run.py 文件源码

def find_n_most_similar_articles(self):
        """
        Find the n most similar articles with the highest similarity score for each TMT article in the DataFrame.
        :return:
        """
        # Iterate over each article in DataFrame
        for index, row in self.df_article_vectors.iterrows():
            # Get the similarity scores of the current article compared to all other articles
            similarity_scores = self.similarity_score_dict[index]
            # Find the highest similarity scores in the similarity_score_dict until we have found the n most similar.
            for i in range(0, self.n_most_similar):
                # Find most similar article, i.e. with highest cosine similarity. Note: if Euclidean distance, then min!
                most_similar_article_index = max(similarity_scores, key=similarity_scores.get)
                most_similar_article_score = similarity_scores[most_similar_article_index]
                del similarity_scores[most_similar_article_index]
                # Find corresponding title and set it as most similar article i in DataFrame
                title = self.df_article_vectors.loc[most_similar_article_index]['title'].encode('utf-8')
                title_plus_score = "{} ({:.2f})".format(title, most_similar_article_score)
                self.df_article_vectors.set_value(index, 'most_similar_'+str(i+1), title_plus_score)