def groupby_apply(self, by, apply_func_nb, *args, on_matrix=False, **kwargs):
"""See `vectorbt.generic.nb.groupby_apply_nb` and
`vectorbt.generic.nb.groupby_apply_matrix_nb` for `on_matrix=True`.
For `by`, see `pd.DataFrame.groupby`.
Example:
```python-repl
>>> mean_nb = njit(lambda col, i, a: np.nanmean(a))
>>> df.vbt.groupby_apply([1, 1, 2, 2, 3], mean_nb)
a b c
1 1.5 4.5 1.5
2 3.5 2.5 2.5
3 5.0 1.0 1.0
>>> mean_matrix_nb = njit(lambda i, a: np.nanmean(a))
>>> df.vbt.groupby_apply([1, 1, 2, 2, 3], mean_matrix_nb, on_matrix=True)
a b c
1 2.500000 2.500000 2.500000
2 2.833333 2.833333 2.833333
3 2.333333 2.333333 2.333333
```"""
checks.assert_numba_func(apply_func_nb)
regrouped = self._obj.groupby(by, axis=0, **kwargs)
groups = Dict()
for i, (k, v) in enumerate(regrouped.indices.items()):
groups[i] = np.asarray(v)
if on_matrix:
result = nb.groupby_apply_matrix_nb(self.to_2d_array(), groups, apply_func_nb, *args)
else:
result = nb.groupby_apply_nb(self.to_2d_array(), groups, apply_func_nb, *args)
return self.wrap_reduced(result, index=list(regrouped.indices.keys()))
def resample_apply(self,
freq,
apply_func_nb,
*args,
on_matrix=False,
**kwargs):
"""See `vectorbt.generic.nb.groupby_apply_nb` and
`vectorbt.generic.nb.groupby_apply_matrix_nb` for `on_matrix=True`.
For `freq`, see `pd.DataFrame.resample`.
Example:
```python-repl
>>> mean_nb = njit(lambda col, i, a: np.nanmean(a))
>>> print(df.vbt.resample_apply('2d', mean_nb))
a b c
2020-01-01 1.5 4.5 1.5
2020-01-03 3.5 2.5 2.5
2020-01-05 5.0 1.0 1.0
>>> mean_matrix_nb = njit(lambda i, a: np.nanmean(a))
>>> print(df.vbt.resample_apply('2d', mean_matrix_nb, on_matrix=True))
a b c
2020-01-01 2.500000 2.500000 2.500000
2020-01-03 2.833333 2.833333 2.833333
2020-01-05 2.333333 2.333333 2.333333
```"""
checks.assert_numba_func(apply_func_nb)
resampled = self._obj.resample(freq, axis=0, **kwargs)
groups = Dict()
for i, (k, v) in enumerate(resampled.indices.items()):
groups[i] = np.asarray(v)
if on_matrix:
result = nb.groupby_apply_matrix_nb(self.to_2d_array(), groups,
apply_func_nb, *args)
else:
result = nb.groupby_apply_nb(self.to_2d_array(), groups,
apply_func_nb, *args)
result_obj = self.wrap(result, index=list(resampled.indices.keys()))
resampled_arr = np.full(
(resampled.ngroups, self.to_2d_array().shape[1]), np.nan)
resampled_obj = self.wrap(resampled_arr,
index=pd.Index(list(resampled.groups.keys()),
freq=freq))
resampled_obj.loc[result_obj.index] = result_obj.values
return resampled_obj