Top_Trending.py 文件源码

def resample_missing_values(df, date, period):
    df.set_index('date', inplace=True)
    # For duplicate values for same coordinates, the maximum value is chosen rather than average.
    df = (df.groupby(['lat', 'lon', 'countries'])).resample('D').max()
    df.reset_index(['lat', 'lon', 'countries'], drop=True, inplace=True)
    df['count'].fillna(0, inplace=True)
    df.groupby(['lat', 'lon', 'countries']).fillna(method='ffill', inplace=True)
    df.groupby(['lat', 'lon', 'countries']).fillna(method='bfill', inplace=True)
    df.reset_index(inplace=True)
    idx = pd.DatetimeIndex(start=date - dt.timedelta(days=(period - 1)), end=date, freq='D')
    new_df = pd.DataFrame()
    for index, group in df.groupby(['lat', 'lon', 'countries']):
        group = expand_date_range(group, idx)
        new_df = pd.concat([new_df, group])
    new_df.rename(columns={'index': 'date'}, inplace=True)
    return new_df