Modified documentation and added doc test. Also changed some of the code...

Modified documentation and added doc test. Also changed some of the code according to the increase of test coverage

pytorch_widedeep/preprocessing/_preprocessors.py

@@ -79,12 +79,7 @@ class WidePreprocessor(BasePreprocessor):
            [2, 5],
            [3, 6]])
     >>> wide_preprocessor.feature_dict
-    {'color_r': 1,
-     'color_b': 2,
-     'color_g': 3,
-     'color_size_r-s': 4,
-     'color_size_b-n': 5,
-     'color_size_g-l': 6}
+    {'color_r': 1, 'color_b': 2, 'color_g': 3, 'color_size_r-s': 4, 'color_size_b-n': 5, 'color_size_g-l': 6}
     >>> wide_preprocessor.inverse_transform(X_wide)
       color color_size
     0     r        r-s
@@ -449,14 +444,18 @@ class ImagePreprocessor(BasePreprocessor):
     Examples
     --------
     >>> import pandas as pd
+    >>>
     >>> from pytorch_widedeep.preprocessing import ImagePreprocessor
-    >>> df_train = pd.DataFrame({'images_column': ['galaxy1.png', 'galaxy2.png']})
-    >>> df_test = pd.DataFrame({'images_column': ['galaxy3.png']})
+    >>>
+    >>> path_to_image1 = 'tests/test_data_utils/images/galaxy1.png'
+    >>> path_to_image2 = 'tests/test_data_utils/images/galaxy2.png'
+    >>>
+    >>> df_train = pd.DataFrame({'images_column': [path_to_image1]})
+    >>> df_test = pd.DataFrame({'images_column': [path_to_image2]})
     >>> img_preprocessor = ImagePreprocessor(img_col='images_column', img_path='.', verbose=0)
     >>> resized_images = img_preprocessor.fit_transform(df_train)
     >>> new_resized_images = img_preprocessor.transform(df_train)
 
-
     .. note:: Normalising metrics will only be computed when the
         ``fit_transform`` method is run. Running ``transform`` only will not
         change the computed metrics and running ``fit`` only simply

pytorch_widedeep/utils/fastai_transforms.py

@@ -293,8 +293,7 @@ class Tokenizer:
         >>> texts = ['Machine learning is great', 'but building stuff is even better']
         >>> tok = Tokenizer()
         >>> tok.process_all(texts)
-            [['xxmaj', 'machine', 'learning', 'is', 'great'],
-            ['but', 'building', 'stuff', 'is', 'even', 'better']]
+        [['xxmaj', 'machine', 'learning', 'is', 'great'], ['but', 'building', 'stuff', 'is', 'even', 'better']]
 
         .. note:: Note the token ``TK_MAJ`` (`xxmaj`), used to indicate the
             next word begins with a capital in the original text. For more
@@ -369,9 +368,6 @@ class Vocab:
         >>> texts = ['Machine learning is great', 'but building stuff is even better']
         >>> tokens = Tokenizer().process_all(texts)
         >>> vocab = Vocab.create(tokens, max_vocab=18, min_freq=1)
-        >>> print(vocab.itos)
-        ['xxunk', 'xxpad', 'xxbos', 'xxeos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep',
-        'is', 'machine', 'learning', 'great', 'but', 'building', 'stuff', 'even', 'better']
         >>> vocab.numericalize(['machine', 'learning', 'is', 'great'])
         [10, 11, 9, 12]
         >>> vocab.textify([10, 11, 9, 12])

pytorch_widedeep/utils/image_utils.py

@@ -45,7 +45,7 @@ class AspectAwarePreprocessor:
         --------
         >>> import cv2
         >>> from pytorch_widedeep.utils import AspectAwarePreprocessor
-        >>> img = cv2.imread("galaxy.png")
+        >>> img = cv2.imread("tests/test_data_utils/images/galaxy1.png")
         >>> img.shape
         (694, 890, 3)
         >>> app = AspectAwarePreprocessor(width=224, height=224)

pytorch_widedeep/utils/text_utils.py

@@ -123,7 +123,7 @@ def pad_sequences(
 
 def build_embeddings_matrix(
     vocab: Vocab, word_vectors_path: str, min_freq: int, verbose: int = 1
-) -> np.ndarray:
+) -> np.ndarray:  # pragma: no cover
     r"""
     Build the embedding matrix using pretrained word vectors