data.py 文件源码

def event_to_min_per_hour(df, event):
    def hourly(start, end):
        ret = [(start.floor("1h"), 60 - start.minute)]
        t = start.ceil("1h")
        while t <= end:
            ret.append((t, 60))
            t += pd.Timedelta("1h")
        ret.append((end.floor("1h"), end.minute - 60))
        return ret

    df = df[df.event.str.contains(event)]

    res = []
    for i, (start, end, _) in df.iterrows():
        res += hourly(start, end)

    df = pd.DataFrame(res)
    df.columns = ['ut_ms', event + "_mins"]

    df = df.set_index('ut_ms')
    df = df.resample("1h").sum().fillna(0.0)
    return df