def inverse_transform(self, X):
"""Inverse ordinal-encode the columns in `X`
Parameters
----------
X : array or dataframe
Either the NumPy, dask, or pandas version
Returns
-------
data : DataFrame
Dask array or dataframe will return a Dask DataFrame.
Numpy array or pandas dataframe will return a pandas DataFrame
"""
if isinstance(X, np.ndarray):
X = pd.DataFrame(X, columns=self.columns_)
elif isinstance(X, da.Array):
# later on we concat(..., axis=1), which requires
# known divisions. Suboptimal, but I think unavoidable.
unknown = np.isnan(X.chunks[0]).any()
if unknown:
lengths = blockwise(len, "i", X[:, 0], "i",
dtype="i8").compute()
X = X.copy()
chunks = (tuple(lengths), X.chunks[1])
X._chunks = chunks
X = dd.from_dask_array(X, columns=self.columns_)
big = isinstance(X, dd.DataFrame)
if big:
chunks = np.array(X.divisions)
chunks[-1] = chunks[-1] + 1
chunks = tuple(chunks[1:] - chunks[:-1])
X = X.copy()
for col in self.categorical_columns_:
if _HAS_CTD:
dtype = self.dtypes_[col]
categories, ordered = dtype.categories, dtype.ordered
else:
categories, ordered = self.dtypes_[col]
# use .values to avoid warning from pandas
codes = X[col].values
if big:
# dask
codes._chunks = (chunks, )
# Need a Categorical.from_codes for dask
series = (dd.from_dask_array(
codes, columns=col).astype("category").cat.set_categories(
np.arange(len(categories)),
ordered=ordered).cat.rename_categories(categories))
# Bug in pandas <= 0.20.3 lost name
if series.name is None:
series.name = col
series.divisions = X.divisions
else:
# pandas
series = pd.Series(
pd.Categorical.from_codes(codes,
categories,
ordered=ordered),
name=col,
)
X[col] = series
return X
def inverse_transform(self, X):
"""Inverse dummy-encode the columns in `X`
Parameters
----------
X : array or dataframe
Either the NumPy, dask, or pandas version
Returns
-------
data : DataFrame
Dask array or dataframe will return a Dask DataFrame.
Numpy array or pandas dataframe will return a pandas DataFrame
"""
if isinstance(X, np.ndarray):
X = pd.DataFrame(X, columns=self.transformed_columns_)
elif isinstance(X, da.Array):
# later on we concat(..., axis=1), which requires
# known divisions. Suboptimal, but I think unavoidable.
unknown = np.isnan(X.chunks[0]).any()
if unknown:
lengths = blockwise(len, "i", X[:, 0], "i",
dtype="i8").compute()
X = X.copy()
chunks = (tuple(lengths), X.chunks[1])
X._chunks = chunks
X = dd.from_dask_array(X, columns=self.transformed_columns_)
big = isinstance(X, dd.DataFrame)
if big:
chunks = np.array(X.divisions)
chunks[-1] = chunks[-1] + 1
chunks = tuple(chunks[1:] - chunks[:-1])
non_cat = X[list(self.non_categorical_columns_)]
cats = []
for col in self.categorical_columns_:
slice_ = self.categorical_blocks_[col]
if _HAS_CTD:
dtype = self.dtypes_[col]
categories, ordered = dtype.categories, dtype.ordered
else:
categories, ordered = self.dtypes_[col]
# use .values to avoid warning from pandas
cols_slice = list(X.columns[slice_])
if big:
inds = X[cols_slice].to_dask_array(lengths=chunks)
else:
inds = X[cols_slice].values
codes = inds.argmax(1)
if self.drop_first:
codes += 1
codes[(inds == 0).all(1)] = 0
if big:
# dask
codes._chunks = (chunks, )
# Need a Categorical.from_codes for dask
series = (dd.from_dask_array(
codes, columns=col).astype("category").cat.set_categories(
np.arange(len(categories)),
ordered=ordered).cat.rename_categories(categories))
# Bug in pandas <= 0.20.3 lost name
if series.name is None:
series.name = col
series.divisions = X.divisions
else:
# pandas
series = pd.Series(
pd.Categorical.from_codes(codes,
categories,
ordered=ordered),
name=col,
)
cats.append(series)
if big:
df = dd.concat([non_cat] + cats, axis=1)[list(self.columns_)]
else:
df = pd.concat([non_cat] + cats, axis=1)[self.columns_]
return df
