• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• skutil-master
  • build_tools
    • cythonize.py
    • travis
      • test_script.sh
      • after_success.sh
      • install.sh
  • .coveragerc
  • skutil
    • h2o
      • encode.py
      • balance.py
      • util.py
      • pipeline.py
      • one_way_fs.py
      • frame.py
      • select.py
      • metrics.py
      • transform.py
      • grid_search.py
      • split.py
      • __init__.py
      • README.md
      • fixes.py
      • tests
        • test_h2o.py
        • __init__.py
      • base.py
    • utils
      • util.py
      • metaestimators.py
      • __init__.py
      • fixes.py
      • tests
        • test_util.py
        • __init__.py
    • feature_selection
      • select.py
      • combos.py
      • __init__.py
      • tests
        • test_select.py
        • __init__.py
      • base.py
    • odr
      • dqrutl.py
      • setup.py
      • __init__.py
      • dqrsl.f
      • README.md
      • dqrsl.pyf
      • tests
        • __init__.py
        • test_odr.py
    • grid_search.py
    • _build_utils
      • __init__.py
    • setup.py
    • model_selection
      • __init__.py
    • __init__.py
    • decomposition
      • decompose.py
      • __init__.py
      • tests
        • test_decompose.py
        • __init__.py
    • tests
      • test_pipe.py
      • __init__.py
      • test_big.py
    • linear_model
      • __init__.py
      • tests
        • __init__.py
    • preprocessing
      • encode.py
      • balance.py
      • transform.py
      • impute.py
      • __init__.py
      • tests
        • test_balance.py
        • __init__.py
        • test_encode.py
        • test_impute.py
        • test_transform.py
    • metrics
      • pairwise.py
      • kernel.py
      • setup.py
      • _act.py
      • __init__.py
      • tests
        • __init__.py
        • test_metrics.py
      • _kernel_fast.pyx
    • base.py
    • testing
      • __init__.py
      • utils.py
  • LICENSE
  • setup.py
  • setup.cfg
  • .travis.yml
  • README.md
  • requirements.txt
  • .gitignore
  • doc
    • Makefile
    • make.bat
    • images
    • examples
      • h2o
        • h2o_pipeline.ipynb
      • decomposition
        • SelectivePCA weighting.ipynb
      • pipeline
        • README.md
        • skutil grid demo.ipynb
      • machine_learning_demo
    • sphinxext
      • numpy_ext
        • docscrape_sphinx.py
        • docscrape.py
        • numpydoc.py
        • __init__.py
    • index.rst
    • conf.py
    • publish_gh_pages.sh
    • rsts
      • examples
        • h2opipeline.rst
        • encoders.rst
        • transformers.rst
        • index.rst
      • setup
        • index.rst
      • codebase
        • skutil_feature_selection.rst
        • skutil_linear_model.rst
        • skutil_base.rst
        • skutil_grid_search.rst
        • skutil_utils.rst
        • skutil_model_selection.rst
        • skutil_odr.rst
        • skutil_preprocessing.rst
        • index.rst
        • skutil_metrics.rst
        • skutil_decomposition.rst
        • skutil_h2o.rst

import numpy as np
from numpy.testing import (assert_array_equal, assert_array_almost_equal)
from sklearn.decomposition import PCA, TruncatedSVD
from sklearn.datasets import load_iris
from skutil.decomposition import *
from skutil.testing import assert_fails
from skutil.utils import load_iris_df
from skutil.decomposition.decompose import _BaseSelectiveDecomposer

# Def data for testing
iris = load_iris()
X = load_iris_df(False)


def test_selective_pca():
    original = X
    cols = [original.columns[0]]  # Only perform on first...
    compare_cols = np.array(original[['sepal width (cm)', 'petal length (cm)',
                                      'petal width (cm)']].as_matrix())  # should be the same as the trans cols

    transformer = SelectivePCA(cols=cols, n_components=0.85).fit(original)
    transformed = transformer.transform(original)

    untouched_cols = np.array(transformed[['sepal width (cm)', 'petal length (cm)', 'petal width (cm)']].as_matrix())
    assert_array_almost_equal(compare_cols, untouched_cols)
    assert 'PC1' in transformed.columns
    assert transformed.shape[1] == 4
    assert isinstance(transformer.get_decomposition(), PCA)
    assert SelectivePCA().get_decomposition() is None

    # test the selective mixin
    assert isinstance(transformer.cols, list)

    # what if we want to weight it?
    pca_df = SelectivePCA(weight=True, n_components=0.99, as_df=False).fit_transform(original)
    pca_arr = SelectivePCA(weight=True, n_components=0.99, as_df=False).fit_transform(iris.data)
    assert_array_equal(pca_df, pca_arr)

    # hack to assert they are not equal if weighted
    pca_arr = SelectivePCA(weight=False, n_components=0.99, as_df=False).fit_transform(iris.data)
    assert_fails(assert_array_equal, AssertionError, pca_df, pca_arr)


def test_selective_tsvd():
    original = X
    cols = [original.columns[0], original.columns[1]]  # Only perform on first two columns...
    compare_cols = np.array(
        original[['petal length (cm)', 'petal width (cm)']].as_matrix())  # should be the same as the trans cols

    transformer = SelectiveTruncatedSVD(cols=cols, n_components=1).fit(original)
    transformed = transformer.transform(original)

    untouched_cols = np.array(transformed[['petal length (cm)', 'petal width (cm)']].as_matrix())
    assert_array_almost_equal(compare_cols, untouched_cols)
    assert 'Concept1' in transformed.columns
    assert transformed.shape[1] == 3
    assert isinstance(transformer.get_decomposition(), TruncatedSVD)
    assert SelectiveTruncatedSVD().get_decomposition() is None  # default None

    # test the selective mixin
    assert isinstance(transformer.cols, list)


def test_not_implemented_failure():
    # define anon decomposer
    class AnonDecomposer(_BaseSelectiveDecomposer):
        def __init__(self, cols=None, n_components=None, as_df=True):
            super(AnonDecomposer, self).__init__(cols, n_components, as_df)

        def get_decomposition(self):
            return super(AnonDecomposer, self).get_decomposition()

    assert_fails(AnonDecomposer().get_decomposition, NotImplementedError)