data_retrieval.py 文件源码

def get_irrelevant_cited_papers(bad_papers, db_cursor, papers_table='papers'):
    """Retrieves the papers cited by the irrelevant papers given in input, from a SQL database.

    Args:
        bad_papers (list of dicts): the list of irrelevant papers, formatted as the output of :func:`data_retrieval.list2paper`
        db_cursor (:class:`MySQLdb.cursors.Cursor`): cursor of a SQL database in which there is a papers table
        papers_table (string): name of the papers table in the SQL database

    Returns:
        tuple of tuples: the results of the SQL query
    """
    citations = []
    for p in bad_papers:
        for c in p['citations']:
            citations.append([p['index'], c])

    citations_df = pd.DataFrame(citations, columns=['citing', 'cited'])
    cited = citations_df['cited'].unique()

    db_cursor.execute("SELECT id, title, abstract FROM papers p WHERE p.abstract != '' AND p.id IN (" + ','.join(["%s"] * len(cited)) + ")", tuple(cited))

    return db_cursor.fetchall()