8000 various minor spelling tweaks (#9783) · jwjohnson314/scikit-learn@6f996fa · GitHub
[go: up one dir, main page]
Skip to content

Commit 6f996fa

Browse files
brettkoonceJeremiah Johnson
brettkoonce
authored and
Jeremiah Johnson
committed
various minor spelling tweaks (scikit-learn#9783)
1 parent 8128e7a commit 6f996fa

File tree

15 files changed

+19
-19
lines changed

15 files changed

+19
-19
lines changed

‎doc/datasets/kddcup99.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -12,11 +12,11 @@ generated using a closed network and hand-injected attacks to produce a
1212
large number of different types of attack with normal activity in the
1313
background. As the initial goal was to produce a large training set for
1414
supervised learning algorithms, there is a large proportion (80.1%) of
15-
abnormal data which is unrealistic in real world, and inapropriate for
15+
abnormal data which is unrealistic in real world, and inappropriate for
1616
unsupervised anomaly detection which aims at detecting 'abnormal' data, ie
1717
1) qualitatively different from normal data
1818
2) in large minority among the observations.
19-
We thus transform the KDD Data set into two differents data set: SA and SF.
19+
We thus transform the KDD Data set into two different data sets: SA and SF.
2020

2121
-SA is obtained by simply selecting all the normal data, and a small
2222
proportion of abnormal data to gives an anomaly proportion of 1%.

‎doc/datasets/labeled_faces.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -29,11 +29,11 @@ Usage
2929

3030
``scikit-learn`` provides two loaders that will automatically download,
3131
cache, parse the metadata files, decode the jpeg and convert the
32-
interesting slices into memmaped numpy arrays. This dataset size is more
32+
interesting slices into memmapped numpy arrays. This dataset size is more
3333
than 200 MB. The first load typically takes more than a couple of minutes
3434
to fully decode the relevant part of the JPEG files into numpy arrays. If
3535
the dataset has been loaded once, the following times the loading times
36-
less than 200ms by using a memmaped version memoized on the disk in the
36+
less than 200ms by using a memmapped version memoized on the disk in the
3737
``~/scikit_learn_data/lfw_home/`` folder using ``joblib``.
3838

3939
The first loader is used for the Face Identification task: a multi-class

‎doc/modules/calibration.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ with different biases per method:
5656
than 0 for this case, thus moving the average prediction of the bagged
5757
ensemble away from 0. We observe this effect most strongly with random
5858
forests because the base-level trees trained with random forests have
59-
relatively high variance due to feature subseting." As a result, the
59+
relatively high variance due to feature subsetting." As a result, the
6060
calibration curve also referred to as the reliability diagram (Wilks 1995 [5]_) shows a
6161
characteristic sigmoid shape, indicating that the classifier could trust its
6262
"intuition" more and return probabilties closer to 0 or 1 typically.
@@ -78,7 +78,7 @@ The class :class:`CalibratedClassifierCV` uses a cross-validation generator and
7878
estimates for each split the model parameter on the train samples and the
7979
calibration of the test samples. The probabilities predicted for the
8080
folds are then averaged. Already fitted classifiers can be calibrated by
81-
:class:`CalibratedClassifierCV` via the paramter cv="prefit". In this case,
81+
:class:`CalibratedClassifierCV` via the parameter cv="prefit". In this case,
8282
the user has to take care manually that data for model fitting and calibration
8383
are disjoint.
8484

‎doc/modules/gaussian_process.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -280,7 +280,7 @@ of the dataset, this might be considerably faster. However, note that
280280
"one_vs_one" does not support predicting probability estimates but only plain
281281
predictions. Moreover, note that :class:`GaussianProcessClassifier` does not
282282
(yet) implement a true multi-class Laplace approximation internally, but
283-
as discussed aboved is based on solving several binary classification tasks
283+
as discussed above is based on solving several binary classification tasks
284284
internally, which are combined using one-versus-rest or one-versus-one.
285285

286286
GPC examples

‎doc/modules/manifold.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -558,7 +558,7 @@ descent will get stuck in a bad local minimum. If it is too high the KL
558558
divergence will increase during optimization. More tips can be found in
559559
Laurens van der Maaten's FAQ (see references). The last parameter, angle,
560560
is a tradeoff between performance and accuracy. Larger angles imply that we
561-
can approximate larger regions by a single point,leading to better speed
561+
can approximate larger regions by a single point, leading to better speed
562562
but less accurate results.
563563

564564
`"How to Use t-SNE Effectively" <http://distill.pub/2016/misread-tsne/>`_

‎doc/modules/multiclass.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -367,7 +367,7 @@ classifier per target. This allows multiple target variable
367367
classifications. The purpose of this class is to extend estimators
368368
to be able to estimate a series of target functions (f1,f2,f3...,fn)
369369
that are trained on a single X predictor matrix to predict a series
370-
of reponses (y1,y2,y3...,yn).
370+
of responses (y1,y2,y3...,yn).
371371

372372
Below is an example of multioutput classification:
373373

‎doc/modules/neighbors.rst

Lines changed: 1 addition & 1 deletion
< 93CD td data-grid-cell-id="diff-5a360fc3bc0145debf419e857214ebec61adaba13bd176f135907535714c64a8-297-296-2" data-line-anchor="diff-5a360fc3bc0145debf419e857214ebec61adaba13bd176f135907535714c64a8L297" data-selected="false" role="gridcell" style="background-color:var(--diffBlob-deletionLine-bgColor, var(--diffBlob-deletion-bgColor-line));padding-right:24px" tabindex="-1" valign="top" class="focusable-grid-cell diff-text-cell left-side-diff-cell border-right left-side">-
axes, dividing it into nested orthotopic regions into which data points
Original file line numberDiff line numberDiff line change
@@ -294,7 +294,7 @@ the *KD tree* data structure (short for *K-dimensional tree*), which
294294
generalizes two-dimensional *Quad-trees* and 3-dimensional *Oct-trees*
295295
to an arbitrary number of dimensions. The KD tree is a binary tree
296296
structure which recursively partitions the parameter space along the data
297
297+
axes, dividing it into nested orthotropic regions into which data points
298298
are filed. The construction of a KD tree is very fast: because partitioning
299299
is performed only along the data axes, no :math:`D`-dimensional distances
300300
need to be computed. Once constructed, the nearest neighbor of a query

‎doc/modules/neural_networks_unsupervised.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -135,7 +135,7 @@ negative gradient, however, is intractable. Its goal is to lower the energy of
135135
joint states that the model prefers, therefore making it stay true to the data.
136136
It can be approximated by Markov chain Monte Carlo using block Gibbs sampling by
137137
iteratively sampling each of :math:`v` and :math:`h` given the other, until the
138-
chain mixes. Samples generated in this way are sometimes refered as fantasy
138+
chain mixes. Samples generated in this way are sometimes referred as fantasy
139139
particles. This is inefficient and it is difficult to determine whether the
140140
Markov chain mixes.
141141

‎doc/modules/pipeline.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -164,7 +164,7 @@ object::
164164
>>> # Clear the cache directory when you don't need it anymore
165165
>>> rmtree(cachedir)
166166

167-
.. warning:: **Side effect of caching transfomers**
167+
.. warning:: **Side effect of caching transformers**
168168

169169
Using a :class:`Pipeline` without cache enabled, it is possible to
170170
inspect the original instance such as::

‎doc/modules/preprocessing.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -482,7 +482,7 @@ Then we fit the estimator, and transform a data point.
482482
In the result, the first two numbers encode the gender, the next set of three
483483
numbers the continent and the last four the web browser.
484484

485-
Note that, if there is a possibilty that the training data might have missing categorical
485+
Note that, if there is a possibility that the training data might have missing categorical
486486
features, one has to explicitly set ``n_values``. For example,
487487

488488
>>> enc = preprocessing.OneHotEncoder(n_values=[2, 3, 4])
@@ -588,7 +588,7 @@ In some cases, only interaction terms among features are required, and it can be
588588

589589
The features of X have been transformed from :math:`(X_1, X_2, X_3)` to :math:`(1, X_1, X_2, X_3, X_1X_2, X_1X_3, X_2X_3, X_1X_2X_3)`.
590590

591-
Note that polynomial features are used implicitily in `kernel methods <https://en.wikipedia.org/wiki/Kernel_method>`_ (e.g., :class:`sklearn.svm.SVC`, :class:`sklearn.decomposition.KernelPCA`) when using polynomial :ref:`svm_kernels`.
591+
Note that polynomial features are used implicitly in `kernel methods <https://en.wikipedia.org/wiki/Kernel_method>`_ (e.g., :class:`sklearn.svm.SVC`, :class:`sklearn.decomposition.KernelPCA`) when using polynomial :ref:`svm_kernels`.
592592

593593
See :ref:`sphx_glr_auto_examples_linear_model_plot_polynomial_interpolation.py` for Ridge regression using created polynomial features.
594594

0 commit comments

Comments
 (0)
0