Merge branch 'master' of github.com:teabolt/eli5 into keras-gradcam-text

CHANGES.rst

@@ -1,6 +1,18 @@
 Changelog
 =========
 
+0.10.1 (2019-08-29)
+-------------------
+
+* Don't include typing dependency on Python 3.5+
+  to fix installation on Python 3.7
+
+0.10.0 (2019-08-21)
+-------------------
+
+* Keras image classifiers: explaining predictions with Grad-CAM
+  (GSoC-2019 project by @teabolt).
+
 0.9.0 (2019-07-05)
 ------------------
 

eli5/__init__.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
-__version__ = '0.9.0'
+__version__ = '0.10.1'
 
 from .formatters import (
     format_as_html,
@@ -95,4 +95,4 @@
     )
 except ImportError:
     # keras is not available
-    pass
+    pass

eli5/_feature_names.py

@@ -5,8 +5,8 @@
     Union, Callable, Pattern
 )
 
-import numpy as np  # type: ignore
-import scipy.sparse as sp  # type: ignore
+import numpy as np
+import scipy.sparse as sp
 
 
 class FeatureNames(Sized, Iterable):

eli5/_feature_weights.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
-import numpy as np  # type: ignore
+import numpy as np
 
 from eli5.base import FeatureWeights, FeatureWeight
 from .utils import argsort_k_largest_positive, argsort_k_smallest, mask

eli5/_graphviz.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-import graphviz  # type: ignore
+import graphviz
 
 
 def is_supported():

eli5/base.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 from typing import Any, List, Tuple, Union, Optional
 
-import numpy as np # type: ignore
+import numpy as np
 
 from .base_utils import attrs
 from .formatters.features import FormattedFeatureName

eli5/base_utils.py

@@ -1,9 +1,9 @@
 import inspect
 
-import attr  # type: ignore
+import attr
 
 try:
-    from functools import singledispatch  # type: ignore
+    from functools import singledispatch
 except ImportError:
     from singledispatch import singledispatch  # type: ignore
 

eli5/catboost.py

@@ -1,7 +1,7 @@
 from __future__ import absolute_import, division
 
-import numpy as np  # type: ignore
-import catboost # type: ignore
+import numpy as np
+import catboost
 
 from eli5.explain import explain_weights
 from eli5._feature_importances import get_feature_importance_explanation

eli5/formatters/as_dataframe.py

@@ -2,7 +2,7 @@
 from typing import Any, Dict, List, Optional
 import warnings
 
-import pandas as pd  # type: ignore
+import pandas as pd
 
 import eli5
 from eli5.base import (

eli5/formatters/as_dict.py

@@ -1,7 +1,7 @@
 import six
 
-import attr   # type: ignore
-import numpy as np   # type: ignore
+import attr
+import numpy as np
 
 from .features import FormattedFeatureName
 

eli5/formatters/html.py

@@ -3,8 +3,8 @@
 from itertools import groupby
 from typing import List, Optional, Tuple
 
-import numpy as np  # type: ignore
-from jinja2 import Environment, PackageLoader  # type: ignore
+import numpy as np
+from jinja2 import Environment, PackageLoader
 
 from eli5 import _graphviz
 from eli5.base import (Explanation, TargetExplanation, FeatureWeights,

eli5/formatters/image.py

@@ -2,9 +2,9 @@
 from __future__ import absolute_import
 from typing import Union, Optional, Callable
 
-import numpy as np # type: ignore
-from PIL import Image # type: ignore
-import matplotlib.cm # type: ignore
+import numpy as np
+from PIL import Image
+import matplotlib.cm
 
 from eli5.base import Explanation
 from eli5.nn.gradcam import (

eli5/formatters/text.py

@@ -2,14 +2,16 @@
 from __future__ import absolute_import
 from itertools import chain
 import six
+from tabulate import tabulate
 from typing import List, Optional, Iterator
 
 from eli5.base import Explanation, FeatureImportances
 from . import fields
 from .features import FormattedFeatureName
 from .utils import (
     format_signed, format_value, format_weight, has_any_values_for_weights,
-    replace_spaces, should_highlight_spaces, tabulate)
+    replace_spaces, should_highlight_spaces)
+from .utils import tabulate as eli5_tabulate
 from .trees import tree2text
 
 
@@ -153,7 +155,6 @@ def _decision_tree_lines(explanation):
 
 def _transition_features_lines(explanation):
     # type: (Explanation) -> List[str]
-    from tabulate import tabulate  # type: ignore
     tf = explanation.transition_features
     assert tf is not None
     return [
@@ -203,7 +204,7 @@ def _targets_lines(explanation,  # type: Explanation
 
         w = target.feature_weights
         assert w is not None
-        table = tabulate(
+        table = eli5_tabulate(
             [table_line(fw) for fw in chain(w.pos, reversed(w.neg))],
             header=table_header,
             col_align=col_align,

eli5/formatters/text_helpers.py

@@ -1,7 +1,7 @@
 from collections import Counter
 from typing import List, Optional
 
-import numpy as np  # type: ignore
+import numpy as np
 
 from eli5.base import TargetExplanation, WeightedSpans, DocWeightedSpans
 from eli5.base_utils import attrs

eli5/formatters/trees.py

@@ -24,6 +24,8 @@ def p(*args):
         else:
             assert node.left is not None
             assert node.right is not None
+            assert node.threshold is not None
+
             feat_name = node.feature_name
 
             if depth > 0:

eli5/formatters/utils.py

@@ -2,10 +2,9 @@
 from itertools import chain
 import re
 import six
-from numbers import Real
 from typing import Any, Union, List, Dict, Callable, Match, Optional
 
-import numpy as np  # type: ignore
+import numpy as np
 
 from eli5.base import Explanation
 from .features import FormattedFeatureName
@@ -143,12 +142,12 @@ def tabulate(data,  # type: List[List[Any]]
 
 
 def format_weight(value):
-    # type: (Real) -> str
+    # type: (float) -> str
     return '{:+.3f}'.format(value)
 
 
 def format_value(value):
-    # type: (Optional[Real]) -> str
+    # type: (Optional[float]) -> str
     if value is None:
         return ''
     elif np.isnan(value):

eli5/ipython.py

@@ -3,15 +3,15 @@
 from typing import Any, Dict, Tuple
 import warnings
 
-from IPython.display import HTML, Image  # type: ignore
+from IPython.display import HTML, Image
 
 from .explain import explain_weights, explain_prediction
 from .formatters import format_as_html, fields
 try:
     from .formatters.image import format_as_image
 except ImportError as e:
     # missing dependencies
-    format_as_image = e # type: ignore
+    format_as_image = e  # type: ignore
 
 
 FORMAT_KWARGS = {'include_styles', 'force_weights',

eli5/keras/explain_prediction.py

@@ -2,14 +2,14 @@
 from __future__ import absolute_import
 from typing import Union, Optional, Callable, List, Tuple, Generator, TYPE_CHECKING
 if TYPE_CHECKING:
-    import PIL # type: ignore
-
-import numpy as np # type: ignore
-import keras # type: ignore
-import keras.backend as K # type: ignore
-from keras.models import Model # type: ignore
-from keras.layers import Layer # type: ignore
-from keras.layers import (  # type: ignore
+    import PIL
+
+import numpy as np
+import keras
+import keras.backend as K
+from keras.models import Model
+from keras.layers import Layer
+from keras.layers import (
     Conv2D,
     MaxPooling2D,
     AveragePooling2D,
@@ -26,7 +26,7 @@
     GRU,
     Bidirectional,
 )
-from keras.preprocessing.image import array_to_img # type: ignore
+from keras.preprocessing.image import array_to_img
 
 from eli5.base import (
     Explanation, 

eli5/keras/gradcam.py

@@ -9,11 +9,11 @@
 from __future__ import absolute_import
 from typing import Any, Optional, Tuple, List
 
-import numpy as np # type: ignore
-import keras # type: ignore
-import keras.backend as K # type: ignore
-from keras.models import Model # type: ignore
-from keras.layers import Layer # type: ignore
+import numpy as np
+import keras
+import keras.backend as K
+from keras.models import Model
+from keras.layers import Layer
 
 from eli5.nn.gradcam import (
     _validate_targets,
@@ -128,6 +128,25 @@ def _classification_target(model, targets):
         # from the array of predictions
         predicted_idx = K.argmax(model.output, axis=-1)
 
+<<<<<<< HEAD
     # access value by index
     predicted_val = K.gather(model.output[0, :], predicted_idx)
-    return predicted_idx, predicted_val
+    return predicted_idx, predicted_val
+=======
+def _validate_target(target, output_shape):
+    # type: (int, tuple) -> None
+    """
+    Check whether ``target``, 
+    an integer index into the model's output
+    is valid for the given ``output_shape``.
+    """
+    if isinstance(target, int):
+        output_nodes = output_shape[1:][0]
+        if not (0 <= target < output_nodes):
+            raise ValueError('Prediction target index is ' 
+                             'outside the required range [0, {}). '
+                             'Got {}'.format(output_nodes, target))
+    else:
+        raise TypeError('Prediction target must be int. '
+                        'Got: {}'.format(target))
+>>>>>>> 017c738f8dcf3e31346de49a390835ffafad3f1b

eli5/lightgbm.py

@@ -3,8 +3,8 @@
 from collections import defaultdict
 from typing import DefaultDict, Optional
 
-import numpy as np  # type: ignore
-import lightgbm  # type: ignore
+import numpy as np
+import lightgbm
 
 from eli5.explain import explain_weights, explain_prediction
 from eli5._feature_importances import get_feature_importance_explanation

eli5/lightning.py

@@ -1,9 +1,9 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
-from lightning.impl.base import BaseEstimator  # type: ignore
-from lightning import classification, regression   # type: ignore
-from sklearn.multiclass import OneVsRestClassifier   # type: ignore
+from lightning.impl.base import BaseEstimator
+from lightning import classification, regression
+from sklearn.multiclass import OneVsRestClassifier
 
 from eli5.base import Explanation
 from eli5.base_utils import singledispatch

eli5/lime/_vectorizer.py

@@ -2,8 +2,8 @@
 from __future__ import absolute_import
 from typing import Tuple, Callable, Dict, Optional, List
 
-import numpy as np  # type: ignore
-from sklearn.base import BaseEstimator, TransformerMixin  # type: ignore
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin
 
 from eli5.base import DocWeightedSpans, FeatureWeights
 from eli5.sklearn.text import _get_feature_weights_dict
@@ -13,8 +13,8 @@
 class SingleDocumentVectorizer(BaseEstimator, TransformerMixin):
     """ Fake vectorizer which converts document just to a vector of ones """
 
-    def __init__(self, token_pattern=None):
-        # type: (Optional[str]) -> None
+    def __init__(self, token_pattern):
+        # type: (str) -> None
         self.token_pattern = token_pattern
 
     def fit(self, X, y=None):

eli5/lime/lime.py

@@ -6,12 +6,12 @@
 from __future__ import absolute_import
 from typing import Any, Callable, Dict, Optional
 
-import numpy as np  # type: ignore
-from sklearn.feature_extraction.text import CountVectorizer  # type: ignore
-from sklearn.linear_model import SGDClassifier  # type: ignore
-from sklearn.model_selection import train_test_split  # type: ignore
-from sklearn.utils import check_random_state  # type: ignore
-from sklearn.base import clone, BaseEstimator  # type: ignore
+import numpy as np
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.linear_model import SGDClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.utils import check_random_state
+from sklearn.base import clone, BaseEstimator
 
 import eli5
 from eli5.sklearn.utils import sklearn_version
@@ -148,7 +148,7 @@ def __init__(self,
                  rbf_sigma=None,  # type: float
                  random_state=None,
                  expand_factor=10,  # type: Optional[int]
-                 token_pattern=None,  # type: str
+                 token_pattern=None,  # type: Optional[str]
                  ):
         # type: (...) -> None
         self.n_samples = n_samples
@@ -162,7 +162,7 @@ def __init__(self,
         if char_based is None:
             if token_pattern is None:
                 self.char_based = False  # type: Optional[bool]
-                self.token_pattern = DEFAULT_TOKEN_PATTERN
+                self.token_pattern = DEFAULT_TOKEN_PATTERN  # type: str
             else:
                 self.char_based = None
                 self.token_pattern = token_pattern