def get_dummies(data,
prefix=None,
prefix_sep='_',
dummy_na=False,
columns=None,
sparse=False,
drop_first=False,
dtype=None):
"""
Convert categorical variable into dummy/indicator variables, also
known as one hot encoding.
Parameters
----------
data : array-like, Series, or DataFrame
prefix : string, list of strings, or dict of strings, default None
String to append DataFrame column names.
Pass a list with length equal to the number of columns
when calling get_dummies on a DataFrame. Alternatively, `prefix`
can be a dictionary mapping column names to prefixes.
prefix_sep : string, default '_'
If appending prefix, separator/delimiter to use. Or pass a
list or dictionary as with `prefix.`
dummy_na : bool, default False
Add a column to indicate NaNs, if False NaNs are ignored.
columns : list-like, default None
Column names in the DataFrame to be encoded.
If `columns` is None then all the columns with
`object` or `category` dtype will be converted.
sparse : bool, default False
Whether the dummy-encoded columns should be be backed by
a :class:`SparseArray` (True) or a regular NumPy array (False).
In Koalas, this value must be "False".
drop_first : bool, default False
Whether to get k-1 dummies out of k categorical levels by removing the
first level.
dtype : dtype, default np.uint8
Data type for new columns. Only a single dtype is allowed.
Returns
-------
dummies : DataFrame
See Also
--------
Series.str.get_dummies
Examples
--------
>>> s = ks.Series(list('abca'))
>>> ks.get_dummies(s)
a b c
0 1 0 0
1 0 1 0
2 0 0 1
3 1 0 0
>>> df = ks.DataFrame({'A': ['a', 'b', 'a'], 'B': ['b', 'a', 'c'],
... 'C': [1, 2, 3]},
... columns=['A', 'B', 'C'])
>>> ks.get_dummies(df, prefix=['col1', 'col2'])
C col1_a col1_b col2_a col2_b col2_c
0 1 1 0 0 1 0
1 2 0 1 1 0 0
2 3 1 0 0 0 1
>>> ks.get_dummies(ks.Series(list('abcaa')))
a b c
0 1 0 0
1 0 1 0
2 0 0 1
3 1 0 0
4 1 0 0
>>> ks.get_dummies(ks.Series(list('abcaa')), drop_first=True)
b c
0 0 0
1 1 0
2 0 1
3 0 0
4 0 0
>>> ks.get_dummies(ks.Series(list('abc')), dtype=float)
a b c
0 1.0 0.0 0.0
1 0.0 1.0 0.0
2 0.0 0.0 1.0
"""
if sparse is not False:
raise NotImplementedError(
"get_dummies currently does not support sparse")
if isinstance(columns, str):
columns = [columns]
if dtype is None:
dtype = 'byte'
if isinstance(data, Series):
if prefix is not None:
prefix = [str(prefix)]
columns = [data.name]
kdf = data.to_dataframe()
remaining_columns = []
else:
if isinstance(prefix, str):
raise ValueError(
"get_dummies currently does not support prefix as string types"
)
kdf = data.copy()
if columns is None:
columns = [
column for column in kdf.columns
if isinstance(data._sdf.schema[column].dataType,
_get_dummies_default_accept_types)
]
if len(columns) == 0:
return kdf
if prefix is None:
prefix = columns
column_set = set(columns)
remaining_columns = [
kdf[column] for column in kdf.columns if column not in column_set
]
if any(not isinstance(kdf._sdf.schema[column].dataType,
_get_dummies_acceptable_types)
for column in columns):
raise ValueError("get_dummies currently only accept {} values".format(
', '.join([t.typeName() for t in _get_dummies_acceptable_types])))
if prefix is not None and len(columns) != len(prefix):
raise ValueError(
"Length of 'prefix' ({}) did not match the length of the columns being encoded ({})."
.format(len(prefix), len(columns)))
all_values = _reduce_spark_multi(
kdf._sdf,
[F.collect_set(F.col(column)).alias(column) for column in columns])
for i, column in enumerate(columns):
values = sorted(all_values[i])
if drop_first:
values = values[1:]
def column_name(value):
if prefix is None:
return str(value)
else:
return '{}{}{}'.format(prefix[i], prefix_sep, value)
for value in values:
remaining_columns.append(
(kdf[column].notnull() &
(kdf[column] == value)).astype(dtype).rename(
column_name(value)))
if dummy_na:
remaining_columns.append(kdf[column].isnull().astype(dtype).rename(
column_name('nan')))
return kdf[remaining_columns]
def get_dummies(data,
prefix=None,
prefix_sep='_',
dummy_na=False,
columns=None,
sparse=False,
drop_first=False,
dtype=None):
if sparse is not False:
raise NotImplementedError(
"get_dummies currently does not support sparse")
if isinstance(columns, string_types):
columns = [columns]
if dtype is None:
dtype = 'byte'
if isinstance(data, Series):
if prefix is not None:
prefix = [str(prefix)]
columns = [data.name]
kdf = data.to_dataframe()
remaining_columns = []
else:
if isinstance(prefix, string_types):
raise ValueError(
"get_dummies currently does not support prefix as string types"
)
kdf = data.copy()
if columns is None:
columns = [
column for column in kdf.columns
if isinstance(data._sdf.schema[column].dataType,
_get_dummies_default_accept_types)
]
if len(columns) == 0:
return kdf
if prefix is None:
prefix = columns
column_set = set(columns)
remaining_columns = [
kdf[column] for column in kdf.columns if column not in column_set
]
if any(not isinstance(kdf._sdf.schema[column].dataType,
_get_dummies_acceptable_types)
for column in columns):
raise ValueError("get_dummies currently only accept {} values".format(
', '.join([t.typeName() for t in _get_dummies_acceptable_types])))
if prefix is not None and len(columns) != len(prefix):
raise ValueError(
"Length of 'prefix' ({}) did not match the length of the columns being encoded ({})."
.format(len(prefix), len(columns)))
all_values = _reduce_spark_multi(
kdf._sdf,
[F.collect_set(F.col(column)).alias(column) for column in columns])
for i, column in enumerate(columns):
values = sorted(all_values[i])
if drop_first:
values = values[1:]
def column_name(value):
if prefix is None:
return str(value)
else:
return '{}{}{}'.format(prefix[i], prefix_sep, value)
for value in values:
remaining_columns.append(
(kdf[column].notnull() &
(kdf[column] == value)).astype(dtype).rename(
column_name(value)))
if dummy_na:
remaining_columns.append(kdf[column].isnull().astype(dtype).rename(
column_name('nan')))
return kdf[remaining_columns]