Codebase cleanup

docs/sources/index.md

@@ -125,6 +125,7 @@ Keras welcomes all contributions from the community.
 - New features should be documented. Make sure you update the documentation along with your Pull Request.
 - The documentation for every new feature should include a usage example in the form of a code snippet. 
 - All changes should be tested. Make sure any new feature you add has a corresponding unit test.
+- Please no Pull Requests about coding style.
 - Even if you don't contribute to the Keras source code, if you have an application of Keras that is concise and powerful, please consider adding it to our collection of [examples](https://github.com/fchollet/keras/tree/master/examples).
 
 

examples/cifar10_cnn.py

@@ -19,7 +19,7 @@
     (it's still underfitting at that point, though).
 
     Note: the data was pickled with Python 2, and some encoding issues might prevent you
-    from loading it in Python 3. You might have to load it in Python 2, 
+    from loading it in Python 3. You might have to load it in Python 2,
     save it in a different format, load it in Python 3 and repickle it.
 '''
 
@@ -40,16 +40,16 @@
 
 model = Sequential()
 
-model.add(Convolution2D(32, 3, 3, 3, border_mode='full')) 
+model.add(Convolution2D(32, 3, 3, 3, border_mode='full'))
 model.add(Activation('relu'))
 model.add(Convolution2D(32, 32, 3, 3))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(poolsize=(2, 2)))
 model.add(Dropout(0.25))
 
-model.add(Convolution2D(64, 32, 3, 3, border_mode='full')) 
+model.add(Convolution2D(64, 32, 3, 3, border_mode='full'))
 model.add(Activation('relu'))
-model.add(Convolution2D(64, 64, 3, 3)) 
+model.add(Convolution2D(64, 64, 3, 3))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(poolsize=(2, 2)))
 model.add(Dropout(0.25))
@@ -93,7 +93,7 @@
         horizontal_flip=True, # randomly flip images
         vertical_flip=False) # randomly flip images
 
-    # compute quantities required for featurewise normalization 
+    # compute quantities required for featurewise normalization
     # (std, mean, and principal components if ZCA whitening is applied)
     datagen.fit(X_train)
 
@@ -114,11 +114,3 @@
         for X_batch, Y_batch in datagen.flow(X_test, Y_test):
             score = model.test_on_batch(X_batch, Y_batch)
             progbar.add(X_batch.shape[0], values=[("test loss", score)])
-
-
-
-
-
-
-
-

examples/imdb_lstm.py

@@ -15,17 +15,17 @@
 '''
     Train a LSTM on the IMDB sentiment classification task.
 
-    The dataset is actually too small for LSTM to be of any advantage 
+    The dataset is actually too small for LSTM to be of any advantage
     compared to simpler, much faster methods such as TF-IDF+LogReg.
 
-    Notes: 
+    Notes:
 
-    - RNNs are tricky. Choice of batch size is important, 
-    choice of loss and optimizer is critical, etc. 
+    - RNNs are tricky. Choice of batch size is important,
+    choice of loss and optimizer is critical, etc.
     Some configurations won't converge.
 
-    - LSTM loss decrease patterns during training can be quite different 
-    from what you see with CNNs/MLPs/etc. 
+    - LSTM loss decrease patterns during training can be quite different
+    from what you see with CNNs/MLPs/etc.
 
     GPU command:
         THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_lstm.py

examples/kaggle_otto_nn.py

@@ -36,6 +36,7 @@
     Get the data from Kaggle: https://www.kaggle.com/c/otto-group-product-classification-challenge/data
 '''
 
+
 def load_data(path, train=True):
     df = pd.read_csv(path)
     X = df.values.copy()
@@ -47,13 +48,15 @@ def load_data(path, train=True):
         X, ids = X[:, 1:].astype(np.float32), X[:, 0].astype(str)
         return X, ids
 
+
 def preprocess_data(X, scaler=None):
     if not scaler:
         scaler = StandardScaler()
         scaler.fit(X)
     X = scaler.transform(X)
     return X, scaler
 
+
 def preprocess_labels(labels, encoder=None, categorical=True):
     if not encoder:
         encoder = LabelEncoder()
@@ -63,6 +66,7 @@ def preprocess_labels(labels, encoder=None, categorical=True):
         y = np_utils.to_categorical(y)
     return y, encoder
 
+
 def make_submission(y_prob, ids, encoder, fname):
     with open(fname, 'w') as f:
         f.write('id,')

examples/mnist_cnn.py

@@ -41,7 +41,7 @@
 
 model = Sequential()
 
-model.add(Convolution2D(32, 1, 3, 3, border_mode='full')) 
+model.add(Convolution2D(32, 1, 3, 3, border_mode='full'))
 model.add(Activation('relu'))
 model.add(Convolution2D(32, 32, 3, 3))
 model.add(Activation('relu'))

examples/mnist_mlp.py

@@ -20,8 +20,6 @@
 nb_classes = 10
 nb_epoch = 20
 
-
-
 # the data, shuffled and split between tran and test sets
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 

examples/skipgram_word_embeddings.py

@@ -1,30 +1,30 @@
 
 '''
-    We loop over words in a dataset, and for each word, we look at a context window around the word. 
+    We loop over words in a dataset, and for each word, we look at a context window around the word.
     We generate pairs of (pivot_word, other_word_from_same_context) with label 1,
     and pairs of (pivot_word, random_word) with label 0 (skip-gram method).
 
     We use the layer WordContextProduct to learn embeddings for the word couples,
     and compute a proximity score between the embeddings (= p(context|word)),
     trained with our positive and negative labels.
 
-    We then use the weights computed by WordContextProduct to encode words 
-    and demonstrate that the geometry of the embedding space 
+    We then use the weights computed by WordContextProduct to encode words
+    and demonstrate that the geometry of the embedding space
     captures certain useful semantic properties.
 
-    Read more about skip-gram in this particularly gnomic paper by Mikolov et al.: 
+    Read more about skip-gram in this particularly gnomic paper by Mikolov et al.:
         http://arxiv.org/pdf/1301.3781v3.pdf
 
-    Note: you should run this on GPU, otherwise training will be quite slow. 
+    Note: you should run this on GPU, otherwise training will be quite slow.
     On a EC2 GPU instance, expect 3 hours per 10e6 comments (~10e8 words) per epoch with dim_proj=256.
     Should be much faster on a modern GPU.
 
     GPU command:
         THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python skipgram_word_embeddings.py
 
-    Dataset: 5,845,908 Hacker News comments. 
-    Obtain the dataset at: 
-        https://mega.co.nz/#F!YohlwD7R!wec0yNO86SeaNGIYQBOR0A 
+    Dataset: 5,845,908 Hacker News comments.
+    Obtain the dataset at:
+        https://mega.co.nz/#F!YohlwD7R!wec0yNO86SeaNGIYQBOR0A
         (HNCommentsAll.1perline.json.bz2)
 '''
 from __future__ import absolute_import
@@ -66,6 +66,7 @@
 to_replace = [(''', "'")]
 hex_tags = re.compile(r'&.*?;')
 
+
 def clean_comment(comment):
     c = str(comment.encode("utf-8"))
     c = html_tags.sub(' ', c)
@@ -74,6 +75,7 @@ def clean_comment(comment):
     c = hex_tags.sub(' ', c)
     return c
 
+
 def text_generator(path=data_path):
     f = open(path)
     for i, l in enumerate(f):
@@ -120,7 +122,7 @@ def text_generator(path=data_path):
         progbar = generic_utils.Progbar(tokenizer.document_count)
         samples_seen = 0
         losses = []
-        
+
         for i, seq in enumerate(tokenizer.texts_to_sequences_generator(text_generator())):
             # get skipgram couples for one text in the dataset
             couples, labels = sequence.skipgrams(seq, max_features, window_size=4, negative_samples=1., sampling_table=sampling_table)
@@ -158,26 +160,29 @@ def text_generator(path=data_path):
 reverse_word_index = dict([(v, k) for k, v in list(word_index.items())])
 word_index = tokenizer.word_index
 
+
 def embed_word(w):
     i = word_index.get(w)
-    if (not i) or (i<skip_top) or (i>=max_features):
+    if (not i) or (i < skip_top) or (i >= max_features):
         return None
     return norm_weights[i]
 
+
 def closest_to_point(point, nb_closest=10):
     proximities = np.dot(norm_weights, point)
     tups = list(zip(list(range(len(proximities))), proximities))
     tups.sort(key=lambda x: x[1], reverse=True)
-    return [(reverse_word_index.get(t[0]), t[1]) for t in tups[:nb_closest]]  
+    return [(reverse_word_index.get(t[0]), t[1]) for t in tups[:nb_closest]]
+
 
 def closest_to_word(w, nb_closest=10):
     i = word_index.get(w)
-    if (not i) or (i<skip_top) or (i>=max_features):
+    if (not i) or (i < skip_top) or (i >= max_features):
         return []
     return closest_to_point(norm_weights[i].T, nb_closest)
 
 
-''' the resuls in comments below were for: 
+''' the resuls in comments below were for:
     5.8M HN comments
     dim_proj = 256
     nb_epoch = 2
@@ -187,31 +192,31 @@ def closest_to_word(w, nb_closest=10):
     skip_top = 100
     negative_samples = 1.
     window_size = 4
-    and frequency subsampling of factor 10e-5. 
+    and frequency subsampling of factor 10e-5.
 '''
 
-words = ["article", # post, story, hn, read, comments
-"3", # 6, 4, 5, 2
-"two", # three, few, several, each
-"great", # love, nice, working, looking
-"data", # information, memory, database
-"money", # company, pay, customers, spend
-"years", # ago, year, months, hours, week, days
-"android", # ios, release, os, mobile, beta
-"javascript", # js, css, compiler, library, jquery, ruby
-"look", # looks, looking
-"business", # industry, professional, customers
-"company", # companies, startup, founders, startups
-"after", # before, once, until
-"own", # personal, our, having
-"us", # united, country, american, tech, diversity, usa, china, sv
-"using", # javascript, js, tools (lol)
-"here", # hn, post, comments
+words = [
+    "article", # post, story, hn, read, comments
+    "3", # 6, 4, 5, 2
+    "two", # three, few, several, each
+    "great", # love, nice, working, looking
+    "data", # information, memory, database
+    "money", # company, pay, customers, spend
+    "years", # ago, year, months, hours, week, days
+    "android", # ios, release, os, mobile, beta
+    "javascript", # js, css, compiler, library, jquery, ruby
+    "look", # looks, looking
+    "business", # industry, professional, customers
+    "company", # companies, startup, founders, startups
+    "after", # before, once, until
+    "own", # personal, our, having
+    "us", # united, country, american, tech, diversity, usa, china, sv
+    "using", # javascript, js, tools (lol)
+    "here", # hn, post, comments
 ]
 
 for w in words:
     res = closest_to_word(w)
     print('====', w)
     for r in res:
         print(r)
-

keras/activations.py

@@ -1,35 +1,44 @@
 from __future__ import absolute_import
 import theano.tensor as T
 
+
 def softmax(x):
     return T.nnet.softmax(x.reshape((-1, x.shape[-1]))).reshape(x.shape)
 
+
 def time_distributed_softmax(x):
     import warnings
     warnings.warn("time_distributed_softmax is deprecated. Just use softmax!", DeprecationWarning)
     return softmax(x)
 
+
 def softplus(x):
     return T.nnet.softplus(x)
 
+
 def relu(x):
     return (x + abs(x)) / 2.0
 
+
 def tanh(x):
     return T.tanh(x)
 
+
 def sigmoid(x):
     return T.nnet.sigmoid(x)
 
+
 def hard_sigmoid(x):
     return T.nnet.hard_sigmoid(x)
 
+
 def linear(x):
     '''
     The function returns the variable that is passed in, so all types work
     '''
     return x
 
+
 from .utils.generic_utils import get_from_module
 def get(identifier):
     return get_from_module(identifier, globals(), 'activation function')