def test_hdfstore_timeseries_manager_sorted(self, tmpdir):
"""Check hdfstore returns a sorted index dataframe"""
t_start1 = dt.datetime(2017, 1, 1)
t_end1 = dt.datetime(2017, 1, 6)
index1 = pd.date_range(t_start1, t_end1, freq='D', closed='left')
t_start2 = dt.datetime(2017, 1, 3)
t_end2 = dt.datetime(2017, 1, 5)
index2 = pd.date_range(t_start2, t_end2, freq='D', closed='left')
df1 = pd.DataFrame({'data': range(len(index1))}, index=index1)
df2 = pd.DataFrame({'data': range(len(index2))}, index=index2)
mgr = HDFStoreTimeseriesMgr(str(tmpdir))
mgr.set('test', 'df', Timeseries.from_dataframe(df1))
mgr.set('test', 'df', Timeseries.from_dataframe(df2))
ts_out = mgr.get('test', 'df', t_start=t_start1, t_end=t_end1)
assert ts_out.dataframe.index.equals(index1)
def tsload(data_list):
"""Deserialize timeseries values from a dict to a structured DataFrame.
:param list data_list: Timeseries values (as a list of dicts).
:return Timeseries: Timeseries values loaded in structured DataFrame.
"""
if not data_list:
return Timeseries()
# Create dataframe and rename columns
dataframe = pd.DataFrame(data_list)
dataframe = dataframe.rename(
columns={
'timestamp': Timeseries.TIMESTAMPS_COL,
'value': Timeseries.DATA_COL,
'update_ts': Timeseries.UPDATE_TIMESTAMP_COL,
'quality': Timeseries.QUALITY_COL,
})
# Reject if duplicate indexes
dups = dataframe[Timeseries.TIMESTAMPS_COL].duplicated()
if any(dups):
abort(422,
errors={
'data':
'{} duplicate indexe(s)'.format(np.count_nonzero(dups))
})
# Create and return timeseries
return Timeseries.from_dataframe(dataframe)
def test_timeseries_stats(self):
index = [
dt.datetime(2017, 1, 5),
dt.datetime(2017, 1, 1),
dt.datetime(2017, 1, 8),
dt.datetime(2017, 1, 3),
]
data = [1, 2, 3, 4]
df = pd.DataFrame({'data': data}, index=index)
ts = Timeseries.from_dataframe(df)
assert ts.stats() == {
'count': 4,
'start': dt.datetime(2017, 1, 1),
'end': dt.datetime(2017, 1, 8),
'update_ts': ts.dataframe[Timeseries.UPDATE_TIMESTAMP_COL].max()
}
