Merge branch 'dev' of https://github.com/eonu/sequentia into dev

lib/sequentia/classifiers/hmm/hmm_classifier.py

@@ -45,7 +45,7 @@ def fit(self, models):
         self._encoder = LabelEncoder()
         self._encoder.fit([model.label for model in models])
 
-    def predict(self, X, prior='frequency', verbose=True, return_scores=False, original_labels=True, n_jobs=1):
+    def predict(self, X, prior='frequency', return_scores=False, original_labels=True, verbose=True, n_jobs=1):
         """Predicts the label for an observation sequence (or multiple sequences) according to maximum likelihood or posterior scores.
 
         Parameters
@@ -62,6 +62,12 @@ def predict(self, X, prior='frequency', verbose=True, return_scores=False, origi
 
             Alternatively, class prior probabilities can be specified in an iterable of floats, e.g. `[0.1, 0.3, 0.6]`.
 
+        return_scores: bool
+            Whether to return the scores of each model on the observation sequence(s).
+
+        original_labels: bool
+            Whether to inverse-transform the labels to their original encoding.
+
         verbose: bool
             Whether to display a progress bar or not.
 
@@ -70,12 +76,6 @@ def predict(self, X, prior='frequency', verbose=True, return_scores=False, origi
                 are always displayed in the console, regardless of where you are running this function from
                 (e.g. a Jupyter notebook).
 
-        return_scores: bool
-            Whether to return the scores of each model on the observation sequence(s).
-
-        original_labels: bool
-            Whether to inverse-transform the labels to their original encoding.
-
         n_jobs: int > 0 or -1
             | The number of jobs to run in parallel.
             | Setting this to -1 will use all available CPU cores.
@@ -105,9 +105,9 @@ def predict(self, X, prior='frequency', verbose=True, return_scores=False, origi
             assert np.isclose(sum(prior), 1.), 'Class priors must form a probability distribution by summing to one'
         else:
             self._val.one_of(prior, ['frequency', 'uniform'], desc='prior')
-        self._val.boolean(verbose, desc='verbose')
         self._val.boolean(return_scores, desc='return_scores')
         self._val.boolean(original_labels, desc='original_labels')
+        self._val.boolean(verbose, desc='verbose')
         self._val.restricted_integer(n_jobs, lambda x: x == -1 or x > 0, 'number of jobs', '-1 or greater than zero')
 
         # Create look-up for prior probabilities

lib/sequentia/classifiers/knn/knn_classifier.py

@@ -137,14 +137,17 @@ def fit(self, X, y):
         self._X, self._y = X, self._encoder.transform(y)
         self._n_features = X[0].shape[1]
 
-    def predict(self, X, verbose=True, original_labels=True, n_jobs=1):
+    def predict(self, X, original_labels=True, verbose=True, n_jobs=1):
         """Predicts the label for an observation sequence (or multiple sequences).
 
         Parameters
         ----------
         X: numpy.ndarray (float) or list of numpy.ndarray (float)
             An individual observation sequence or a list of multiple observation sequences.
 
+        original_labels: bool
+            Whether to inverse-transform the labels to their original encoding.
+
         verbose: bool
             Whether to display a progress bar or not.
 
@@ -153,9 +156,6 @@ def predict(self, X, verbose=True, original_labels=True, n_jobs=1):
                 are always displayed in the console, regardless of where you are running this function from
                 (e.g. a Jupyter notebook).
 
-        original_labels: bool
-            Whether to inverse-transform the labels to their original encoding.
-
         n_jobs: int > 0 or -1
             | The number of jobs to run in parallel.
             | Setting this to -1 will use all available CPU cores.
@@ -174,8 +174,8 @@ def predict(self, X, verbose=True, original_labels=True, n_jobs=1):
             raise RuntimeError('The classifier needs to be fitted before predictions are made')
 
         X = self._val.observation_sequences(X, allow_single=True)
-        self._val.boolean(verbose, desc='verbose')
         self._val.boolean(original_labels, desc='original_labels')
+        self._val.boolean(verbose, desc='verbose')
         self._val.restricted_integer(n_jobs, lambda x: x == -1 or x > 0, 'number of jobs', '-1 or greater than zero')
 
         if isinstance(X, np.ndarray):
@@ -215,7 +215,7 @@ def evaluate(self, X, y, verbose=True, n_jobs=1):
         """
         X, y = self._val.observation_sequences_and_labels(X, y)
         self._val.boolean(verbose, desc='verbose')
-        predictions = self.predict(X, verbose=verbose, original_labels=False, n_jobs=n_jobs)
+        predictions = self.predict(X, original_labels=False, verbose=verbose, n_jobs=n_jobs)
         cm = confusion_matrix(self._encoder.transform(y), predictions, labels=self._encoder.transform(self._encoder.classes_))
         return np.sum(np.diag(cm)) / np.sum(cm), cm