Merge pull request #844 from RasaHQ/auto-pep8-all

testing everything with pep8

.travis.yml

@@ -26,8 +26,9 @@ before_script:
 - mkdir $HOME/tmp
 - export TMPDIR=$HOME/tmp
 script:
-- py.test tests/base --cov rasa_nlu --pep8 -v --cov-append
-- py.test tests/training --cov rasa_nlu --pep8 -v --cov-append
+- py.test --pep8 -m pep8
+- py.test tests/base --cov rasa_nlu -v --cov-append
+- py.test tests/training --cov rasa_nlu -v --cov-append
 after_success:
 - coveralls
 jobs:

rasa_nlu/classifiers/keyword_intent_classifier.py

@@ -31,7 +31,8 @@ def parse(self, text):
 
         _text = text.lower()
 
-        def is_present(x): return x in _text
+        def is_present(x):
+            return x in _text
 
         if any(map(is_present, self.his)):
             return "greet"

rasa_nlu/classifiers/mitie_intent_classifier.py

@@ -22,7 +22,6 @@
 
 
 class MitieIntentClassifier(Component):
-
     name = "intent_classifier_mitie"
 
     provides = ["intent"]
@@ -37,7 +36,7 @@ def required_packages(cls):
         # type: () -> List[Text]
         return ["mitie"]
 
-    def train(self, training_data, config,  **kwargs):
+    def train(self, training_data, config, **kwargs):
         # type: (TrainingData, RasaNLUConfig, **Any) -> None
         import mitie
 

rasa_nlu/download.py

@@ -42,7 +42,7 @@ def download_mitie_fe_file(fe_file):    # pragma: no cover
     response = requests.get(_fe_file_url, stream=True)
 
     with io.open(fe_file, "wb") as output:
-        for data in tqdm(response.iter_content(chunk_size=1024*1024), unit='MB', unit_scale=True):
+        for data in tqdm(response.iter_content(chunk_size=1024 * 1024), unit='MB', unit_scale=True):
             output.write(data)
     logger.debug("file written! {0}, {1}".format(fe_file, os.path.exists(fe_file)))
 

rasa_nlu/emulators/luis.py

@@ -51,5 +51,5 @@ def normalise_response_json(self, data):
                     "endIndex": None,
                     "score": None
                 } for e in data["entities"]
-                ] if "entities" in data else []
+            ] if "entities" in data else []
         }

rasa_nlu/evaluate.py

@@ -22,6 +22,7 @@
                              "ordinal", "phone-number", "timezone", "temperature", "time", "url", "volume"}
 entity_processors = {"ner_synonyms"}
 
+
 def create_argparser():  # pragma: no cover
     import argparse
     parser = argparse.ArgumentParser(
@@ -94,6 +95,7 @@ def log_evaluation_table(test_y, preds):  # pragma: no cover
     logger.info("Accuracy:  {}".format(accuracy))
     logger.info("Classification report: \n{}".format(report))
 
+
 def remove_empty_intent_examples(targets, predictions):
     """Removes those examples without intent."""
     targets = np.array(targets)
@@ -103,7 +105,7 @@ def remove_empty_intent_examples(targets, predictions):
     return targets, predictions
 
 
-def prepare_data(data, cutoff = 5):
+def prepare_data(data, cutoff=5):
     """Remove intent groups with less than cutoff instances."""
     data = data.sorted_intent_examples()
     logger.info("Raw data intent examples: {}".format(len(data)))
@@ -461,6 +463,7 @@ def run_cv_evaluation(data, n_folds, nlu_config):
 
     return dict(results)
 
+
 if __name__ == '__main__':  # pragma: no cover
     parser = create_argparser()
     args = parser.parse_args()
@@ -476,10 +479,10 @@ def run_cv_evaluation(data, n_folds, nlu_config):
 
     if args.mode == "crossvalidation":
         data = training_data.load_data(args.data)
-        data = prepare_data(data, cutoff = 5)
+        data = prepare_data(data, cutoff=5)
         results = run_cv_evaluation(data, int(args.folds), nlu_config)
         logger.info("CV evaluation (n={})".format(args.folds))
-        for k,v in results.items():
+        for k, v in results.items():
             logger.info("{}: {:.3f} ({:.3f})".format(k, np.mean(v), np.std(v)))
     elif args.mode == "evaluation":
         run_evaluation(nlu_config, args.model)

rasa_nlu/training_data/formats/dialogflow.py

@@ -20,6 +20,7 @@
 DIALOGFLOW_ENTITIES = "dialogflow_entities"
 DIALOGFLOW_ENTITY_ENTRIES = "dialogflow_entity_entries"
 
+
 class DialogflowReader(TrainingDataReader):
     def read(self, fn, **kwargs):
         # type: ([Text]) -> TrainingData
@@ -42,7 +43,6 @@ def read(self, fn, **kwargs):
         elif fformat == DIALOGFLOW_ENTITIES:
             return self._read_entities(examples_js)
 
-
     def _read_intent(self, intent_js, examples_js):
         """Reads the intent and examples from respective jsons."""
         intent = intent_js.get("name")

rasa_nlu/training_data/formats/luis.py

@@ -48,4 +48,4 @@ def read_from_json(self, js, **kwargs):
             if intent:
                 data["intent"] = intent
             training_examples.append(Message(text, data))
-        return TrainingData(training_examples, regex_features=regex_features)
+        return TrainingData(training_examples, regex_features=regex_features)

rasa_nlu/training_data/formats/markdown.py

@@ -147,10 +147,10 @@ def dumps(self, training_data):
     def _generate_training_examples_md(self, training_data):
         """generates markdown training examples."""
         training_examples = sorted([e.as_dict() for e in training_data.training_examples],
-                                      key=lambda k: k['intent'])
+                                   key=lambda k: k['intent'])
         md = u''
         for i, example in enumerate(training_examples):
-            if i == 0 or training_examples[i-1]['intent'] != example['intent']:
+            if i == 0 or training_examples[i - 1]['intent'] != example['intent']:
                 md += self._generate_section_header_md(INTENT, example['intent'], i != 0)
 
             md += self._generate_item_md(self._generate_message_md(example))
@@ -160,7 +160,7 @@ def _generate_training_examples_md(self, training_data):
     def _generate_synonyms_md(self, training_data):
         """generates markdown for entity synomyms."""
         entity_synonyms = sorted(training_data.entity_synonyms.items(),
-                                      key=lambda x: x[1])
+                                 key=lambda x: x[1])
         md = u''
         for i, synonym in enumerate(entity_synonyms):
             if i == 0 or entity_synonyms[i - 1][1] != synonym[1]:
@@ -183,7 +183,7 @@ def _generate_regex_features_md(self, training_data):
 
         return md
 
-    def _generate_section_header_md(self, section_type, title, prepend_newline = True):
+    def _generate_section_header_md(self, section_type, title, prepend_newline=True):
         """generates markdown section header."""
         prefix = "\n" if prepend_newline else ""
         return prefix + "## {}:{}\n".format(section_type, title)
@@ -218,4 +218,3 @@ def _generate_entity_md(self, text, entity):
             entity_type += ":{}".format(entity['value'])
 
         return '[{}]({})'.format(entity_text, entity_type)
-

rasa_nlu/training_data/formats/wit.py

@@ -41,4 +41,4 @@ def read_from_json(self, js, **kwargs):
             if entities is not None:
                 data["entities"] = entities
             training_examples.append(Message(text, data))
-        return TrainingData(training_examples)
+        return TrainingData(training_examples)

rasa_nlu/training_data/training_data.py

@@ -175,13 +175,13 @@ def validate(self):
         for intent, count in self.examples_per_intent.items():
             if count < self.MIN_EXAMPLES_PER_INTENT:
                 warnings.warn("Intent '{}' has only {} training examples! "
-                            "Minimum is {}, training may fail.".format(intent, count,
-                                                                       self.MIN_EXAMPLES_PER_INTENT))
+                              "Minimum is {}, training may fail.".format(intent, count,
+                                                                         self.MIN_EXAMPLES_PER_INTENT))
         for entity_type, count in self.examples_per_entity.items():
             if count < self.MIN_EXAMPLES_PER_ENTITY:
                 warnings.warn("Entity '{}' has only {} training examples! "
-                            "minimum is {}, training may fail.".format(entity_type, count,
-                                                                       self.MIN_EXAMPLES_PER_ENTITY))
+                              "minimum is {}, training may fail.".format(entity_type, count,
+                                                                         self.MIN_EXAMPLES_PER_ENTITY))
 
     def print_stats(self):
         logger.info("Training data stats: \n" +

rasa_nlu/training_data/util.py

@@ -23,4 +23,4 @@ def transform_entity_synonyms(synonyms, known_synonyms=None):
 def check_duplicate_synonym(entity_synonyms, text, syn, context_str=""):
     if text in entity_synonyms and entity_synonyms[text] != syn:
         logger.warning("Found inconsistent entity synonyms while {0}, overwriting {1}->{2}"
-                       "with {1}->{2} during merge".format(context_str, text, entity_synonyms[text], syn))
+                       "with {1}->{2} during merge".format(context_str, text, entity_synonyms[text], syn))

setup.cfg

@@ -3,7 +3,11 @@
 pep8maxlinelength = 120
 pep8ignore =
     docs/conf.py ALL
+    *.py W503
+    *.py E126
 
+# ignoring W503: line break occurred before a binary operator
+# ignoring E126: continuation line over-indented for hanging indent
 
 [metadata]
 description-file = README.md

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup
 
 __version__ = None  # Avoids IDE errors, but actual version is read from version.py
-exec (open('rasa_nlu/version.py').read())
+exec(open('rasa_nlu/version.py').read())
 
 tests_requires = [
     "pytest",

tests/base/test_emulators.py

@@ -70,7 +70,7 @@ def test_luis_response():
                 "endIndex": None,
                 "score": None
             } for e in data["entities"]
-            ]
+        ]
     }
 
 

tests/evaluation.py

@@ -21,6 +21,7 @@
 
 logging.basicConfig(level="DEBUG")
 
+
 @pytest.fixture(scope="module")
 def duckling_interpreter(component_builder):
     _conf = utilities.base_test_conf("")
@@ -214,11 +215,11 @@ def test_prepare_data():
     td = training_data.load_data('data/examples/rasa/demo-rasa.json')
     clean_data = prepare_data(td, 0)
     unique_intents = sorted(set([i.data["intent"] for i in clean_data]))
-    assert(unique_intents == ['affirm', 'goodbye', 'greet', 'restaurant_search'])
+    assert (unique_intents == ['affirm', 'goodbye', 'greet', 'restaurant_search'])
 
     clean_data = prepare_data(td, 10)
     unique_intents = sorted(set([i.data["intent"] for i in clean_data]))
-    assert(unique_intents == ['affirm', 'restaurant_search'])
+    assert (unique_intents == ['affirm', 'restaurant_search'])
 
 
 def test_run_cv_evaluation():
@@ -230,11 +231,11 @@ def test_run_cv_evaluation():
     np.seed(2018)
     results = run_cv_evaluation(td, n_folds, nlu_config)
 
-    rel_tol=1e-09
-    abs_tol=0.01
+    rel_tol = 1e-09
+    abs_tol = 0.01
 
     acc = np.mean(results["accuracy"])
-    exp_acc = 0.65 # expected result
+    exp_acc = 0.65  # expected result
     np.testing.assert_approx_equal(acc, exp_acc, significant=5)