From ebf2bf81075ae1f4eb47ea0f54981c512bda5ceb Mon Sep 17 00:00:00 2001
From: Taehoon Lee <me@taehoonlee.com>
Date: Fri, 23 Jun 2017 18:43:46 +0900
Subject: [PATCH] Fix typos (#9205)
---
sklearn/datasets/tests/test_svmlight_format.py | 2 +-
sklearn/feature_selection/base.py | 2 +-
sklearn/metrics/cluster/unsupervised.py | 4 ++--
sklearn/neighbors/dist_metrics.pyx | 4 ++--
sklearn/neighbors/lof.py | 2 +-
sklearn/preprocessing/tests/test_label.py | 4 ++--
sklearn/tests/test_pipeline.py | 2 +-
sklearn/tree/_tree.pyx | 2 +-
8 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/sklearn/datasets/tests/test_svmlight_format.py b/sklearn/datasets/tests/test_svmlight_format.py
index c98206065f..d688dc7982 100644
--- a/sklearn/datasets/tests/test_svmlight_format.py
+++ b/sklearn/datasets/tests/test_svmlight_format.py
@@ -442,7 +442,7 @@ def test_load_with_offsets():
mark_2 = 4 * size // 5
length_1 = mark_2 - mark_1
- # load the original sparse matrix into 3 independant CSR matrices
+ # load the original sparse matrix into 3 independent CSR matrices
X_0, y_0 = load_svmlight_file(f, n_features=n_features,
offset=mark_0, length=length_0)
X_1, y_1 = load_svmlight_file(f, n_features=n_features,
diff --git a/sklearn/feature_selection/base.py b/sklearn/feature_selection/base.py
index e8a0733a28..3067d6ef31 100644
--- a/sklearn/feature_selection/base.py
+++ b/sklearn/feature_selection/base.py
@@ -17,7 +17,7 @@ from ..externals import six
class SelectorMixin(six.with_metaclass(ABCMeta, TransformerMixin)):
"""
- Tranformer mixin that performs feature selection given a support mask
+ Transformer mixin that performs feature selection given a support mask
This mixin provides a feature selector implementation with `transform` and
`inverse_transform` functionality given an implementation of
diff --git a/sklearn/metrics/cluster/unsupervised.py b/sklearn/metrics/cluster/unsupervised.py
index adb141c312..f4da109f16 100644
--- a/sklearn/metrics/cluster/unsupervised.py
+++ b/sklearn/metrics/cluster/unsupervised.py
@@ -28,7 +28,7 @@ def silhouette_score(X, labels, metric='euclidean', sample_size=None,
sample. The Silhouette Coefficient for a sample is ``(b - a) / max(a,
b)``. To clarify, ``b`` is the distance between a sample and the nearest
cluster that the sample is not a part of.
- Note that Silhouette Coefficent is only defined if number of labels
+ Note that Silhouette Coefficient is only defined if number of labels
is 2 <= n_labels <= n_samples - 1.
This function returns the mean Silhouette Coefficient over all samples.
@@ -114,7 +114,7 @@ def silhouette_samples(X, labels, metric='euclidean', **kwds):
distance (``a``) and the mean nearest-cluster distance (``b``) for each
sample. The Silhouette Coefficient for a sample is ``(b - a) / max(a,
b)``.
- Note that Silhouette Coefficent is only defined if number of labels
+ Note that Silhouette Coefficient is only defined if number of labels
is 2 <= n_labels <= n_samples - 1.
This function returns the Silhouette Coefficient for each sample.
diff --git a/sklearn/neighbors/dist_metrics.pyx b/sklearn/neighbors/dist_metrics.pyx
index 6af0441083..4a76a9eb63 100644
--- a/sklearn/neighbors/dist_metrics.pyx
+++ b/sklearn/neighbors/dist_metrics.pyx
@@ -343,7 +343,7 @@ cdef class DistanceMetric:
"""Convert the Reduced distance to the true distance.
The reduced distance, defined for some metrics, is a computationally
- more efficent measure which preserves the rank of the true distance.
+ more efficient measure which preserves the rank of the true distance.
For example, in the Euclidean distance metric, the reduced distance
is the squared-euclidean distance.
"""
@@ -353,7 +353,7 @@ cdef class DistanceMetric:
"""Convert the true distance to the reduced distance.
The reduced distance, defined for some metrics, is a computationally
- more efficent measure which preserves the rank of the true distance.
+ more efficient measure which preserves the rank of the true distance.
For example, in the Euclidean distance metric, the reduced distance
is the squared-euclidean distance.
"""
diff --git a/sklearn/neighbors/lof.py b/sklearn/neighbors/lof.py
index c8595645e9..605032106a 100644
--- a/sklearn/neighbors/lof.py
+++ b/sklearn/neighbors/lof.py
@@ -294,5 +294,5 @@ class LocalOutlierFactor(NeighborsBase, KNeighborsMixin, UnsupervisedMixin):
self.n_neighbors_ - 1]
reach_dist_array = np.maximum(distances_X, dist_k)
- # 1e-10 to avoid `nan' when when nb of duplicates > n_neighbors_:
+ # 1e-10 to avoid `nan' when nb of duplicates > n_neighbors_:
return 1. / (np.mean(reach_dist_array, axis=1) + 1e-10)
diff --git a/sklearn/preprocessing/tests/test_label.py b/sklearn/preprocessing/tests/test_label.py
index f48ad29bd2..8cd4a5b340 100644
--- a/sklearn/preprocessing/tests/test_label.py
+++ b/sklearn/preprocessing/tests/test_label.py
@@ -221,7 +221,7 @@ def test_sparse_output_multilabel_binarizer():
inverse = inputs[0]()
for sparse_output in [True, False]:
for inp in inputs:
- # With fit_tranform
+ # With fit_transform
mlb = MultiLabelBinarizer(sparse_output=sparse_output)
got = mlb.fit_transform(inp())
assert_equal(issparse(got), sparse_output)
@@ -263,7 +263,7 @@ def test_multilabel_binarizer():
[1, 1, 0]])
inverse = inputs[0]()
for inp in inputs:
- # With fit_tranform
+ # With fit_transform
mlb = MultiLabelBinarizer()
got = mlb.fit_transform(inp())
assert_array_equal(indicator_mat, got)
diff --git a/sklearn/tests/test_pipeline.py b/sklearn/tests/test_pipeline.py
index 841662be14..2549d84dfc 100644
--- a/sklearn/tests/test_pipeline.py
+++ b/sklearn/tests/test_pipeline.py
@@ -874,7 +874,7 @@ def test_pipeline_memory():
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
- # Get the time stamp of the tranformer in the cached pipeline
+ # Get the time stamp of the transformer in the cached pipeline
ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
diff --git a/sklearn/tree/_tree.pyx b/sklearn/tree/_tree.pyx
index 33aece77c9..911e63bbf6 100644
--- a/sklearn/tree/_tree.pyx
+++ b/sklearn/tree/_tree.pyx
@@ -637,7 +637,7 @@ cdef class Tree:
def __getstate__(self):
"""Getstate re-implementation, for pickling."""
d = {}
- # capacity is infered during the __setstate__ using nodes
+ # capacity is inferred during the __setstate__ using nodes
d["max_depth"] = self.max_depth
d["node_count"] = self.node_count
d["nodes"] = self._get_node_ndarray()
--
GitLab