oracle-ads 2.13.9rc0__py3-none-any.whl → 2.13.10rc0__py3-none-any.whl

ads/feature_engineering/feature_type/boolean.py

@@ -0,0 +1,183 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+"""
+The module that represents a Boolean feature type.
+
+Classes:
+    Boolean
+        The feature type that represents binary values True/False.
+
+Functions:
+    default_handler(data: pd.Series) -> pd.Series
+        Processes given data and indicates if the data matches requirements.
+"""
+import matplotlib.pyplot as plt
+import pandas as pd
+from ads.feature_engineering.feature_type.base import FeatureType
+from ads.feature_engineering.utils import (
+    _count_unique_missing,
+    is_boolean,
+    _set_seaborn_theme,
+    SchemeTeal,
+)
+from ads.feature_engineering import schema
+from ads.common.decorator.runtime_dependency import (
+    runtime_dependency,
+    OptionalDependency,
+)
+
+
+def default_handler(data: pd.Series, *args, **kwargs) -> pd.Series:
+    """Processes given data and indicates if the data matches requirements.
+
+    Parameters
+    ----------
+    data: :class:`pandas.Series`
+        The data to process.
+
+    Returns
+    -------
+    :class:`pandas.Series`
+        The logical list indicating if the data matches requirements.
+    """
+    return pd.Series((is_boolean(value) for value in data.values))
+
+
+class Boolean(FeatureType):
+    """
+    Type representing binary values True/False.
+
+    Attributes
+    ----------
+    description: str
+        The feature type description.
+    name: str
+        The feature type name.
+    warning: FeatureWarning
+        Provides functionality to register warnings and invoke them.
+    validator
+        Provides functionality to register validators and invoke them.
+
+    Methods
+    --------
+    feature_stat(x: pd.Series) -> pd.DataFrame
+        Generates feature statistics.
+    feature_plot(x: pd.Series) -> plt.Axes
+        Show the counts of observations in True/False using bars.
+
+    Examples
+    --------
+    >>> from ads.feature_engineering.feature_type.boolean import Boolean
+    >>> import pandas as pd
+    >>> import numpy as np
+    >>> s = pd.Series([True, False, True, False, np.NaN, None], name='bool')
+    >>> s.ads.feature_type = ['boolean']
+    >>> Boolean.validator.is_boolean(s)
+    0     True
+    1     True
+    2     True
+    3     True
+    4    False
+    5    False
+    dtype: bool
+    """
+
+    description = "Type representing binary values True/False."
+
+    @staticmethod
+    def feature_stat(x: pd.Series) -> pd.DataFrame:
+        """Generates feature statistics.
+
+        Feature statistics include (total)count, unique(count) and missing(count).
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being evaluated.
+
+        Returns
+        -------
+        :class:`pandas.DataFrame`
+            Summary statistics of the Series or Dataframe provided.
+
+        Examples
+        --------
+        >>> s = pd.Series([True, False, True, False, np.NaN, None], name='bool')
+        >>> s.ads.feature_type = ['boolean']
+        >>> s.ads.feature_stat()
+            Metric  Value
+        0	count	6
+        1	unique	2
+        2	missing	2
+        """
+        return _count_unique_missing(x)
+
+    @staticmethod
+    @runtime_dependency(module="seaborn", install_from=OptionalDependency.VIZ)
+    def feature_plot(x: pd.Series) -> plt.Axes:
+        """
+        Shows the counts of observations in True/False using bars.
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being evaluated.
+
+        Returns
+        -------
+        matplotlib.axes._subplots.AxesSubplot
+            Plot object for the series based on the Boolean feature type.
+
+        Examples
+        --------
+        >>> s = pd.Series([True, False, True, False, np.NaN, None], name='bool')
+        >>> s.ads.feature_type = ['boolean']
+        >>> s.ads.feature_plot()
+        """
+        col_name = x.name if x.name else "boolean"
+        df = x.to_frame(col_name)
+        df["validation"] = default_handler(x)
+        df = df[df["validation"] == True]
+        if len(df.index):
+            _set_seaborn_theme()
+            ax = seaborn.countplot(y=col_name, data=df, color=SchemeTeal.AREA_DARK)
+            ax.set(xlabel="Count")
+            return ax
+
+    @classmethod
+    def feature_domain(cls, x: pd.Series) -> schema.Domain:
+        """
+        Generate the domain of the data of this feature type.
+
+        Examples
+        --------
+        >>> s = pd.Series([True, False, True, False, np.NaN, None], name='bool')
+        >>> s.ads.feature_type = ['boolean']
+        >>> s.ads.feature_domain()
+        constraints:
+        - expression: $x in [True, False]
+            language: python
+        stats:
+            count: 6
+            missing: 2
+            unique: 2
+        values: Boolean
+
+        Returns
+        -------
+        ads.feature_engineering.schema.Domain
+            Domain based on the Boolean feature type.
+        """
+
+        return schema.Domain(
+            cls.__name__,
+            cls.feature_stat(x).to_dict()[x.name],
+            [schema.Expression("$x in [True, False]")],
+        )
+
+
+Boolean.validator.register("is_boolean", default_handler)

ads/feature_engineering/feature_type/category.py

@@ -0,0 +1,146 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+"""
+The module that represents a Category feature type.
+
+Classes:
+    Category
+        The Category feature type.
+"""
+import matplotlib.pyplot as plt
+import pandas as pd
+from ads.feature_engineering.feature_type.base import FeatureType
+from ads.feature_engineering.utils import (
+    _count_unique_missing,
+    _set_seaborn_theme,
+    SchemeTeal,
+)
+from ads.feature_engineering import schema
+from ads.common.decorator.runtime_dependency import (
+    runtime_dependency,
+    OptionalDependency,
+)
+
+
+class Category(FeatureType):
+    """
+    Type representing discrete unordered values.
+
+    Attributes
+    ----------
+    description: str
+        The feature type description.
+    name: str
+        The feature type name.
+    warning: FeatureWarning
+        Provides functionality to register warnings and invoke them.
+    validator
+        Provides functionality to register validators and invoke them.
+
+    Methods
+    --------
+    feature_stat(x: pd.Series) -> pd.DataFrame
+        Generates feature statistics.
+    feature_plot(x: pd.Series) -> plt.Axes
+        Shows the counts of observations in each categorical bin using bar chart.
+
+    """
+
+    description = "Type representing discrete unordered values."
+
+    @staticmethod
+    def feature_stat(x: pd.Series) -> pd.DataFrame:
+        """Generates feature statistics.
+
+        Feature statistics include (total)count, unique(count) and missing(count) if there are any.
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being evaluated.
+
+        Returns
+        -------
+        :class:`pandas.DataFrame`
+            Summary statistics of the Series or Dataframe provided.
+
+        Examples
+        --------
+        >>> cat = pd.Series(['S', 'C', 'S', 'S', 'S', 'Q', 'S', 'S', 'S', 'C', 'S', 'S', 'S',
+                    'S', 'S', 'S', 'Q', 'S', 'S', '', np.NaN, None], name='сategory')
+        >>> cat.ads.feature_type = ['сategory']
+        >>> cat.ads.feature_stat()
+            Metric  Value
+        0	count	22
+        1	unique	3
+        2	missing	3
+        """
+        return _count_unique_missing(x)
+
+    @staticmethod
+    @runtime_dependency(module="seaborn", install_from=OptionalDependency.VIZ)
+    def feature_plot(x: pd.Series) -> plt.Axes:
+        """
+        Shows the counts of observations in each categorical bin using bar chart.
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being evaluated.
+
+        Returns
+        -------
+        matplotlib.axes._subplots.AxesSubplot
+            Plot object for the series based on the Category feature type.
+
+        Examples
+        --------
+        >>> cat = pd.Series(['S', 'C', 'S', 'S', 'S', 'Q', 'S', 'S', 'S', 'C', 'S', 'S', 'S',
+                    'S', 'S', 'S', 'Q', 'S', 'S', '', np.NaN, None], name='сategory')
+        >>> cat.ads.feature_type = ['сategory']
+        >>> cat.ads.feature_plot()
+        """
+        col_name = x.name if x.name else "сategory"
+        df = x.to_frame(name=col_name)
+        df = df.dropna()
+        if len(df.index):
+            _set_seaborn_theme()
+            ax = seaborn.countplot(y=col_name, data=df, color=SchemeTeal.AREA_DARK)
+            ax.set(xlabel="Count")
+            return ax
+
+    @classmethod
+    def feature_domain(cls, x: pd.Series) -> schema.Domain:
+        """
+        Generate the domain of the data of this feature type.
+
+        Examples
+        --------
+        >>> cat = pd.Series(['S', 'C', 'S', 'S', 'S', 'Q', 'S', 'S', 'S', 'C', 'S', 'S', 'S',
+                    'S', 'S', 'S', 'Q', 'S', 'S', '', np.NaN, None], name='category')
+        >>> cat.ads.feature_type = ['category']
+        >>> cat.ads.feature_domain()
+        constraints:
+        - expression: $x in ['S', 'C', 'Q', '']
+            language: python
+        stats:
+            count: 22
+            missing: 3
+            unique: 3
+        values: Category
+
+        Returns
+        -------
+        ads.feature_engineering.schema.Domain
+            Domain based on the Category feature type.
+        """
+
+        return schema.Domain(
+            cls.__name__,
+            cls.feature_stat(x).to_dict()[x.name],
+            [schema.Expression(f"$x in {x.dropna().unique().tolist()}")],
+        )

ads/feature_engineering/feature_type/constant.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+"""
+The module that represents a Constant feature type.
+
+Classes:
+    Constant
+        The Constant feature type.
+"""
+import matplotlib.pyplot as plt
+import pandas as pd
+from ads.feature_engineering.feature_type.base import FeatureType
+from ads.feature_engineering.utils import (
+    _count_unique_missing,
+    _set_seaborn_theme,
+    SchemeTeal,
+)
+from ads.feature_engineering import schema
+from ads.common.decorator.runtime_dependency import (
+    runtime_dependency,
+    OptionalDependency,
+)
+
+
+class Constant(FeatureType):
+    """
+    Type representing constant values.
+
+    Attributes
+    ----------
+    description: str
+        The feature type description.
+    name: str
+        The feature type name.
+    warning: FeatureWarning
+        Provides functionality to register warnings and invoke them.
+    validator
+        Provides functionality to register validators and invoke them.
+
+    Methods
+    --------
+    feature_stat(x: pd.Series) -> pd.DataFrame
+        Generates feature statistics.
+    feature_plot(x: pd.Series) -> plt.Axes
+        Shows the counts of observations in bars.
+    """
+
+    description = "Type representing constant values."
+
+    @staticmethod
+    def feature_stat(x: pd.Series) -> pd.DataFrame:
+        """Generates feature statistics.
+
+        Feature statistics include (total)count, unique(count) and missing(count).
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being evaluated.
+
+        Returns
+        -------
+        :class:`pandas.DataFrame`
+            Summary statistics of the Series provided.
+
+        Examples
+        --------
+        >>> s = pd.Series([1, 1, 1, 1, 1], name='constant')
+        >>> s.ads.feature_type = ['constant']
+        >>> s.ads.feature_stat()
+            Metric  Value
+        0	count	5
+        1	unique	1
+        """
+        return _count_unique_missing(x)
+
+    @staticmethod
+    @runtime_dependency(module="seaborn", install_from=OptionalDependency.VIZ)
+    def feature_plot(x: pd.Series) -> plt.Axes:
+        """
+        Shows the counts of observations in bars.
+
+        Parameters
+        ----------
+        x : :class:`pandas.Series`
+            The feature being shown.
+
+        Examples
+        --------
+        >>> s = pd.Series([1, 1, 1, 1, 1], name='constant')
+        >>> s.ads.feature_type = ['constant']
+        >>> s.ads.feature_plot()
+
+        Returns
+        -------
+        matplotlib.axes._subplots.AxesSubplot
+            Plot object for the series based on the Constant feature type.
+        """
+        col_name = x.name if x.name else "constant"
+        df = x.to_frame(name=col_name)
+        df = df.dropna()
+        if len(df.index):
+            _set_seaborn_theme()
+            ax = seaborn.countplot(y=col_name, data=df, color=SchemeTeal.AREA_DARK)
+            ax.set(xlabel="Count")
+            return ax
+
+    @classmethod
+    def feature_domain(cls, x: pd.Series) -> schema.Domain:
+        """
+        Generate the domain of the data of this feature type.
+        Example
+        -------
+        >>> s = pd.Series([1, 1, 1, 1, 1], name='constant')
+        >>> s.ads.feature_type = ['constant']
+        >>> s.ads.feature_domain()
+        constraints: []
+        stats:
+            count: 5
+            unique: 1
+        values: Constant
+
+        Returns
+        -------
+        ads.feature_engineering.schema.Domain
+            Domain based on the Constant feature type.
+        """
+
+        return schema.Domain(
+            cls.__name__,
+            cls.feature_stat(x).to_dict()[x.name],
+            [],
+        )

ads/feature_engineering/feature_type/continuous.py

@@ -0,0 +1,151 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+"""
+The module that represents a Continuous feature type.
+
+Classes:
+    Continuous
+        The Continuous feature type.
+"""
+import matplotlib.pyplot as plt
+import pandas as pd
+from ads.feature_engineering.feature_type.base import FeatureType
+from ads.feature_engineering.utils import (
+    _add_missing,
+    _set_seaborn_theme,
+    SchemeTeal,
+    _format_stat,
+)
+from ads.feature_engineering import schema
+from ads.common.decorator.runtime_dependency import (
+    runtime_dependency,
+    OptionalDependency,
+)
+
+
+class Continuous(FeatureType):
+    """
+    Type representing continuous values.
+
+    Attributes
+    ----------
+    description: str
+        The feature type description.
+    name: str
+        The feature type name.
+    warning: FeatureWarning
+        Provides functionality to register warnings and invoke them.
+    validator
+        Provides functionality to register validators and invoke them.
+
+    Methods
+    --------
+    feature_stat(x: pd.Series) -> pd.DataFrame
+        Generates feature statistics.
+    feature_plot(x: pd.Series) -> plt.Axes
+        Shows distributions of datasets using box plot.
+    """
+
+    description = "Type representing continuous values."
+
+    @staticmethod
+    def feature_stat(x: pd.Series) -> pd.DataFrame:
+        """Generates feature statistics.
+
+        Feature statistics include (total)count, mean, standard deviation, sample minimum,
+        lower quartile, median, 75%, upper quartile, skew and missing(count).
+
+        Examples
+        --------
+        >>> cts = pd.Series([13.32, 3.32, 4.3, 2.45, 6.34, 2.25,
+                            4.43, 3.26, np.NaN, None], name='continuous')
+        >>> cts.ads.feature_type = ['continuous']
+        >>> cts.ads.feature_stat()
+            Metric                  Value
+        0	count	                10.000
+        1	mean	                4.959
+        2	standard deviation	    3.620
+        3	sample minimum	        2.250
+        4	lower quartile	        3.058
+        5	median	                3.810
+        6	upper quartile	        4.908
+        7	sample maximum	        13.320
+        8	skew	                2.175
+        9	missing	                2.000
+
+        Returns
+        -------
+        :class:`pandas.DataFrame`
+            Summary statistics of the Series or Dataframe provided.
+        """
+        df_stat = x.describe()
+        _format_stat(df_stat)
+        df_stat["count"] = len(x)
+        df_stat["skew"] = x.skew()
+        df_stat = _add_missing(x, df_stat).to_frame()
+        df_stat.iloc[:, 0] = df_stat.iloc[:, 0].round(3)
+        return df_stat
+
+    @staticmethod
+    @runtime_dependency(module="seaborn", install_from=OptionalDependency.VIZ)
+    def feature_plot(x: pd.Series) -> plt.Axes:
+        """
+        Shows distributions of datasets using box plot.
+
+        Examples
+        --------
+        >>> cts = pd.Series([13.32, 3.32, 4.3, 2.45, 6.34, 2.25,
+                            4.43, 3.26, np.NaN, None], name='continuous')
+        >>> cts.ads.feature_type = ['continuous']
+        >>> cts.ads.feture_plot()
+
+        Returns
+        -------
+        matplotlib.axes._subplots.AxesSubplot
+            Plot object for the series based on the Continuous feature type.
+        """
+        col_name = x.name if x.name else "continuous"
+        df = x.to_frame(name=col_name)
+        df = df[pd.to_numeric(df[col_name], errors="coerce").notnull()]
+        if len(df.index):
+            _set_seaborn_theme()
+            return seaborn.boxplot(
+                x=df[col_name], width=0.2, color=SchemeTeal.AREA_DARK
+            )
+
+    @classmethod
+    def feature_domain(cls, x: pd.Series) -> schema.Domain:
+        """
+        Generate the domain of the data of this feature type.
+
+        Examples
+        --------
+        >>> cts = pd.Series([13.32, 3.32, 4.3, 2.45, 6.34, 2.25,
+                            4.43, 3.26, np.NaN, None], name='continuous')
+        >>> cts.ads.feature_type = ['continuous']
+        >>> cts.ads.feature_domain()
+        constraints: []
+        stats:
+            count: 10.0
+            lower quartile: 3.058
+            mean: 4.959
+            median: 3.81
+            missing: 2.0
+            sample maximum: 13.32
+            sample minimum: 2.25
+            skew: 2.175
+            standard deviation: 3.62
+            upper quartile: 4.908
+        values: Continuous
+
+        Returns
+        -------
+        ads.feature_engineering.schema.Domain
+            Domain based on the Continuous feature type.
+        """
+
+        return schema.Domain(cls.__name__, cls.feature_stat(x).to_dict()[x.name], [])