How to use the pdpipe.sklearn_stages.Scale function in pdpipe

To help you get started, weโ€™ve selected a few pdpipe examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github pdpipe / pdpipe / tests / sklearn_stages / test_scale.py View on Github external
def test_scale_with_exclude():
    """Basic binning test."""
    df = _some_df2()
    scale_stage = Scale("StandardScaler", with_std=False)
    res_df = scale_stage(df)
    assert "ph" in res_df.columns
    assert "gt" in res_df.columns
github pdpipe / pdpipe / tests / sklearn_stages / test_scale.py View on Github external
def test_scale_app_exception():
    df1 = _some_df1()
    scale_stage = Scale(
        "StandardScaler", exclude_columns=[], exclude_object_columns=False
    )
    with pytest.raises(PipelineApplicationError):
        scale_stage(df1)

    df2 = _some_df2()
    res_df = scale_stage(df2)
    assert "ph" in res_df.columns
    assert "gt" in res_df.columns

    # test transform exception
    with pytest.raises(PipelineApplicationError):
        scale_stage(df1)
github pdpipe / pdpipe / tests / sklearn_stages / test_scale.py View on Github external
def test_scale_with_exclude_cols():
    df = _some_df1()
    scale_stage = Scale("StandardScaler", exclude_columns=["lbl"], exmsg="AA")
    res_df = scale_stage(df)
    assert list(res_df.columns) == ["ph", "gt", "lbl"]
    assert "ph" in res_df.columns
    assert "gt" in res_df.columns
    assert res_df["ph"][1] < df["ph"][1]

    # see only transform (no fit) when already fitted
    df2 = _some_df1b()
    res_df2 = scale_stage(df2)
    assert "ph" in res_df2.columns
    assert "gt" in res_df2.columns
    assert res_df2["ph"][1] < df2["ph"][1]
    assert res_df["ph"][1] < res_df2["ph"][1]

    # check fit_transform when already fitted
    df3 = _some_df1b()
github pdpipe / pdpipe / tests / sklearn_stages / test_scale.py View on Github external
def test_scale():
    df = _some_df2()
    scale_stage = Scale("StandardScaler")
    res_df = scale_stage(df)
    assert "ph" in res_df.columns
    assert "gt" in res_df.columns
    assert res_df["ph"][1] < df["ph"][1]

    # see only transform (no fit) when already fitted
    df2 = _some_df2b()
    res_df2 = scale_stage(df2)
    assert "ph" in res_df2.columns
    assert "gt" in res_df2.columns
    assert res_df2["ph"][1] < df2["ph"][1]
    assert res_df["ph"][1] < res_df2["ph"][1]

    # check fit_transform when already fitted
    df3 = _some_df2b()
    res_df3 = scale_stage.fit_transform(df2)
github pdpipe / pdpipe / pdpipe / sklearn_stages.py View on Github external
exclude_object_columns=True,
        **kwargs
    ):
        self.scaler = scaler
        if exclude_columns is None:
            self._exclude_columns = []
            desc_suffix = "."
        else:
            self._exclude_columns = _interpret_columns_param(exclude_columns)
            col_str = _list_str(self._exclude_columns)
            desc_suffix = " except columns {}.".format(col_str)
        self._exclude_obj_cols = exclude_object_columns
        super_kwargs = {
            "exmsg": Scale._DEF_SCALE_EXC_MSG,
            "appmsg": Scale._DEF_SCALE_APP_MSG,
            "desc": Scale._DESC_PREFIX + desc_suffix,
        }
        self._kwargs = kwargs
        valid_super_kwargs = super()._init_kwargs()
        for key in kwargs:
            if key in valid_super_kwargs:
                super_kwargs[key] = kwargs[key]
        super().__init__(**super_kwargs)
github pdpipe / pdpipe / pdpipe / sklearn_stages.py View on Github external
scaler,
        exclude_columns=None,
        exclude_object_columns=True,
        **kwargs
    ):
        self.scaler = scaler
        if exclude_columns is None:
            self._exclude_columns = []
            desc_suffix = "."
        else:
            self._exclude_columns = _interpret_columns_param(exclude_columns)
            col_str = _list_str(self._exclude_columns)
            desc_suffix = " except columns {}.".format(col_str)
        self._exclude_obj_cols = exclude_object_columns
        super_kwargs = {
            "exmsg": Scale._DEF_SCALE_EXC_MSG,
            "appmsg": Scale._DEF_SCALE_APP_MSG,
            "desc": Scale._DESC_PREFIX + desc_suffix,
        }
        self._kwargs = kwargs
        valid_super_kwargs = super()._init_kwargs()
        for key in kwargs:
            if key in valid_super_kwargs:
                super_kwargs[key] = kwargs[key]
        super().__init__(**super_kwargs)
github pdpipe / pdpipe / pdpipe / sklearn_stages.py View on Github external
exclude_columns=None,
        exclude_object_columns=True,
        **kwargs
    ):
        self.scaler = scaler
        if exclude_columns is None:
            self._exclude_columns = []
            desc_suffix = "."
        else:
            self._exclude_columns = _interpret_columns_param(exclude_columns)
            col_str = _list_str(self._exclude_columns)
            desc_suffix = " except columns {}.".format(col_str)
        self._exclude_obj_cols = exclude_object_columns
        super_kwargs = {
            "exmsg": Scale._DEF_SCALE_EXC_MSG,
            "appmsg": Scale._DEF_SCALE_APP_MSG,
            "desc": Scale._DESC_PREFIX + desc_suffix,
        }
        self._kwargs = kwargs
        valid_super_kwargs = super()._init_kwargs()
        for key in kwargs:
            if key in valid_super_kwargs:
                super_kwargs[key] = kwargs[key]
        super().__init__(**super_kwargs)