data.py 文件源码

def parse_context_ftl(path):
    raw = read(path, "ftl")

    df = raw.copy()
    df['ut_ms'] = pd.to_datetime(raw['utb_ms'], unit='ms')
    df.sort_values("ut_ms", inplace=True)
    # dummies
    df = df.set_index('ut_ms')
    dummies = pd.get_dummies(df.type).join(df['flagcomms'], how="outer")
    dummies = dummies.resample("1h").sum().fillna(0.0)

    df = raw.copy()
    df['event'] = df.type + df.flagcomms.astype("str")
    del df['type'], df['flagcomms']
    df['ute_ms'] = pd.to_datetime(df['ute_ms'], unit='ms')
    df['utb_ms'] = pd.to_datetime(df['utb_ms'], unit='ms')
    durations = [event_to_min_per_hour(df, event) for event in df.event.unique()]
    durations = pd.concat(durations, axis=1).fillna(0)

    return dummies.join(durations, how="outer")