def __resampleData(self, data: pd.Series, resampleFreq: str,
aggStrategy: str) -> pd.Series:
if len(data) == 0:
return data
if pd.isna(resampleFreq):
return data
if not (resampleFreq.lower() in ['s', 'm', 'b', 'h', 'd']):
return data
if pd.isna(aggStrategy) or (aggStrategy.lower() == 'raw'):
return data
# storing series labels
seriesName = data.name
indName = data.index.name
# changing series labels
data.name = 'vals'
data.index.name = 'times'
data = data.reset_index()
# modify times as per resampleFreq
# https://stackoverflow.com/questions/43400331/remove-seconds-and-minutes-from-a-pandas-dataframe-column
if resampleFreq.lower() == 'd':
data = data.assign(times=data.times.dt.floor('D'))
elif resampleFreq.lower() == 'h':
data = data.assign(times=data.times.dt.floor('H'))
elif resampleFreq.lower() == 'm':
data = data.assign(times=data.times.dt.floor('min'))
elif resampleFreq.lower() == 's':
data = data.assign(times=data.times.dt.floor('S'))
elif resampleFreq.lower() == 'b':
data = data.assign(times=data.times.dt.floor('min'))
data.times = data.times.map(
lambda x: x.replace(minute=(x.minute - x.minute % 15)))
# aggregate the samples based on times
if aggStrategy.lower() == 'snap':
data = data.groupby('times', as_index=False).first()
elif aggStrategy.lower() == 'average':
data = data.groupby('times', as_index=False).mean()
data = pd.Series(data.vals.values, index=data.times.values)
# restore original labels
data.name = seriesName
data.index.name = indName
return data
