FIX precision to float64 across the codebase

raghavrv · raghavrv · commit 31d1de0552a5 · 2015-10-12T11:46:59.000+02:00
diff --git a/doc/modules/preprocessing.rst b/doc/modules/preprocessing.rst
@@ -398,7 +398,7 @@ Continuing the example above::
 
   >>> enc = preprocessing.OneHotEncoder()
   >>> enc.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])  # doctest: +ELLIPSIS
-  OneHotEncoder(categorical_features='all', dtype=<... 'float'>,
+  OneHotEncoder(categorical_features='all', dtype=<... 'numpy.float64'>,
          handle_unknown='error', n_values='auto', sparse=True)
   >>> enc.transform([[0, 1, 3]]).toarray()
   array([[ 1.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.]])
diff --git a/sklearn/cluster/hierarchical.py b/sklearn/cluster/hierarchical.py
@@ -234,7 +234,7 @@ def ward_tree(X, connectivity=None, n_components=None, n_clusters=None,
     moments_1[:n_samples] = 1
     moments_2 = np.zeros((n_nodes, n_features), order='C')
     moments_2[:n_samples] = X
-    inertia = np.empty(len(coord_row), dtype=np.float, order='C')
+    inertia = np.empty(len(coord_row), dtype=np.float64, order='C')
     _hierarchical.compute_ward_dist(moments_1, moments_2, coord_row, coord_col,
                                     inertia)
     inertia = list(six.moves.zip(inertia, coord_row, coord_col))
@@ -279,7 +279,7 @@ def ward_tree(X, connectivity=None, n_components=None, n_clusters=None,
         coord_row = np.empty(coord_col.shape, dtype=np.intp, order='C')
         coord_row.fill(k)
         n_additions = len(coord_row)
-        ini = np.empty(n_additions, dtype=np.float, order='C')
+        ini = np.empty(n_additions, dtype=np.float64, order='C')
 
         _hierarchical.compute_ward_dist(moments_1, moments_2,
                                         coord_row, coord_col, ini)
diff --git a/sklearn/datasets/base.py b/sklearn/datasets/base.py
@@ -279,7 +279,7 @@ def load_iris():
         target = np.empty((n_samples,), dtype=np.int)
 
         for i, ir in enumerate(data_file):
-            data[i] = np.asarray(ir[:-1], dtype=np.float)
+            data[i] = np.asarray(ir[:-1], dtype=np.float64)
             target[i] = np.asarray(ir[-1], dtype=np.int)
 
     with open(join(module_path, 'descr', 'iris.rst')) as rst_file:
@@ -342,7 +342,7 @@ def load_breast_cancer():
         target = np.empty((n_samples,), dtype=np.int)
 
         for count, value in enumerate(data_file):
-            data[count] = np.asarray(value[:-1], dtype=np.float)
+            data[count] = np.asarray(value[:-1], dtype=np.float64)
             target[count] = np.asarray(value[-1], dtype=np.int)
 
     with open(join(module_path, 'descr', 'breast_cancer.rst')) as rst_file:
@@ -536,8 +536,8 @@ def load_boston():
         feature_names = np.array(temp)
 
         for i, d in enumerate(data_file):
-            data[i] = np.asarray(d[:-1], dtype=np.float)
-            target[i] = np.asarray(d[-1], dtype=np.float)
+            data[i] = np.asarray(d[:-1], dtype=np.float64)
+            target[i] = np.asarray(d[-1], dtype=np.float64)
 
     return Bunch(data=data,
                  target=target,
diff --git a/sklearn/decomposition/factor_analysis.py b/sklearn/decomposition/factor_analysis.py
@@ -151,7 +151,7 @@ def fit(self, X, y=None):
         -------
         self
         """
-        X = check_array(X, copy=self.copy, dtype=np.float)
+        X = check_array(X, copy=self.copy, dtype=np.float64)
 
         n_samples, n_features = X.shape
         n_components = self.n_components
diff --git a/sklearn/decomposition/incremental_pca.py b/sklearn/decomposition/incremental_pca.py
@@ -164,7 +164,7 @@ def fit(self, X, y=None):
         self.noise_variance_ = None
         self.var_ = None
         self.n_samples_seen_ = 0
-        X = check_array(X, dtype=np.float)
+        X = check_array(X, dtype=np.float64)
         n_samples, n_features = X.shape
 
         if self.batch_size is None:
@@ -190,7 +190,7 @@ def partial_fit(self, X, y=None):
         self: object
             Returns the instance itself.
         """
-        X = check_array(X, copy=self.copy, dtype=np.float)
+        X = check_array(X, copy=self.copy, dtype=np.float64)
         n_samples, n_features = X.shape
         if not hasattr(self, 'components_'):
             self.components_ = None
diff --git a/sklearn/ensemble/tests/test_gradient_boosting.py b/sklearn/ensemble/tests/test_gradient_boosting.py
@@ -286,8 +286,8 @@ def test_regression_synthetic():
 
 
 def test_feature_importances():
-    X = np.array(boston.data, dtype=np.float32)
-    y = np.array(boston.target, dtype=np.float32)
+    X = np.array(boston.data, dtype=np.float64)
+    y = np.array(boston.target, dtype=np.float64)
 
     for presort in True, False:
         clf = GradientBoostingRegressor(n_estimators=100, max_depth=5,
@@ -558,11 +558,11 @@ def test_float_class_labels():
     # Test with float class labels.
     clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
 
-    float_y = np.asarray(y, dtype=np.float32)
+    float_y = np.asarray(y, dtype=np.float64)
 
     clf.fit(X, float_y)
     assert_array_equal(clf.predict(T),
-                       np.asarray(true_result, dtype=np.float32))
+                       np.asarray(true_result, dtype=np.float64))
     assert_equal(100, len(clf.estimators_))
 
 
diff --git a/sklearn/ensemble/tests/test_gradient_boosting_loss_functions.py b/sklearn/ensemble/tests/test_gradient_boosting_loss_functions.py
@@ -71,7 +71,7 @@ def test_sample_weight_smoke():
     # least squares
     loss = LeastSquaresError(1)
     loss_wo_sw = loss(y, pred)
-    loss_w_sw = loss(y, pred, np.ones(pred.shape[0], dtype=np.float32))
+    loss_w_sw = loss(y, pred, np.ones(pred.shape[0], dtype=np.float64))
     assert_almost_equal(loss_wo_sw, loss_w_sw)
 
 
@@ -113,30 +113,30 @@ def test_sample_weight_init_estimators():
 
 
 def test_weighted_percentile():
-    y = np.empty(102, dtype=np.float)
+    y = np.empty(102, dtype=np.float64)
     y[:50] = 0
     y[-51:] = 2
     y[-1] = 100000
     y[50] = 1
-    sw = np.ones(102, dtype=np.float)
+    sw = np.ones(102, dtype=np.float64)
     sw[-1] = 0.0
     score = _weighted_percentile(y, sw, 50)
     assert score == 1
 
 
 def test_weighted_percentile_equal():
-    y = np.empty(102, dtype=np.float)
+    y = np.empty(102, dtype=np.float64)
     y.fill(0.0)
-    sw = np.ones(102, dtype=np.float)
+    sw = np.ones(102, dtype=np.float64)
     sw[-1] = 0.0
     score = _weighted_percentile(y, sw, 50)
     assert score == 0
 
 
 def test_weighted_percentile_zero_weight():
-    y = np.empty(102, dtype=np.float)
+    y = np.empty(102, dtype=np.float64)
     y.fill(1.0)
-    sw = np.ones(102, dtype=np.float)
+    sw = np.ones(102, dtype=np.float64)
     sw.fill(0.0)
     score = _weighted_percentile(y, sw, 50)
     assert score == 1.0
diff --git a/sklearn/ensemble/weight_boosting.py b/sklearn/ensemble/weight_boosting.py
@@ -111,7 +111,7 @@ def fit(self, X, y, sample_weight=None):
 
         if sample_weight is None:
             # Initialize weights to 1 / n_samples
-            sample_weight = np.empty(X.shape[0], dtype=np.float)
+            sample_weight = np.empty(X.shape[0], dtype=np.float64)
             sample_weight[:] = 1. / X.shape[0]
         else:
             # Normalize existing weights
@@ -128,8 +128,8 @@ def fit(self, X, y, sample_weight=None):
 
         # Clear any previous fit results
         self.estimators_ = []
-        self.estimator_weights_ = np.zeros(self.n_estimators, dtype=np.float)
-        self.estimator_errors_ = np.ones(self.n_estimators, dtype=np.float)
+        self.estimator_weights_ = np.zeros(self.n_estimators, dtype=np.float64)
+        self.estimator_errors_ = np.ones(self.n_estimators, dtype=np.float64)
 
         for iboost in range(self.n_estimators):
             # Boosting step
diff --git a/sklearn/feature_extraction/tests/test_image.py b/sklearn/feature_extraction/tests/test_image.py
@@ -51,8 +51,8 @@ def test_grid_to_graph():
     assert_true(A.dtype == np.bool)
     A = grid_to_graph(n_x=size, n_y=size, n_z=size, mask=mask, dtype=np.int)
     assert_true(A.dtype == np.int)
-    A = grid_to_graph(n_x=size, n_y=size, n_z=size, mask=mask, dtype=np.float)
-    assert_true(A.dtype == np.float)
+    A = grid_to_graph(n_x=size, n_y=size, n_z=size, mask=mask, dtype=np.float64)
+    assert_true(A.dtype == np.float64)
 
 
 def test_connect_regions():
@@ -75,12 +75,12 @@ def test_connect_regions_with_grid():
 
 
 def _downsampled_lena():
-    lena = sp.misc.lena().astype(np.float32)
+    lena = sp.misc.lena().astype(np.float64)
     lena = (lena[::2, ::2] + lena[1::2, ::2] + lena[::2, 1::2]
             + lena[1::2, 1::2])
     lena = (lena[::2, ::2] + lena[1::2, ::2] + lena[::2, 1::2]
             + lena[1::2, 1::2])
-    lena = lena.astype(np.float)
+    lena = lena.astype(np.float64)
     lena /= 16.0
     return lena
 
diff --git a/sklearn/feature_selection/tests/test_chi2.py b/sklearn/feature_selection/tests/test_chi2.py
@@ -39,7 +39,7 @@ def test_chi2():
     chi2 = mkchi2(k=2).fit(X, y)
     assert_equal(sorted(chi2.get_support(indices=True)), [0, 2])
 
-    Xsp = csr_matrix(X, dtype=np.float)
+    Xsp = csr_matrix(X, dtype=np.float64)
     chi2 = mkchi2(k=2).fit(Xsp, y)
     assert_equal(sorted(chi2.get_support(indices=True)), [0, 2])
     Xtrans = chi2.transform(Xsp)
diff --git a/sklearn/feature_selection/univariate_selection.py b/sklearn/feature_selection/univariate_selection.py
@@ -267,7 +267,7 @@ def f_regression(X, y, center=True):
     """
     if issparse(X) and center:
         raise ValueError("center=True only allowed for dense data")
-    X, y = check_X_y(X, y, ['csr', 'csc', 'coo'], dtype=np.float)
+    X, y = check_X_y(X, y, ['csr', 'csc', 'coo'], dtype=np.float64)
     if center:
         y = y - np.mean(y)
         X = X.copy('F')  # faster in fortran
diff --git a/sklearn/gaussian_process/correlation_models.py b/sklearn/gaussian_process/correlation_models.py
@@ -38,8 +38,8 @@ def absolute_exponential(theta, d):
         An array with shape (n_eval, ) containing the values of the
         autocorrelation model.
     """
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.abs(np.asarray(d, dtype=np.float))
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.abs(np.asarray(d, dtype=np.float64))
 
     if d.ndim > 1:
         n_features = d.shape[1]
@@ -81,8 +81,8 @@ def squared_exponential(theta, d):
         autocorrelation model.
     """
 
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.asarray(d, dtype=np.float)
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.asarray(d, dtype=np.float64)
 
     if d.ndim > 1:
         n_features = d.shape[1]
@@ -125,8 +125,8 @@ def generalized_exponential(theta, d):
         model.
     """
 
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.asarray(d, dtype=np.float)
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.asarray(d, dtype=np.float64)
 
     if d.ndim > 1:
         n_features = d.shape[1]
@@ -174,8 +174,8 @@ def pure_nugget(theta, d):
         model.
     """
 
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.asarray(d, dtype=np.float)
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.asarray(d, dtype=np.float64)
 
     n_eval = d.shape[0]
     r = np.zeros(n_eval)
@@ -211,8 +211,8 @@ def cubic(theta, d):
         model.
     """
 
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.asarray(d, dtype=np.float)
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.asarray(d, dtype=np.float64)
 
     if d.ndim > 1:
         n_features = d.shape[1]
@@ -261,8 +261,8 @@ def linear(theta, d):
         model.
     """
 
-    theta = np.asarray(theta, dtype=np.float)
-    d = np.asarray(d, dtype=np.float)
+    theta = np.asarray(theta, dtype=np.float64)
+    d = np.asarray(d, dtype=np.float64)
 
     if d.ndim > 1:
         n_features = d.shape[1]
diff --git a/sklearn/gaussian_process/regression_models.py b/sklearn/gaussian_process/regression_models.py
@@ -30,7 +30,7 @@ def constant(x):
         An array with shape (n_eval, p) with the values of the regression
         model.
     """
-    x = np.asarray(x, dtype=np.float)
+    x = np.asarray(x, dtype=np.float64)
     n_eval = x.shape[0]
     f = np.ones([n_eval, 1])
     return f
@@ -54,7 +54,7 @@ def linear(x):
         An array with shape (n_eval, p) with the values of the regression
         model.
     """
-    x = np.asarray(x, dtype=np.float)
+    x = np.asarray(x, dtype=np.float64)
     n_eval = x.shape[0]
     f = np.hstack([np.ones([n_eval, 1]), x])
     return f
@@ -80,7 +80,7 @@ def quadratic(x):
         model.
     """
 
-    x = np.asarray(x, dtype=np.float)
+    x = np.asarray(x, dtype=np.float64)
     n_eval, n_features = x.shape
     f = np.hstack([np.ones([n_eval, 1]), x])
     for k in range(n_features):
diff --git a/sklearn/isotonic.py b/sklearn/isotonic.py
@@ -119,11 +119,11 @@ def isotonic_regression(y, sample_weight=None, y_min=None, y_max=None,
     "Active set algorithms for isotonic regression; A unifying framework"
     by Michael J. Best and Nilotpal Chakravarti, section 3.
     """
-    y = np.asarray(y, dtype=np.float)
+    y = np.asarray(y, dtype=np.float64)
     if sample_weight is None:
         sample_weight = np.ones(len(y), dtype=y.dtype)
     else:
-        sample_weight = np.asarray(sample_weight, dtype=np.float)
+        sample_weight = np.asarray(sample_weight, dtype=np.float64)
     if not increasing:
         y = y[::-1]
         sample_weight = sample_weight[::-1]
diff --git a/sklearn/linear_model/randomized_l1.py b/sklearn/linear_model/randomized_l1.py
@@ -161,7 +161,7 @@ def _randomized_lasso(X, y, weights, mask, alpha=1., verbose=False,
     X -= X.mean(axis=0)
     y -= y.mean()
 
-    alpha = np.atleast_1d(np.asarray(alpha, dtype=np.float))
+    alpha = np.atleast_1d(np.asarray(alpha, dtype=np.float64))
 
     X = (1 - weights) * X
     with warnings.catch_warnings():
@@ -355,7 +355,7 @@ def _randomized_logistic(X, y, weights, mask, C=1., verbose=False,
     else:
         X *= (1 - weights)
 
-    C = np.atleast_1d(np.asarray(C, dtype=np.float))
+    C = np.atleast_1d(np.asarray(C, dtype=np.float64))
     scores = np.zeros((X.shape[1], len(C)), dtype=np.bool)
 
     for this_C, this_scores in zip(C, scores.T):
diff --git a/sklearn/manifold/locally_linear.py b/sklearn/manifold/locally_linear.py
@@ -315,10 +315,10 @@ def locally_linear_embedding(
                                     return_distance=False)
         neighbors = neighbors[:, 1:]
 
-        Yi = np.empty((n_neighbors, 1 + n_components + dp), dtype=np.float)
+        Yi = np.empty((n_neighbors, 1 + n_components + dp), dtype=np.float64)
         Yi[:, 0] = 1
 
-        M = np.zeros((N, N), dtype=np.float)
+        M = np.zeros((N, N), dtype=np.float64)
 
         use_svd = (n_neighbors > d_in)
 
@@ -419,7 +419,7 @@ def locally_linear_embedding(
 
         #Now calculate M.
         # This is the [N x N] matrix whose null space is the desired embedding
-        M = np.zeros((N, N), dtype=np.float)
+        M = np.zeros((N, N), dtype=np.float64)
         for i in range(N):
             s_i = s_range[i]
 
diff --git a/sklearn/neighbors/regression.py b/sklearn/neighbors/regression.py
@@ -152,7 +152,7 @@ def predict(self, X):
         if weights is None:
             y_pred = np.mean(_y[neigh_ind], axis=1)
         else:
-            y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float)
+            y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float64)
             denom = np.sum(weights, axis=1)
 
             for j in range(_y.shape[1]):
diff --git a/sklearn/neural_network/rbm.py b/sklearn/neural_network/rbm.py
diff --git a/sklearn/preprocessing/data.py b/sklearn/preprocessing/data.py
diff --git a/sklearn/svm/base.py b/sklearn/svm/base.py
diff --git a/sklearn/tests/test_naive_bayes.py b/sklearn/tests/test_naive_bayes.py
diff --git a/sklearn/utils/fixes.py b/sklearn/utils/fixes.py
diff --git a/sklearn/utils/tests/test_fast_dict.py b/sklearn/utils/tests/test_fast_dict.py
diff --git a/sklearn/utils/tests/test_murmurhash.py b/sklearn/utils/tests/test_murmurhash.py
