3)
if __name__ == "__main__":
"""
use the trained model v2_2 to get topics for all articles
"""
model_name = "v2_2"
func_tokenizer = TfidfVectorizer(stop_words="english").build_tokenizer()
func_stemmer = PorterStemmer()
# load model
t0 = time.time()
recommender = Recommender(model_name, func_tokenizer, func_stemmer)
article_dict, article_dt = MyMongo().get_article_attri()
recommender.df_articles["dt"] = recommender.df_articles["url"].map(lambda x: article_dt.get(x, None))
topic_summary = TopicSummarizer(
recommender.df_articles,
recommender.W_articles,
recommender.sorted_topics_articles,
recommender.get_topic_names(),
)
topic_summary.write_data(
"../../webapp/static/articles_per_topic.csv",
"../../webapp/static/articles_per_month.csv",
"../../webapp/static/data.csv",
)
