def test_deduplicate_timeseries_dataframe(self):
with pytest.raises(AssertionError):
deduplicate_timeseries_dataframe(self.df, dt_col="z")
with pytest.raises(AssertionError):
deduplicate_timeseries_dataframe(self.df, dt_col="a")
res_df = deduplicate_timeseries_dataframe(self.df, dt_col="datetime")
assert len(res_df) == 50
def deduplicate(self):
'''
Remove those duplicated records which has exactly the same values in each feature_col
for each multivariate timeseries distinguished by id_col.
:return: the tsdataset instance.
'''
self.df = deduplicate_timeseries_dataframe(df=self.df, dt_col=self.dt_col)
return self
def deduplicate(self):
'''
Remove those duplicated rows which has exactly the same values in each feature_col for
each multivariate timeseries distinguished by id_col
:return: the tsdataset instance.
Note: It is preferred that `deduplicate` is called before all other operations if needed.
'''
df_list = [deduplicate_timeseries_dataframe(df=self.df[self.df[self.id_col] == id_name],
dt_col=self.dt_col)
for id_name in self._id_list]
self.df = pd.concat(df_list)
return self
def deduplicate(self):
'''
Remove those duplicated records which has exactly the same values in each feature_col
for each multivariate timeseries distinguished by id_col.
:return: the tsdataset instance.
'''
df_list = [
deduplicate_timeseries_dataframe(
df=self.df[self.df[self.id_col] == id_name],
dt_col=self.dt_col) for id_name in self._id_list
]
self.df = pd.concat(df_list)
return self