visual pipeline prototype closes #47

docs/api/modules.rst

@@ -10,4 +10,5 @@ API Reference
     yellowbrick.classifier
     yellowbrick.cluster
     yellowbrick.text
+    yellowbrick.pipeline
     yellowbrick.style

tests/test_features/test_pcoords.py

@@ -63,6 +63,9 @@ def test_integrated_pcoords(self):
         # Convert X to an ndarray
         X = np.array(X.tolist())
 
+        import time
+        start = time.time()
         # Test the visualizer
         visualizer = ParallelCoordinates()
         visualizer.fit_transform(X, y)
+        raise Exception("X conversion to {:0.3f} seconds".format(time.time()-start))

tests/test_pipeline.py

@@ -38,28 +38,34 @@ class Thing(object):
     pass
 
 
-class EstimatorSpec(BaseEstimator):
+class MockEstimator(BaseEstimator):
 
     def fit(self, X, y=None, **kwargs):
         return self
 
-MockEstimator = mock.Mock(spec = EstimatorSpec)
+class MockVisualEstimator(Visualizer):
 
+    def fit(self, X, y=None, **kwargs):
+        self.draw(**kwargs)
+        return self
+
+    def draw(self, **kwargs):
+        pass
 
-class TransformerSpec(BaseEstimator, TransformerMixin):
+
+class MockTransformer(BaseEstimator, TransformerMixin):
 
     def fit(self, X, y=None, **kwargs):
         return self
 
     def transform(self, X, **kwargs):
         return X
 
-MockTransformer = mock.Mock(spec = TransformerSpec)
-
 
-class VisualTransformerSpec(Visualizer, TransformerMixin):
+class MockVisualTransformer(Visualizer, TransformerMixin):
 
     def fit(self, X, y=None, **kwargs):
+        self.draw(**kwargs)
         return self
 
     def transform(self, X, **kwargs):
@@ -68,11 +74,6 @@ def transform(self, X, **kwargs):
     def draw(self, **kwargs):
         pass
 
-    def poof(self, **kwargs):
-        pass
-
-MockVisualTransformer = mock.Mock(spec = VisualTransformerSpec)
-
 
 ##########################################################################
 ## VisualPipeline Tests
@@ -145,27 +146,64 @@ def test_visual_steps_property(self):
 
         pipeline = VisualPipeline([
             ('a', MockTransformer()),
-            ('b', VisualTransformerSpec()),
+            ('b', MockVisualTransformer()),
             ('c', MockTransformer()),
-            ('d', VisualTransformerSpec()),
+            ('d', MockVisualTransformer()),
             ('e', MockEstimator()),
         ])
 
+        self.assertNotIn('a', pipeline.visual_steps)
         self.assertIn('b', pipeline.visual_steps)
+        self.assertNotIn('c', pipeline.visual_steps)
         self.assertIn('d', pipeline.visual_steps)
+        self.assertNotIn('e', pipeline.visual_steps)
+
+    def test_pipeline_poof(self):
+        """
+        Test the poof call against the VisualPipeline
+        """
+
+        pipeline = VisualPipeline([
+            ('a', mock.MagicMock(MockTransformer())),
+            ('b', mock.MagicMock(MockVisualTransformer())),
+            ('c', mock.MagicMock(MockTransformer())),
+            ('d', mock.MagicMock(MockVisualTransformer())),
+            ('e', mock.MagicMock(MockEstimator()),)
+        ])
+
+        pipeline.poof()
+        pipeline.steps[1][1].poof.assert_called_once_with(outpath=None)
+        pipeline.steps[3][1].poof.assert_called_once_with(outpath=None)
+
+    def test_pipeline_savefig_poof(self):
+        """
+        Test the poof call with an outdir to save all the figures
+        """
+        pipeline = VisualPipeline([
+            ('a', mock.MagicMock(MockTransformer())),
+            ('b', mock.MagicMock(MockVisualTransformer())),
+            ('c', mock.MagicMock(MockTransformer())),
+            ('d', mock.MagicMock(MockVisualTransformer())),
+            ('e', mock.MagicMock(MockVisualEstimator()),)
+        ])
+
+        pipeline.poof(outdir="/tmp/figures")
+        pipeline.steps[1][1].poof.assert_called_once_with(outpath="/tmp/figures/b.pdf")
+        pipeline.steps[3][1].poof.assert_called_once_with(outpath="/tmp/figures/d.pdf")
+        pipeline.steps[4][1].poof.assert_called_once_with(outpath="/tmp/figures/e.pdf")
 
-    @unittest.skip("mocks don't work for some reason")
+    @unittest.skip("need to find a way for fit to return self in mocks")
     def test_fit_transform_poof_and_draw_calls(self):
         """
-        Test calling fit, transform, draw and poof on the pipeline
+        Test calling fit, transform, and poof on the pipeline
         """
 
         pipeline = VisualPipeline([
-            ('a', MockTransformer()),
-            ('b', MockVisualTransformer()),
-            ('c', MockTransformer()),
-            ('d', MockVisualTransformer()),
-            ('e', MockEstimator()),
+            ('a', mock.MagicMock(MockTransformer())),
+            ('b', mock.MagicMock(MockVisualTransformer())),
+            ('c', mock.MagicMock(MockTransformer())),
+            ('d', mock.MagicMock(MockVisualTransformer())),
+            ('e', mock.MagicMock(MockEstimator()),)
         ])
 
         X = [[1, 1, 1, 1, 1],
@@ -180,14 +218,10 @@ def test_fit_transform_poof_and_draw_calls(self):
 
         pipeline.transform(X)
         for name, step in pipeline.named_steps.items():
+            if name == 'e': continue
             step.transform.assert_called_once_with(X)
 
-        pipeline.draw()
-        for name, step in pipeline.named_steps.items():
-            if name in {'a', 'c', 'e'}: continue
-            step.draw.assert_called_once_with()
-
         pipeline.poof()
         for name, step in pipeline.named_steps.items():
             if name in {'a', 'c', 'e'}: continue
-            step.poof.assert_called_once_with()
+            step.poof.assert_called_once_with(outpath=None)

tests/test_utils/test_helpers.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # tests.test_utils.test_helpers
 # Tests for the stand alone helper functions in Yellowbrick utils.
 #
@@ -135,6 +136,26 @@ def test_has_ndarray_int_columns_false_outside_column_range(self):
         self.assertFalse(has_ndarray_int_columns(features, x))
 
 
+##########################################################################
+## String Helpers Tests
+##########################################################################
+
+class StringHelpersTests(unittest.TestCase):
+
+    def test_slugifiy(self):
+        """
+        Test the slugify helper utility
+        """
+
+        cases = (
+            ("This is a test ---", "this-is-a-test"),
+            ("This -- is a ## test ---" , "this-is-a-test"),
+        )
+
+        for case, expected in cases:
+            self.assertEqual(expected, slugify(case))
+
+
 ##########################################################################
 ## Execute Tests
 ##########################################################################

yellowbrick/pipeline.py

@@ -17,7 +17,9 @@
 ## Imports
 ##########################################################################
 
+from os import path
 from .base import Visualizer
+from .utils.helpers import slugify
 from sklearn.pipeline import Pipeline
 
 
@@ -71,25 +73,36 @@ def visual_steps(self):
             if isinstance(step[1], Visualizer)
         )
 
-    def draw(self, *args, **kwargs):
+    def poof(self, outdir=None, ext=".pdf", **kwargs):
         """
-        Calls draw on steps (including the final estimator) that has a draw
-        method and passes the args and kwargs to that draw function.
+        A single entry point to rendering all visualizations in the visual
+        pipeline. The rendering for the output depends on the backend context,
+        but for path based renderings (e.g. saving to a file), specify a
+        directory and extension to compse an outpath to save each
+        visualization (file names will be based on the  named step).
+
+        Parameters
+        ----------
+        outdir : path
+            The directory to save visualizations to.
+
+        ext : string, default = ".pdf"
+            The extension of the file to save the visualization to.
+
+        kwargs : dict
+            Keyword arguments to pass to the ``poof()`` method of all steps.
         """
         for name, step in self.visual_steps.items():
-            step.draw(*args, **kwargs)
+            if outdir is not None:
+                outpath = path.join(outdir, slugify(name) + ext)
+            else:
+                outpath = None
 
-    def poof(self, *args, **kwargs):
-        """
-        Calls poof on steps (including the final estimator) that has a poof
-        method and passes the args and kwargs to that poof function.
-        """
-        for name, step in self.visual_steps.items():
-            step.poof(*args, **kwargs)
+            step.poof(outpath=outpath, **kwargs)
 
-    def fit_transform_poof(self, X, y=None, **kwargs):
+    def fit_transform_poof(self, X, y=None, outpath=None, **kwargs):
         """
         Fit the model and transforms and then call poof.
         """
         self.fit_transform(X, y, **kwargs)
-        self.poof(**kwargs)
+        self.poof(outpath, **kwargs)

yellowbrick/utils/helpers.py

@@ -17,6 +17,8 @@
 ## Imports
 ##########################################################################
 
+import re
+import unicodedata
 import numpy as np
 
 from sklearn.pipeline import Pipeline
@@ -103,3 +105,29 @@ def div_safe( numerator, denominator ):
         return result
     except ValueError as e:
         raise e
+
+
+##########################################################################
+## String Computations
+##########################################################################
+
+def slugify(text):
+    """
+    Returns a slug of given text, normalizing unicode data for file-safe
+    strings. Used for deciding where to write images to disk.
+
+    Parameters
+    ----------
+    text : string
+        The string to slugify
+
+    Returns
+    -------
+    slug : string
+        A normalized slug representation of the text
+
+    .. seealso:: http://yashchandra.com/2014/05/08/how-to-generate-clean-url-or-a-slug-in-python/
+    """
+    slug = re.sub(r'[^\w]+', ' ', text)
+    slug = "-".join(slug.lower().strip().split())
+    return slug