build_dataset.py 文件源码

def make_sessions(data, session_th=30 * 60, is_ordered=False, user_key='user_id', item_key='item_id', time_key='ts'):
    """Assigns session ids to the events in data without grouping keys"""
    if not is_ordered:
        # sort data by user and time
        data.sort_values(by=[user_key, time_key], ascending=True, inplace=True)
    # compute the time difference between queries
    tdiff = np.diff(data[time_key].values)
    # check which of them are bigger then session_th
    split_session = tdiff > session_th
    split_session = np.r_[True, split_session]
    # check when the user chenges is data
    new_user = data['user_id'].values[1:] != data['user_id'].values[:-1]
    new_user = np.r_[True, new_user]
    # a new sessions stars when at least one of the two conditions is verified
    new_session = np.logical_or(new_user, split_session)
    # compute the session ids
    session_ids = np.cumsum(new_session)
    data['session_id'] = session_ids
    return data