def combine_mapped_with_other(self, other, np_func):
"""Combine `MappedArray` with other compatible object.
If other object is also `MappedArray`, their `id_arr` and `col_arr` must match."""
if isinstance(other, MappedArray):
checks.assert_array_equal(self.id_arr, other.id_arr)
checks.assert_array_equal(self.col_arr, other.col_arr)
other = other.values
return self.copy(mapped_arr=np_func(self.values, other))
def make_symmetric(arg):
"""Make `arg` symmetric.
The index and columns of the resulting DataFrame will be identical.
Requires the index and columns to have the same number of levels.
## Example
```python-repl
>>> import pandas as pd
>>> from vectorbt.base.reshape_fns import make_symmetric
>>> df = pd.DataFrame([[1, 2], [3, 4]], index=['a', 'b'], columns=['c', 'd'])
>>> make_symmetric(df)
a b c d
a NaN NaN 1.0 2.0
b NaN NaN 3.0 4.0
c 1.0 3.0 NaN NaN
d 2.0 4.0 NaN NaN
```
"""
checks.assert_type(arg, (pd.Series, pd.DataFrame))
arg = to_2d(arg)
if isinstance(arg.index, pd.MultiIndex) or isinstance(arg.columns, pd.MultiIndex):
checks.assert_type(arg.index, pd.MultiIndex)
checks.assert_type(arg.columns, pd.MultiIndex)
checks.assert_array_equal(arg.index.nlevels, arg.columns.nlevels)
names1, names2 = tuple(arg.index.names), tuple(arg.columns.names)
else:
names1, names2 = arg.index.name, arg.columns.name
if names1 == names2:
new_name = names1
else:
if isinstance(arg.index, pd.MultiIndex):
new_name = tuple(zip(*[names1, names2]))
else:
new_name = (names1, names2)
idx_vals = list(dict.fromkeys(np.concatenate((arg.index, arg.columns))))
arg = arg.copy()
if isinstance(arg.index, pd.MultiIndex):
unique_index = pd.MultiIndex.from_tuples(idx_vals, names=new_name)
arg.index.names = new_name
arg.columns.names = new_name
else:
unique_index = pd.Index(idx_vals, name=new_name)
arg.index.name = new_name
arg.columns.name = new_name
df_out = pd.DataFrame(index=unique_index, columns=unique_index)
df_out.loc[:, :] = arg
df_out[df_out.isnull()] = arg.transpose()
return df_out
def combine_mapped_with_other(
self: MappedArrayT, other: tp.Union["MappedArray", tp.ArrayLike],
np_func: tp.Callable[[tp.ArrayLike, tp.ArrayLike], tp.Array1d]
) -> MappedArrayT:
"""Combine `MappedArray` with other compatible object.
If other object is also `MappedArray`, their `id_arr` and `col_arr` must match."""
if isinstance(other, MappedArray):
checks.assert_array_equal(self.id_arr, other.id_arr)
checks.assert_array_equal(self.col_arr, other.col_arr)
other = other.values
return self.replace(mapped_arr=np_func(self.values, other))
def test_assert_array_equal(self):
index = ['x', 'y', 'z']
columns = ['a', 'b', 'c']
checks.assert_array_equal(np.array([1, 2, 3]), np.array([1, 2, 3]))
checks.assert_array_equal(pd.Series([1, 2, 3], index=index), pd.Series([1, 2, 3], index=index))
checks.assert_array_equal(pd.DataFrame([[1, 2, 3]], columns=columns), pd.DataFrame([[1, 2, 3]], columns=columns))
with pytest.raises(Exception) as e_info:
checks.assert_array_equal(np.array([1, 2]), np.array([1, 2, 3]))
def make_symmetric(arg: tp.SeriesFrame, sort: bool = True) -> tp.Frame:
"""Make `arg` symmetric.
The index and columns of the resulting DataFrame will be identical.
Requires the index and columns to have the same number of levels.
Pass `sort=False` if index and columns should not be sorted, but concatenated
and get duplicates removed.
Usage:
```pycon
>>> import pandas as pd
>>> from vectorbt.base.reshape_fns import make_symmetric
>>> df = pd.DataFrame([[1, 2], [3, 4]], index=['a', 'b'], columns=['c', 'd'])
>>> make_symmetric(df)
a b c d
a NaN NaN 1.0 2.0
b NaN NaN 3.0 4.0
c 1.0 3.0 NaN NaN
d 2.0 4.0 NaN NaN
```
"""
checks.assert_instance_of(arg, (pd.Series, pd.DataFrame))
df: tp.Frame = to_2d(arg)
if isinstance(df.index, pd.MultiIndex) or isinstance(
df.columns, pd.MultiIndex):
checks.assert_instance_of(df.index, pd.MultiIndex)
checks.assert_instance_of(df.columns, pd.MultiIndex)
checks.assert_array_equal(df.index.nlevels, df.columns.nlevels)
names1, names2 = tuple(df.index.names), tuple(df.columns.names)
else:
names1, names2 = df.index.name, df.columns.name
if names1 == names2:
new_name = names1
else:
if isinstance(df.index, pd.MultiIndex):
new_name = tuple(zip(*[names1, names2]))
else:
new_name = (names1, names2)
if sort:
idx_vals = np.unique(np.concatenate((df.index, df.columns))).tolist()
else:
idx_vals = list(dict.fromkeys(np.concatenate((df.index, df.columns))))
df_index = df.index.copy()
df_columns = df.columns.copy()
if isinstance(df.index, pd.MultiIndex):
unique_index = pd.MultiIndex.from_tuples(idx_vals, names=new_name)
df_index.names = new_name
df_columns.names = new_name
else:
unique_index = pd.Index(idx_vals, name=new_name)
df_index.name = new_name
df_columns.name = new_name
df = df.copy(deep=False)
df.index = df_index
df.columns = df_columns
df_out_dtype = np.promote_types(df.values.dtype,
np.min_scalar_type(np.nan))
df_out = pd.DataFrame(index=unique_index,
columns=unique_index,
dtype=df_out_dtype)
df_out.loc[:, :] = df
df_out[df_out.isnull()] = df.transpose()
return df_out
