adding space to shape and putting // in average division

Author: dsullivan7

Diff for: benchmarks/bench_sgd_regression.py

@@ -93,7 +93,7 @@
             clf = SGDRegressor(alpha=alpha / n_train, fit_intercept=False,
                                n_iter=n_iter, learning_rate="invscaling",
                                eta0=.002, power_t=0.05,
-                               average=(n_iter * n_train / 2))
+                               average=(n_iter * n_train // 2))
 
             tstart = time()
             clf.fit(X_train, y_train)
@@ -122,7 +122,7 @@
         pl.plot(list_n_samples, np.sqrt(sgd_results[:, j, 0]),
                 label="SGDRegressor")
         pl.plot(list_n_samples, np.sqrt(asgd_results[:, j, 0]),
-                label="A-SGD")
+                label="A-SGDRegressor")
         pl.plot(list_n_samples, np.sqrt(ridge_results[:, j, 0]),
                 label="Ridge")
         pl.legend(prop={"size": 10})
@@ -137,7 +137,7 @@
         pl.plot(list_n_samples, np.sqrt(sgd_results[:, j, 1]),
                 label="SGDRegressor")
         pl.plot(list_n_samples, np.sqrt(asgd_results[:, j, 1]),
-                label="A-SGD")
+                label="A-SGDRegressor")
         pl.plot(list_n_samples, np.sqrt(ridge_results[:, j, 1]),
                 label="Ridge")
         pl.legend(prop={"size": 10})

Diff for: sklearn/linear_model/stochastic_gradient.py

@@ -494,18 +494,18 @@ def partial_fit(self, X, y, classes=None, sample_weight=None):
         X : {array-like, sparse matrix}, shape (n_samples, n_features)
             Subset of the training data
 
-        y : numpy array, shape (n_samples,)
+        y : numpy array, shape (n_samples, )
             Subset of the target values
 
-        classes : array, shape (n_classes,)
+        classes : array, shape (n_classes, )
             Classes across all calls to partial_fit.
             Can be obtained by via `np.unique(y_all)`, where y_all is the
             target vector of the entire dataset.
             This argument is required for the first call to partial_fit
             and can be omitted in the subsequent calls.
             Note that y doesn't need to contain all labels in `classes`.
 
-        sample_weight : array-like, shape (n_samples,), optional
+        sample_weight : array-like, shape (n_samples, ), optional
             Weights applied to individual samples.
             If not provided, uniform weights are assumed.
 
@@ -527,16 +527,16 @@ def fit(self, X, y, coef_init=None, intercept_init=None,
         X : {array-like, sparse matrix}, shape (n_samples, n_features)
             Training data
 
-        y : numpy array, shape (n_samples,)
+        y : numpy array, shape (n_samples, )
             Target values
 
         coef_init : array, shape (n_classes,n_features)
             The initial coefficients to warm-start the optimization.
 
-        intercept_init : array, shape (n_classes,)
+        intercept_init : array, shape (n_classes, )
             The initial intercept to warm-start the optimization.
 
-        sample_weight : array-like, shape (n_samples,), optional
+        sample_weight : array-like, shape (n_samples, ), optional
             Weights applied to individual samples.
             If not provided, uniform weights are assumed.
 
@@ -672,7 +672,7 @@ class SGDClassifier(BaseSGDClassifier, _LearntSelectorMixin):
     n_features)
         Weights assigned to the features.
 
-    intercept_ : array, shape (1,) if n_classes == 2 else (n_classes,)
+    intercept_ : array, shape (1, ) if n_classes == 2 else (n_classes, )
         Constants in decision function.
 
     Examples
@@ -888,10 +888,10 @@ def partial_fit(self, X, y, sample_weight=None):
         X : {array-like, sparse matrix}, shape (n_samples, n_features)
             Subset of training data
 
-        y : numpy array of shape (n_samples,)
+        y : numpy array of shape (n_samples, )
             Subset of target values
 
-        sample_weight : array-like, shape (n_samples,), optional
+        sample_weight : array-like, shape (n_samples, ), optional
             Weights applied to individual samples.
             If not provided, uniform weights are assumed.
 
@@ -938,16 +938,16 @@ def fit(self, X, y, coef_init=None, intercept_init=None,
         X : {array-like, sparse matrix}, shape (n_samples, n_features)
             Training data
 
-        y : numpy array, shape (n_samples,)
+        y : numpy array, shape (n_samples, )
             Target values
 
-        coef_init : array, shape (n_features,)
+        coef_init : array, shape (n_features, )
             The initial coefficients to warm-start the optimization.
 
-        intercept_init : array, shape (1,)
+        intercept_init : array, shape (1, )
             The initial intercept to warm-start the optimization.
 
-        sample_weight : array-like, shape (n_samples,), optional
+        sample_weight : array-like, shape (n_samples, ), optional
             Weights applied to individual samples (1. for unweighted).
 
         Returns
@@ -969,7 +969,7 @@ def decision_function(self, X):
 
         Returns
         -------
-        array, shape (n_samples,)
+        array, shape (n_samples, )
            Predicted target values per element in X.
         """
         X = check_array(X, accept_sparse='csr')
@@ -987,7 +987,7 @@ def predict(self, X):
 
         Returns
         -------
-        array, shape (n_samples,)
+        array, shape (n_samples, )
            Predicted target values per element in X.
         """
         return self.decision_function(X)
@@ -1159,16 +1159,16 @@ class SGDRegressor(BaseSGDRegressor, _LearntSelectorMixin):
 
     Attributes
     ----------
-    coef_ : array, shape (n_features,)
+    coef_ : array, shape (n_features, )
         Weights asigned to the features.
 
-    intercept_ : array, shape (1,)
+    intercept_ : array, shape (1, )
         The intercept term.
 
-    `average_coef_` : array, shape (n_features,)
+    `average_coef_` : array, shape (n_features, )
         Averaged weights assigned to the features.
 
-    `average_intercept_` : array, shape (1)
+    `average_intercept_` : array, shape (1, )
         The averaged intercept term.
 
     Examples