maxframe 0.1.0b5__cp311-cp311-macosx_11_0_arm64.whl

maxframe/dataframe/misc/explode.py

@@ -0,0 +1,171 @@
+# Copyright 1999-2024 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import numpy as np
+import pandas as pd
+
+from ... import opcodes
+from ...core import OutputType
+from ...serialization.serializables import AnyField, BoolField
+from ..operators import DataFrameOperator, DataFrameOperatorMixin
+from ..utils import parse_index
+
+
+class DataFrameExplode(DataFrameOperator, DataFrameOperatorMixin):
+    _op_type_ = opcodes.EXPLODE
+
+    column = AnyField("column", default=None)
+    ignore_index = BoolField("ignore_field", default=None)
+
+    def __init__(self, output_types=None, **kw):
+        super().__init__(_output_types=output_types, **kw)
+
+    def _rewrite_params(self, in_obj):
+        params = in_obj.params.copy()
+        new_shape = list(in_obj.shape)
+        new_shape[0] = np.nan
+        params["shape"] = tuple(new_shape)
+
+        if self.ignore_index:
+            params["index_value"] = parse_index(
+                pd.RangeIndex(-1), (in_obj.key, in_obj.index_value.key)
+            )
+        else:
+            params["index_value"] = parse_index(
+                None, (in_obj.key, in_obj.index_value.key)
+            )
+        return params
+
+    def __call__(self, df_or_series):
+        return self.new_tileable([df_or_series], **self._rewrite_params(df_or_series))
+
+
+def df_explode(df, column, ignore_index=False):
+    """
+    Transform each element of a list-like to a row, replicating index values.
+
+    Parameters
+    ----------
+    column : str or tuple
+        Column to explode.
+    ignore_index : bool, default False
+        If True, the resulting index will be labeled 0, 1, …, n - 1.
+
+    Returns
+    -------
+    DataFrame
+        Exploded lists to rows of the subset columns;
+        index will be duplicated for these rows.
+
+    Raises
+    ------
+    ValueError :
+        if columns of the frame are not unique.
+
+    See Also
+    --------
+    DataFrame.unstack : Pivot a level of the (necessarily hierarchical)
+        index labels.
+    DataFrame.melt : Unpivot a DataFrame from wide format to long format.
+    Series.explode : Explode a DataFrame from list-like columns to long format.
+
+    Notes
+    -----
+    This routine will explode list-likes including lists, tuples,
+    Series, and np.ndarray. The result dtype of the subset rows will
+    be object. Scalars will be returned unchanged. Empty list-likes will
+    result in a np.nan for that row.
+
+    Examples
+    --------
+    >>> import maxframe.tensor as mt
+    >>> import maxframe.dataframe as md
+    >>> df = md.DataFrame({'A': [[1, 2, 3], 'foo', [], [3, 4]], 'B': 1})
+    >>> df.execute()
+               A  B
+    0  [1, 2, 3]  1
+    1        foo  1
+    2         []  1
+    3     [3, 4]  1
+
+    >>> df.explode('A').execute()
+         A  B
+    0    1  1
+    0    2  1
+    0    3  1
+    1  foo  1
+    2  NaN  1
+    3    3  1
+    3    4  1
+    """
+    op = DataFrameExplode(
+        column=column, ignore_index=ignore_index, output_types=[OutputType.dataframe]
+    )
+    return op(df)
+
+
+def series_explode(series, ignore_index=False):
+    """
+    Transform each element of a list-like to a row.
+
+    Parameters
+    ----------
+    ignore_index : bool, default False
+        If True, the resulting index will be labeled 0, 1, …, n - 1.
+
+    Returns
+    -------
+    Series
+        Exploded lists to rows; index will be duplicated for these rows.
+
+    See Also
+    --------
+    Series.str.split : Split string values on specified separator.
+    Series.unstack : Unstack, a.k.a. pivot, Series with MultiIndex
+        to produce DataFrame.
+    DataFrame.melt : Unpivot a DataFrame from wide format to long format.
+    DataFrame.explode : Explode a DataFrame from list-like
+        columns to long format.
+
+    Notes
+    -----
+    This routine will explode list-likes including lists, tuples,
+    Series, and np.ndarray. The result dtype of the subset rows will
+    be object. Scalars will be returned unchanged. Empty list-likes will
+    result in a np.nan for that row.
+
+    Examples
+    --------
+    >>> import maxframe.tensor as mt
+    >>> import maxframe.dataframe as md
+    >>> s = md.Series([[1, 2, 3], 'foo', [], [3, 4]])
+    >>> s.execute()
+    0    [1, 2, 3]
+    1          foo
+    2           []
+    3       [3, 4]
+    dtype: object
+
+    >>> s.explode().execute()
+    0      1
+    0      2
+    0      3
+    1    foo
+    2    NaN
+    3      3
+    3      4
+    dtype: object
+    """
+    op = DataFrameExplode(ignore_index=ignore_index, output_types=[OutputType.series])
+    return op(series)

maxframe/dataframe/misc/get_dummies.py

@@ -0,0 +1,208 @@
+# Copyright 1999-2024 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import numpy as np
+import pandas as pd
+
+from ...core import OutputType
+from ...serialization.serializables import AnyField, BoolField, ListField, StringField
+from ..datasource.dataframe import from_pandas as from_pandas_df
+from ..datasource.series import from_pandas as from_pandas_series
+from ..initializer import Series as asseries
+from ..operators import DataFrameOperator, DataFrameOperatorMixin
+
+_encoding_dtype_kind = ["O", "S", "U"]
+
+
+class DataFrameGetDummies(DataFrameOperator, DataFrameOperatorMixin):
+    prefix = AnyField("prefix", default=None)
+    prefix_sep = StringField("prefix_sep", default=None)
+    dummy_na = BoolField("dummy_na", default=None)
+    columns = ListField("columns", default=None)
+    sparse = BoolField("sparse", default=None)
+    drop_first = BoolField("drop_first", default=None)
+    dtype = AnyField("dtype", default=None)
+
+    def __init__(self, **kws):
+        super().__init__(**kws)
+        self.output_types = [OutputType.dataframe]
+
+    def __call__(self, data):
+        if isinstance(data, (list, tuple)):
+            data = asseries(data)
+        elif isinstance(data, pd.Series):
+            data = from_pandas_series(data)
+        elif isinstance(data, pd.DataFrame):
+            data = from_pandas_df(data)
+
+        if self.prefix is not None:
+            if isinstance(self.prefix, list):
+                if self.columns is not None:
+                    encoding_col_num = len(self.columns)
+                else:
+                    encoding_col_num = 0
+                    for dtype in data.dtypes.values:
+                        if dtype.kind in _encoding_dtype_kind:
+                            encoding_col_num += 1
+                prefix_num = len(self.prefix)
+                if prefix_num != encoding_col_num:
+                    raise ValueError(
+                        f"Length of 'prefix' ({prefix_num}) did not match "
+                        + f"the length of the columns being encoded ({encoding_col_num})"
+                    )
+            elif isinstance(self.prefix, dict):
+                if self.columns is not None:
+                    encoding_col_num = len(self.columns)
+                    prefix_num = len(self.prefix)
+                    if prefix_num != encoding_col_num:
+                        raise ValueError(
+                            f"Length of 'prefix' ({prefix_num}) did not match "
+                            + f"the length of the columns being encoded ({encoding_col_num})"
+                        )
+                    columns = self.prefix.keys()
+                    for columns_columnname, prefix_columnname in zip(
+                        columns, list(self.columns)
+                    ):
+                        if columns_columnname != prefix_columnname:
+                            raise KeyError(f"{columns_columnname}")
+                else:
+                    self.columns = list(self.prefix.keys())
+                # Convert prefix from dict to list, to simplify tile work
+                self.prefix = list(self.prefix.values())
+
+        return self.new_dataframe(
+            [data],
+            shape=(np.nan, np.nan),
+            dtypes=None,
+            index_value=data.index_value,
+            columns_value=None,
+        )
+
+
+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.
+
+    Parameters
+    ----------
+    data : array-like, Series, or DataFrame
+        Data of which to get dummy indicators.
+    prefix : str, list of str, or dict of str, 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 : str, 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 backed by
+        a :class:`SparseArray` (True) or a regular NumPy array (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
+    -------
+    DataFrame
+        Dummy-coded data.
+
+    Examples
+    --------
+    >>> import maxframe.dataframe as md
+    >>> s = md.Series(list('abca'))
+
+    >>> md.get_dummies(s).execute()
+       a  b  c
+    0  1  0  0
+    1  0  1  0
+    2  0  0  1
+    3  1  0  0
+
+    >>> s1 = ['a', 'b', np.nan]
+
+    >>> md.get_dummies(s1).execute()
+       a  b
+    0  1  0
+    1  0  1
+    2  0  0
+
+    >>> md.get_dummies(s1, dummy_na=True).execute()
+       a  b  NaN
+    0  1  0    0
+    1  0  1    0
+    2  0  0    1
+
+    >>> df = md.DataFrame({'A': ['a', 'b', 'a'], 'B': ['b', 'a', 'c'],
+    ...                    'C': [1, 2, 3]})
+
+    >>> md.get_dummies(df, prefix=['col1', 'col2']).execute()
+       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
+
+    >>> md.get_dummies(pd.Series(list('abcaa'))).execute()
+       a  b  c
+    0  1  0  0
+    1  0  1  0
+    2  0  0  1
+    3  1  0  0
+    4  1  0  0
+
+    >>> md.get_dummies(pd.Series(list('abcaa')), drop_first=True).execute()
+       b  c
+    0  0  0
+    1  1  0
+    2  0  1
+    3  0  0
+    4  0  0
+
+    >>> md.get_dummies(pd.Series(list('abc')), dtype=float).execute()
+         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 columns is not None and not isinstance(columns, list):
+        raise TypeError("Input must be a list-like for parameter `columns`")
+
+    op = DataFrameGetDummies(
+        prefix=prefix,
+        prefix_sep=prefix_sep,
+        dummy_na=dummy_na,
+        columns=columns,
+        sparse=sparse,
+        drop_first=drop_first,
+        dtype=dtype,
+    )
+
+    return op(data)

maxframe/dataframe/misc/isin.py

@@ -0,0 +1,217 @@
+# Copyright 1999-2024 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import numpy as np
+import pandas as pd
+from pandas.api.types import is_list_like
+
+from ... import opcodes
+from ...core import ENTITY_TYPE
+from ...serialization.serializables import AnyField, KeyField
+from ...tensor.core import TENSOR_TYPE
+from ..core import DATAFRAME_TYPE, INDEX_TYPE, SERIES_TYPE
+from ..operators import DataFrameOperator, DataFrameOperatorMixin
+
+
+class DataFrameIsin(DataFrameOperator, DataFrameOperatorMixin):
+    _op_type_ = opcodes.ISIN
+
+    input = KeyField("input")
+    values = AnyField("values", default=None)
+
+    def _set_inputs(self, inputs):
+        super()._set_inputs(inputs)
+        inputs_iter = iter(self._inputs)
+        self.input = next(inputs_iter)
+        if len(self._inputs) > 1:
+            if isinstance(self.values, dict):
+                new_values = dict()
+                for k, v in self.values.items():
+                    if isinstance(v, ENTITY_TYPE):
+                        new_values[k] = next(inputs_iter)
+                    else:
+                        new_values[k] = v
+                self.values = new_values
+            else:
+                self.values = self._inputs[1]
+
+    def __call__(self, elements):
+        inputs = [elements]
+        if isinstance(self.values, ENTITY_TYPE):
+            inputs.append(self.values)
+        elif isinstance(self.values, dict):
+            for v in self.values.values():
+                if isinstance(v, ENTITY_TYPE):
+                    inputs.append(v)
+
+        if elements.ndim == 1:
+            return self.new_series(
+                inputs,
+                shape=elements.shape,
+                dtype=np.dtype("bool"),
+                index_value=elements.index_value,
+                name=elements.name,
+            )
+        else:
+            dtypes = pd.Series(
+                [np.dtype(bool) for _ in elements.dtypes], index=elements.dtypes.index
+            )
+            return self.new_dataframe(
+                inputs,
+                shape=elements.shape,
+                index_value=elements.index_value,
+                columns_value=elements.columns_value,
+                dtypes=dtypes,
+            )
+
+
+def series_isin(elements, values):
+    """
+    Whether elements in Series are contained in `values`.
+
+    Return a boolean Series showing whether each element in the Series
+    matches an element in the passed sequence of `values` exactly.
+
+    Parameters
+    ----------
+    values : set or list-like
+        The sequence of values to test. Passing in a single string will
+        raise a ``TypeError``. Instead, turn a single string into a
+        list of one element.
+
+    Returns
+    -------
+    Series
+        Series of booleans indicating if each element is in values.
+
+    Raises
+    ------
+    TypeError
+      * If `values` is a string
+
+    See Also
+    --------
+    DataFrame.isin : Equivalent method on DataFrame.
+
+    Examples
+    --------
+    >>> import maxframe.dataframe as md
+    >>> s = md.Series(['lame', 'cow', 'lame', 'beetle', 'lame',
+    ...                'hippo'], name='animal')
+    >>> s.isin(['cow', 'lame']).execute()
+    0     True
+    1     True
+    2     True
+    3    False
+    4     True
+    5    False
+    Name: animal, dtype: bool
+
+    Passing a single string as ``s.isin('lame')`` will raise an error. Use
+    a list of one element instead:
+
+    >>> s.isin(['lame']).execute()
+    0     True
+    1    False
+    2     True
+    3    False
+    4     True
+    5    False
+    Name: animal, dtype: bool
+    """
+    if is_list_like(values):
+        values = list(values)
+    elif not isinstance(values, (SERIES_TYPE, TENSOR_TYPE, INDEX_TYPE)):
+        raise TypeError(
+            "only list-like objects are allowed to be passed to isin(), "
+            f"you passed a [{type(values)}]"
+        )
+    op = DataFrameIsin(values=values)
+    return op(elements)
+
+
+def df_isin(df, values):
+    """
+    Whether each element in the DataFrame is contained in values.
+
+    Parameters
+    ----------
+    values : iterable, Series, DataFrame or dict
+        The result will only be true at a location if all the
+        labels match. If `values` is a Series, that's the index. If
+        `values` is a dict, the keys must be the column names,
+        which must match. If `values` is a DataFrame,
+        then both the index and column labels must match.
+
+    Returns
+    -------
+    DataFrame
+        DataFrame of booleans showing whether each element in the DataFrame
+        is contained in values.
+
+    See Also
+    --------
+    DataFrame.eq: Equality test for DataFrame.
+    Series.isin: Equivalent method on Series.
+    Series.str.contains: Test if pattern or regex is contained within a
+        string of a Series or Index.
+
+    Examples
+    --------
+    >>> import maxframe.dataframe as md
+    >>> df = md.DataFrame({'num_legs': [2, 4], 'num_wings': [2, 0]},
+    ...                   index=['falcon', 'dog'])
+    >>> df.execute()
+            num_legs  num_wings
+    falcon         2          2
+    dog            4          0
+
+    When ``values`` is a list check whether every value in the DataFrame
+    is present in the list (which animals have 0 or 2 legs or wings)
+
+    >>> df.isin([0, 2]).execute()
+            num_legs  num_wings
+    falcon      True       True
+    dog        False       True
+
+    When ``values`` is a dict, we can pass values to check for each
+    column separately:
+
+    >>> df.isin({'num_wings': [0, 3]}).execute()
+            num_legs  num_wings
+    falcon     False      False
+    dog        False       True
+
+    When ``values`` is a Series or DataFrame the index and column must
+    match. Note that 'falcon' does not match based on the number of legs
+    in df2.
+
+    >>> other = md.DataFrame({'num_legs': [8, 2], 'num_wings': [0, 2]},
+    ...                      index=['spider', 'falcon'])
+    >>> df.isin(other).execute()
+            num_legs  num_wings
+    falcon      True       True
+    dog        False      False
+    """
+    if is_list_like(values) and not isinstance(values, dict):
+        values = list(values)
+    elif not isinstance(
+        values, (SERIES_TYPE, DATAFRAME_TYPE, TENSOR_TYPE, INDEX_TYPE, dict)
+    ):
+        raise TypeError(
+            "only list-like objects or dict are allowed to be passed to isin(), "
+            f"you passed a [{type(values)}]"
+        )
+    op = DataFrameIsin(values=values)
+    return op(df)