def main(args): logger.info('Reading track dataset...') protocols_df = pd.read_pickle(PROTOCOLS_FILE_PATH) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() protocols = protocols_df['full_text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(protocols) logger.info('Writting results...') show_results(protocols_df, protocols, topics, args.output, args.format)
def main(args): logger.info('Reading track dataset...') git_df = pd.read_pickle(GIT_FILE_PATH) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() repos = git_df['full_text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(repos) logger.info('Writting results...') show_results(git_df, repos, topics, args.output, args.format)
def main(args): logger.info('Reading track dataset...') pmc_df = pd.read_pickle(PMC_FILE_PATH) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() articles = pmc_df['text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(articles) logger.info('Writting results...') show_author_results(pmc_df, articles, topics, args.output)
def main(args): logger.info('Loading article data...') pmc_df = load_articles_df(args.input, args.isFile) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() articles = pmc_df['text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(articles) logger.info('Writting results...') show_results(pmc_df, articles, topics, args.output, args.format)
def main(args): logger.info('Loading repository data...') git_df = load_repos_df(args.input, args.isFile, args.token) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() repos = git_df['full_text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(repos) logger.info('Writting results...') show_results(git_df, repos, topics, args.output, args.format)
def main(args): logger.info('Loading protocol data...') protocols_df = load_protocols_df(args.input, args.isFile) logger.info('Loading topic extraction model...') final_pipe = load_final_pipe() protocols = protocols_df['full_text_cleaned'].values logger.info('Predicting topics...') topics = final_pipe.transform(protocols) logger.info('Writting results...') show_results(protocols_df, protocols, topics, args.output, args.format)