resample_iot_tseries.py

def resample(tseries, rate='15T', short_rate='S', max_gap=None):
    """ Resample (unevenly spaced) timeseries data linearly by first upsampling to a
        high frequency (short_rate) then downsampling to the desired rate.
    
    :param tseries: a pandas timeseries object
    :param rate: rate that tseries should be resampled to
    :param short_rate: intermediate upsampling rate; if None, smallest interval of tseries is used
    :param max_gap: null intervals larger than `max_gap` are being treated as missing
        data and not interpolated. if None, always interpolate. must be provided as pandas
        frequency string format, e.g. '6h'
        
    Copyright (c) 2017 WATTx GmbH
    License: Apache License
    """
    # return series if empty
    if tseries.empty:
        return tseries

    # check for datetime index
    assert isinstance(
        tseries.index[0], pd.tslib.Timestamp), 'Object must have a datetime-like index.'

    # sort tseries by time
    tseries.sort_index(inplace=True)

    # create timedelta from frequency string
    rate_delta = to_offset(rate).delta

    # compute time intervals
    diff = np.diff(tseries.index) / np.timedelta64(1, 's')

    if max_gap is not None:
        # identify intervals in tseries larger than max_gap
        idx = np.where(np.greater(diff, to_offset(max_gap).delta.total_seconds()))[0]
        start = tseries.index[idx].tolist()
        stop = tseries.index[idx + 1].tolist()
        # store start and stop indices of large intervals
        big_gaps = list(zip(start, stop))

    if short_rate is None:
        # use minimal nonzero interval of original series as short_rate
        short_rate = '%dS' % diff[np.nonzero(diff)].min()
        # create timedelta from frequency string
        short_rate_delta = to_offset(short_rate).delta
        # if smallest interval is still larger than rate, use rate instead
        if short_rate_delta > rate_delta:
            short_rate = rate
    else:
        # convert frequency string to timedelta
        short_rate_delta = to_offset(short_rate).delta
        # make sure entered short_rate is smaller than rate
        assert rate_delta >= short_rate_delta, 'short_rate must be <= rate'

    # upsample to short_rate
    tseries = tseries.resample(short_rate, how='mean').interpolate()

    # downsample to desired rate
    tseries = tseries.resample(rate, how='ffill')

    # replace values in large gap itervals with NaN
    if max_gap is not None:
        for start, stop in big_gaps:
            tseries[start:stop] = None

    return tseries

Howdy! This would be very helpful for me right now, but where is the to_offset function defined?

Edit: Ah nevermind, I should have googled: from pandas.tseries.frequencies import to_offset

An alternative that might be more efficient is to use reindex (https://stackoverflow.com/a/40035879/2981639). As far as I can see this doesn't exhibit the shift introduced by resample().mean().interpolate()? The gap filter is quite useful!