tasks.py 文件源码

def y_sum_by_time(x_arr, y_arr, top=None):
    df = pd.DataFrame({'Timestamp': pd.to_datetime(x_arr, unit='s'), 'Status': y_arr})
    df['Date'] = df['Timestamp'].apply(lambda x: "%d/%d/%d" % (x.day, x.month, x.year))
    df['Hour'] = df['Timestamp'].apply(lambda x: "%d" % (x.hour))
    df['Weekday'] = df['Timestamp'].apply(lambda x: "%s" % (x.weekday_name))

    times = ['Hour', 'Weekday', 'Date']

    result = {}

    for groupby in times:

        df_group = df.groupby(groupby, as_index=False).agg({'Status': np.sum})

        if top != None and top > 0:
            #df_group = df_group.nlargest(top, 'Status').sort(['Status', 'Hour'],ascending=False)
            idx = df_group.nlargest(top, 'Status') > 0
        else:
            idx = df_group['Status'].max() == df_group['Status']

        result[groupby] = {k: g['Status'].replace(np.nan, 'None').tolist() for k,g in df_group[idx].groupby(groupby)}

    return result