From 2653833a0790053887f8522de134f83a0fe1427f Mon Sep 17 00:00:00 2001
From: Andreas Mueller <amueller@nyu.edu>
Date: Tue, 3 Nov 2015 12:23:23 -0500
Subject: [PATCH] DOC some fixes to the doc build.
---
doc/datasets/index.rst | 12 +--
doc/datasets/rcv1.rst | 4 +-
doc/modules/decomposition.rst | 1 +
doc/modules/feature_selection.rst | 2 +
doc/modules/gaussian_process.rst | 59 ++++++------
doc/modules/multiclass.rst | 8 +-
doc/modules/neural_networks_supervised.rst | 6 +-
doc/modules/outlier_detection.rst | 1 +
doc/whats_new.rst | 18 ++--
examples/applications/face_recognition.py | 4 +-
examples/gaussian_process/plot_gpr_co2.py | 48 +++++-----
sklearn/cross_decomposition/pls_.py | 23 +++--
sklearn/datasets/descr/breast_cancer.rst | 89 ++++++++++---------
sklearn/datasets/descr/diabetes.rst | 2 +-
sklearn/datasets/descr/digits.rst | 2 +-
sklearn/datasets/descr/iris.rst | 2 +
sklearn/datasets/kddcup99.py | 4 +
sklearn/gaussian_process/gpc.py | 18 ++--
sklearn/gaussian_process/gpr.py | 10 +--
sklearn/gaussian_process/kernels.py | 10 +--
sklearn/linear_model/base.py | 2 +-
sklearn/model_selection/_validation.py | 14 +--
.../neural_network/multilayer_perceptron.py | 4 +-
sklearn/preprocessing/data.py | 14 +--
sklearn/preprocessing/tests/test_data.py | 8 +-
25 files changed, 198 insertions(+), 167 deletions(-)
diff --git a/doc/datasets/index.rst b/doc/datasets/index.rst
index e18cfdd152..e7925f3e94 100644
--- a/doc/datasets/index.rst
+++ b/doc/datasets/index.rst
@@ -267,26 +267,26 @@ features::
.. include:: rcv1.rst
-.. _boston_house_prices
+.. _boston_house_prices:
.. include:: ../../sklearn/datasets/descr/boston_house_prices.rst
-.. _breast_cancer
+.. _breast_cancer:
.. include:: ../../sklearn/datasets/descr/breast_cancer.rst
-.. _diabetes
+.. _diabetes:
.. include:: ../../sklearn/datasets/descr/diabetes.rst
-.. _digits
+.. _digits:
.. include:: ../../sklearn/datasets/descr/digits.rst
-.. _iris
+.. _iris:
.. include:: ../../sklearn/datasets/descr/iris.rst
-.. _linnerud
+.. _linnerud:
.. include:: ../../sklearn/datasets/descr/linnerud.rst
diff --git a/doc/datasets/rcv1.rst b/doc/datasets/rcv1.rst
index 486eeee905..ded38584ce 100644
--- a/doc/datasets/rcv1.rst
+++ b/doc/datasets/rcv1.rst
@@ -41,10 +41,10 @@ There are 103 topics, each represented by a string. Their corpus frequencies spa
>>> rcv1.target_names[:3].tolist() # doctest: +SKIP
['E11', 'ECAT', 'M11']
-The dataset will be downloaded from the `dataset's homepage`_ if necessary.
+The dataset will be downloaded from the `rcv1 homepage`_ if necessary.
The compressed size is about 656 MB.
-.. _dataset's homepage: http://jmlr.csail.mit.edu/papers/volume5/lewis04a/
+.. _rcv1 homepage: http://jmlr.csail.mit.edu/papers/volume5/lewis04a/
.. topic:: References
diff --git a/doc/modules/decomposition.rst b/doc/modules/decomposition.rst
index 91d003ce70..f10e105664 100644
--- a/doc/modules/decomposition.rst
+++ b/doc/modules/decomposition.rst
@@ -776,6 +776,7 @@ a corpus with :math:`D` documents and :math:`K` topics:
2. For each document :math:`d`, draw :math:`\theta_d \sim Dirichlet(\alpha), \: d=1...D`
3. For each word :math:`i` in document :math:`d`:
+
a. Draw a topic index :math:`z_{di} \sim Multinomial(\theta_d)`
b. Draw the observed word :math:`w_{ij} \sim Multinomial(beta_{z_{di}}.)`
diff --git a/doc/modules/feature_selection.rst b/doc/modules/feature_selection.rst
index 88ff7d56d6..60e4d0a38f 100644
--- a/doc/modules/feature_selection.rst
+++ b/doc/modules/feature_selection.rst
@@ -153,6 +153,8 @@ For examples on how it is to be used refer to the sections below.
most important features from the Boston dataset without knowing the
threshold beforehand.
+.. _l1_feature_selection:
+
L1-based feature selection
--------------------------
diff --git a/doc/modules/gaussian_process.rst b/doc/modules/gaussian_process.rst
index 52049efc16..b710564dbb 100644
--- a/doc/modules/gaussian_process.rst
+++ b/doc/modules/gaussian_process.rst
@@ -67,12 +67,15 @@ level from the data (see example below).
The implementation is based on Algorithm 2.1 of [RW2006]_. In addition to
the API of standard sklearn estimators, GaussianProcessRegressor:
- * allows prediction without prior fitting (based on the GP prior)
- * provides an additional method ``sample_y(X)``, which evaluates samples
- drawn from the GPR (prior or posterior) at given inputs
- * exposes a method ``log_marginal_likelihood(theta)``, which can be used
- externally for other ways of selecting hyperparameters, e.g., via
- Markov chain Monte Carlo.
+
+* allows prediction without prior fitting (based on the GP prior)
+
+* provides an additional method ``sample_y(X)``, which evaluates samples
+ drawn from the GPR (prior or posterior) at given inputs
+
+* exposes a method ``log_marginal_likelihood(theta)``, which can be used
+ externally for other ways of selecting hyperparameters, e.g., via
+ Markov chain Monte Carlo.
GPR examples
@@ -171,26 +174,30 @@ model the CO2 concentration as a function of the time t.
The kernel is composed of several terms that are responsible for explaining
different properties of the signal:
- - a long term, smooth rising trend is to be explained by an RBF kernel. The
- RBF kernel with a large length-scale enforces this component to be smooth;
- it is not enforced that the trend is rising which leaves this choice to the
- GP. The specific length-scale and the amplitude are free hyperparameters.
- - a seasonal component, which is to be explained by the periodic
- ExpSineSquared kernel with a fixed periodicity of 1 year. The length-scale
- of this periodic component, controlling its smoothness, is a free parameter.
- In order to allow decaying away from exact periodicity, the product with an
- RBF kernel is taken. The length-scale of this RBF component controls the
- decay time and is a further free parameter.
- - smaller, medium term irregularities are to be explained by a
- RationalQuadratic kernel component, whose length-scale and alpha parameter,
- which determines the diffuseness of the length-scales, are to be determined.
- According to [RW2006]_, these irregularities can better be explained by
- a RationalQuadratic than an RBF kernel component, probably because it can
- accommodate several length-scales.
- - a "noise" term, consisting of an RBF kernel contribution, which shall
- explain the correlated noise components such as local weather phenomena,
- and a WhiteKernel contribution for the white noise. The relative amplitudes
- and the RBF's length scale are further free parameters.
+
+- a long term, smooth rising trend is to be explained by an RBF kernel. The
+ RBF kernel with a large length-scale enforces this component to be smooth;
+ it is not enforced that the trend is rising which leaves this choice to the
+ GP. The specific length-scale and the amplitude are free hyperparameters.
+
+- a seasonal component, which is to be explained by the periodic
+ ExpSineSquared kernel with a fixed periodicity of 1 year. The length-scale
+ of this periodic component, controlling its smoothness, is a free parameter.
+ In order to allow decaying away from exact periodicity, the product with an
+ RBF kernel is taken. The length-scale of this RBF component controls the
+ decay time and is a further free parameter.
+
+- smaller, medium term irregularities are to be explained by a
+ RationalQuadratic kernel component, whose length-scale and alpha parameter,
+ which determines the diffuseness of the length-scales, are to be determined.
+ According to [RW2006]_, these irregularities can better be explained by
+ a RationalQuadratic than an RBF kernel component, probably because it can
+ accommodate several length-scales.
+
+- a "noise" term, consisting of an RBF kernel contribution, which shall
+ explain the correlated noise components such as local weather phenomena,
+ and a WhiteKernel contribution for the white noise. The relative amplitudes
+ and the RBF's length scale are further free parameters.
Maximizing the log-marginal-likelihood after subtracting the target's mean
yields the following kernel with an LML of -83.214:
diff --git a/doc/modules/multiclass.rst b/doc/modules/multiclass.rst
index 49ea0d588e..9db951f4c4 100644
--- a/doc/modules/multiclass.rst
+++ b/doc/modules/multiclass.rst
@@ -215,7 +215,7 @@ code book. The code size is the dimensionality of the aforementioned space.
Intuitively, each class should be represented by a code as unique as
possible and a good code book should be designed to optimize classification
accuracy. In this implementation, we simply use a randomly-generated code
-book as advocated in [2]_ although more elaborate methods may be added in the
+book as advocated in [3]_ although more elaborate methods may be added in the
future.
At fitting time, one binary classifier per bit in the code book is fitted.
@@ -262,16 +262,16 @@ Below is an example of multiclass learning using Output-Codes::
.. topic:: References:
- .. [1] "Solving multiclass learning problems via error-correcting output codes",
+ .. [2] "Solving multiclass learning problems via error-correcting output codes",
Dietterich T., Bakiri G.,
Journal of Artificial Intelligence Research 2,
1995.
- .. [2] "The error coding method and PICTs",
+ .. [3] "The error coding method and PICTs",
James G., Hastie T.,
Journal of Computational and Graphical statistics 7,
1998.
- .. [3] "The Elements of Statistical Learning",
+ .. [4] "The Elements of Statistical Learning",
Hastie T., Tibshirani R., Friedman J., page 606 (second-edition)
2008.
diff --git a/doc/modules/neural_networks_supervised.rst b/doc/modules/neural_networks_supervised.rst
index a921c2d975..cc17be204c 100644
--- a/doc/modules/neural_networks_supervised.rst
+++ b/doc/modules/neural_networks_supervised.rst
@@ -153,7 +153,7 @@ See the examples below and the doc string of
.. topic:: Examples:
- * :ref:`example_plot_mlp_alpha.py`
+ * :ref:`example_neural_networks_plot_mlp_alpha.py`
Regression
@@ -175,7 +175,7 @@ Algorithms
MLP trains using `Stochastic Gradient Descent
<http://en.wikipedia.org/wiki/Stochastic_gradient_descent>`_,
`Adam <http://arxiv.org/abs/1412.6980>`_, or
-`L-BFGS <http://en.wikipedia.org/wiki/Limited-memory_BFGS>`_.
+`L-BFGS <http://en.wikipedia.org/wiki/Limited-memory_BFGS>`__.
Stochastic Gradient Descent (SGD) updates parameters using the gradient of the
loss function with respect to a parameter that needs adaptation, i.e.
@@ -201,7 +201,7 @@ L-BFGS is a fast learning algorithm that approximates the Hessian matrix which
represents the second-order partial derivative of a function. Further it
approximates the inverse of the Hessian matrix to perform parameter updates.
The implementation uses the Scipy version of
-`L-BFGS <http://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.fmin_l_bfgs_b.html>`_..
+`L-BFGS <http://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.fmin_l_bfgs_b.html>`__..
If the selected algorithm is 'L-BFGS', training does not support online nor
mini-batch learning.
diff --git a/doc/modules/outlier_detection.rst b/doc/modules/outlier_detection.rst
index ff24e01225..93de5ad490 100644
--- a/doc/modules/outlier_detection.rst
+++ b/doc/modules/outlier_detection.rst
@@ -169,6 +169,7 @@ This strategy is illustrated below.
:class:`covariance.MinCovDet`.
.. topic:: References:
+
.. [LTZ2008] Liu, Fei Tony, Ting, Kai Ming and Zhou, Zhi-Hua. "Isolation forest."
Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on.
diff --git a/doc/whats_new.rst b/doc/whats_new.rst
index 8587580795..6acd6b8021 100644
--- a/doc/whats_new.rst
+++ b/doc/whats_new.rst
@@ -33,7 +33,7 @@ Enhancements
that takes in the data and yields a generator for the different splits.
This change makes it possible to do nested cross-validation with ease,
facilitated by :class:`model_selection.GridSearchCV` and similar
- utilities. (`#4294 https://github.com/scikit-learn/scikit-learn/pull/4294>`_) by `Raghav R V`_.
+ utilities. (`#4294 <https://github.com/scikit-learn/scikit-learn/pull/4294>`_) by `Raghav R V`_.
- The random forest, extra trees and decision tree estimators now has a
method ``decision_path`` which returns the decision path of samples in
@@ -56,16 +56,16 @@ Bug fixes
.........
- :class:`RandomizedPCA` default number of `iterated_power` is 2 instead of 3.
- This is a speed up with a minor precision decrease. (`#5141 https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
+ This is a speed up with a minor precision decrease. (`#5141 <https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
- :func:`randomized_svd` performs 2 power iterations by default, instead or 0.
In practice this is often enough for obtaining a good approximation of the
- true eigenvalues/vectors in the presence of noise. (`#5141 https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
+ true eigenvalues/vectors in the presence of noise. (`#5141 <https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
- :func:`randomized_range_finder` is more numerically stable when many
power iterations are requested, since it applies LU normalization by default.
If `n_iter<2` numerical issues are unlikely, thus no normalization is applied.
- Other normalization options are available: 'none', 'LU' and 'QR'. (`#5141 https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
+ Other normalization options are available: 'none', 'LU' and 'QR'. (`#5141 <https://github.com/scikit-learn/scikit-learn/pull/5141>`_) by `Giorgio Patrini`_.
- Fixed bug in :func:`manifold.spectral_embedding` where diagonal of unnormalized
Laplacian matrix was incorrectly set to 1. By `Peter Fischer`_.
@@ -85,7 +85,7 @@ API changes summary
- The :mod:`cross_validation`, :mod:`grid_search` and :mod:`learning_curve`
have been deprecated and the classes and functions have been reorganized into
the :mod:`model_selection` module.
- (`#4294 https://github.com/scikit-learn/scikit-learn/pull/4294>`_) by `Raghav R V`_.
+ (`#4294 <https://github.com/scikit-learn/scikit-learn/pull/4294>`_) by `Raghav R V`_.
.. _changes_0_17:
@@ -366,7 +366,7 @@ Bug fixes
- Fixed bug in :class:`cross_decomposition.PLS` that yielded unstable and
platform dependent output, and failed on `fit_transform`.
- By `Arthur Mensch`_.
+ By `Arthur Mensch`_.
- Fixed a bug in :class:`linear_model.LogisticRegression` and
:class:`linear_model.LogisticRegressionCV` when using
@@ -3403,8 +3403,8 @@ Changelog
- New :ref:`gaussian_process` module by Vincent Dubourg. This module
also has great documentation and some very neat examples. See
- :ref:`example_gaussian_process_plot_gp_regression.py` or
- :ref:`example_gaussian_process_plot_gp_probabilistic_classification_after_regression.py`
+ example_gaussian_process_plot_gp_regression.py or
+ example_gaussian_process_plot_gp_probabilistic_classification_after_regression.py
for a taste of what can be done.
- It is now possible to use liblinear’s Multi-class SVC (option
@@ -3866,4 +3866,4 @@ David Huard, Dave Morrill, Ed Schofield, Travis Oliphant, Pearu Peterson.
.. _Graham Clenaghan: https://github.com/gclenaghan
.. _Giorgio Patrini: https://github.com/giorgiop
.. _Elvis Dohmatob: https://github.com/dohmatob
-.. _yelite https://github.com/yelite
+.. _yelite: https://github.com/yelite
diff --git a/examples/applications/face_recognition.py b/examples/applications/face_recognition.py
index b79599ecb3..b23dda4749 100644
--- a/examples/applications/face_recognition.py
+++ b/examples/applications/face_recognition.py
@@ -12,8 +12,9 @@ The dataset used in this example is a preprocessed excerpt of the
Expected results for the top 5 most represented people in the dataset::
+================== ============ ======= ========== =======
precision recall f1-score support
-
+================== ============ ======= ========== =======
Ariel Sharon 0.67 0.92 0.77 13
Colin Powell 0.75 0.78 0.76 60
Donald Rumsfeld 0.78 0.67 0.72 27
@@ -23,6 +24,7 @@ Gerhard Schroeder 0.76 0.76 0.76 25
Tony Blair 0.81 0.69 0.75 36
avg / total 0.80 0.80 0.80 322
+================== ============ ======= ========== =======
"""
from __future__ import print_function
diff --git a/examples/gaussian_process/plot_gpr_co2.py b/examples/gaussian_process/plot_gpr_co2.py
index 07f1d8214d..b0b271a364 100644
--- a/examples/gaussian_process/plot_gpr_co2.py
+++ b/examples/gaussian_process/plot_gpr_co2.py
@@ -13,34 +13,40 @@ model the CO2 concentration as a function of the time t.
The kernel is composed of several terms that are responsible for explaining
different properties of the signal:
- - a long term, smooth rising trend is to be explained by an RBF kernel. The
- RBF kernel with a large length-scale enforces this component to be smooth;
- it is not enforced that the trend is rising which leaves this choice to the
- GP. The specific length-scale and the amplitude are free hyperparameters.
- - a seasonal component, which is to be explained by the periodic
- ExpSineSquared kernel with a fixed periodicity of 1 year. The length-scale
- of this periodic component, controlling its smoothness, is a free parameter.
- In order to allow decaying away from exact periodicity, the product with an
- RBF kernel is taken. The length-scale of this RBF component controls the
- decay time and is a further free parameter.
- - smaller, medium term irregularities are to be explained by a
- RationalQuadratic kernel component, whose length-scale and alpha parameter,
- which determines the diffuseness of the length-scales, are to be determined.
- According to [RW2006], these irregularities can better be explained by
- a RationalQuadratic than an RBF kernel component, probably because it can
- accommodate several length-scales.
- - a "noise" term, consisting of an RBF kernel contribution, which shall
- explain the correlated noise components such as local weather phenomena,
- and a WhiteKernel contribution for the white noise. The relative amplitudes
- and the RBF's length scale are further free parameters.
+
+- a long term, smooth rising trend is to be explained by an RBF kernel. The
+ RBF kernel with a large length-scale enforces this component to be smooth;
+ it is not enforced that the trend is rising which leaves this choice to the
+ GP. The specific length-scale and the amplitude are free hyperparameters.
+
+- a seasonal component, which is to be explained by the periodic
+ ExpSineSquared kernel with a fixed periodicity of 1 year. The length-scale
+ of this periodic component, controlling its smoothness, is a free parameter.
+ In order to allow decaying away from exact periodicity, the product with an
+ RBF kernel is taken. The length-scale of this RBF component controls the
+ decay time and is a further free parameter.
+
+- smaller, medium term irregularities are to be explained by a
+ RationalQuadratic kernel component, whose length-scale and alpha parameter,
+ which determines the diffuseness of the length-scales, are to be determined.
+ According to [RW2006], these irregularities can better be explained by
+ a RationalQuadratic than an RBF kernel component, probably because it can
+ accommodate several length-scales.
+
+- a "noise" term, consisting of an RBF kernel contribution, which shall
+ explain the correlated noise components such as local weather phenomena,
+ and a WhiteKernel contribution for the white noise. The relative amplitudes
+ and the RBF's length scale are further free parameters.
Maximizing the log-marginal-likelihood after subtracting the target's mean
-yields the following kernel with an LML of -83.214:
+yields the following kernel with an LML of -83.214::
+
34.4**2 * RBF(length_scale=41.8)
+ 3.27**2 * RBF(length_scale=180) * ExpSineSquared(length_scale=1.44,
periodicity=1)
+ 0.446**2 * RationalQuadratic(alpha=17.7, length_scale=0.957)
+ 0.197**2 * RBF(length_scale=0.138) + WhiteKernel(noise_level=0.0336)
+
Thus, most of the target signal (34.4ppm) is explained by a long-term rising
trend (length-scale 41.8 years). The periodic component has an amplitude of
3.27ppm, a decay time of 180 years and a length-scale of 1.44. The long decay
diff --git a/sklearn/cross_decomposition/pls_.py b/sklearn/cross_decomposition/pls_.py
index fa481bb4f5..4d77bc2b32 100644
--- a/sklearn/cross_decomposition/pls_.py
+++ b/sklearn/cross_decomposition/pls_.py
@@ -521,7 +521,8 @@ class PLSRegression(_PLS):
Notes
-----
- Matrices :
+ Matrices::
+
T: x_scores_
U: y_scores_
W: x_weights_
@@ -529,16 +530,17 @@ class PLSRegression(_PLS):
P: x_loadings_
Q: y_loadings__
- Are computed such that:
+ Are computed such that::
+
X = T P.T + Err and Y = U Q.T + Err
T[:, k] = Xk W[:, k] for k in range(n_components)
U[:, k] = Yk C[:, k] for k in range(n_components)
x_rotations_ = W (P.T W)^(-1)
y_rotations_ = C (Q.T C)^(-1)
+
where Xk and Yk are residual matrices at iteration k.
- Slides explaining PLS
- :ref:http://www.eigenvector.com/Docs/Wise_pls_properties.pdf
+ `Slides explaining PLS <http://www.eigenvector.com/Docs/Wise_pls_properties.pdf>`
For each component k, find weights u, v that optimizes:
``max corr(Xk u, Yk v) * std(Xk u) std(Yk u)``, such that ``|u| = 1``
@@ -656,7 +658,8 @@ class PLSCanonical(_PLS):
Notes
-----
- Matrices :
+ Matrices::
+
T: x_scores_
U: y_scores_
W: x_weights_
@@ -664,19 +667,21 @@ class PLSCanonical(_PLS):
P: x_loadings_
Q: y_loadings__
- Are computed such that:
+ Are computed such that::
+
X = T P.T + Err and Y = U Q.T + Err
T[:, k] = Xk W[:, k] for k in range(n_components)
U[:, k] = Yk C[:, k] for k in range(n_components)
x_rotations_ = W (P.T W)^(-1)
y_rotations_ = C (Q.T C)^(-1)
+
where Xk and Yk are residual matrices at iteration k.
- Slides explaining PLS
- :ref:http://www.eigenvector.com/Docs/Wise_pls_properties.pdf
+ `Slides explaining PLS <http://www.eigenvector.com/Docs/Wise_pls_properties.pdf>`
For each component k, find weights u, v that optimize::
- max corr(Xk u, Yk v) * std(Xk u) std(Yk u), such that ``|u| = |v| = 1``
+
+ max corr(Xk u, Yk v) * std(Xk u) std(Yk u), such that ``|u| = |v| = 1``
Note that it maximizes both the correlations between the scores and the
intra-block variances.
diff --git a/sklearn/datasets/descr/breast_cancer.rst b/sklearn/datasets/descr/breast_cancer.rst
index 642484f5e3..6e3dfc708f 100644
--- a/sklearn/datasets/descr/breast_cancer.rst
+++ b/sklearn/datasets/descr/breast_cancer.rst
@@ -19,51 +19,52 @@ Data Set Characteristics:
- concave points (number of concave portions of the contour)
- symmetry
- fractal dimension ("coastline approximation" - 1)
-
- The mean, standard error, and "worst" or largest (mean of the three
- largest values) of these features were computed for each image,
- resulting in 30 features. For instance, field 3 is Mean Radius, field
- 13 is Radius SE, field 23 is Worst Radius.
-
+
+ The mean, standard error, and "worst" or largest (mean of the three
+ largest values) of these features were computed for each image,
+ resulting in 30 features. For instance, field 3 is Mean Radius, field
+ 13 is Radius SE, field 23 is Worst Radius.
+
- class:
- WDBC-Malignant
- WDBC-Benign
:Summary Statistics:
- ===================================== ====== ======
- Min Max
- ===================================== ====== ======
- radius (mean): 6.981 28.11
- texture (mean): 9.71 39.28
- perimeter (mean): 43.79 188.5
- area (mean): 143.5 2501.0
- smoothness (mean): 0.053 0.163
- compactness (mean): 0.019 0.345
- concavity (mean): 0.0 0.427
- concave points (mean): 0.0 0.201
- symmetry (mean): 0.106 0.304
- fractal dimension (mean): 0.05 0.097
- radius (standard error): 0.112 2.873
- texture (standard error): 0.36 4.885
- perimeter (standard error): 0.757 21.98
- area (standard error): 6.802 542.2
- smoothness (standard error): 0.002 0.031
- compactness (standard error): 0.002 0.135
- concavity (standard error): 0.0 0.396
- concave points (standard error): 0.0 0.053
- symmetry (standard error): 0.008 0.079
- fractal dimension (standard error): 0.001 0.03
- radius (worst): 7.93 36.04
- texture (worst): 12.02 49.54
- perimeter (worst): 50.41 251.2
- area (worst): 185.2 4254.0
- smoothness (worst): 0.071 0.223
- compactness (worst): 0.027 1.058
- concavity (worst): 0.0 1.252
- concave points (worst): 0.0 0.291
- symmetry (worst): 0.156 0.664
- fractal dimension (worst): 0.055 0.208
- ===================================== ====== ======
+
+ ===================================== ======= ========
+ Min Max
+ ===================================== ======= ========
+ radius (mean): 6.981 28.11
+ texture (mean): 9.71 39.28
+ perimeter (mean): 43.79 188.5
+ area (mean): 143.5 2501.0
+ smoothness (mean): 0.053 0.163
+ compactness (mean): 0.019 0.345
+ concavity (mean): 0.0 0.427
+ concave points (mean): 0.0 0.201
+ symmetry (mean): 0.106 0.304
+ fractal dimension (mean): 0.05 0.097
+ radius (standard error): 0.112 2.873
+ texture (standard error): 0.36 4.885
+ perimeter (standard error): 0.757 21.98
+ area (standard error): 6.802 542.2
+ smoothness (standard error): 0.002 0.031
+ compactness (standard error): 0.002 0.135
+ concavity (standard error): 0.0 0.396
+ concave points (standard error): 0.0 0.053
+ symmetry (standard error): 0.008 0.079
+ fractal dimension (standard error): 0.001 0.03
+ radius (worst): 7.93 36.04
+ texture (worst): 12.02 49.54
+ perimeter (worst): 50.41 251.2
+ area (worst): 185.2 4254.0
+ smoothness (worst): 0.071 0.223
+ compactness (worst): 0.027 1.058
+ concavity (worst): 0.0 1.252
+ concave points (worst): 0.0 0.291
+ symmetry (worst): 0.156 0.664
+ fractal dimension (worst): 0.055 0.208
+ ===================================== ======= ========
:Missing Attribute Values: None
@@ -108,11 +109,11 @@ References
----------
- W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction
for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on
- Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
- San Jose, CA, 1993.
+ Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
+ San Jose, CA, 1993.
- O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and
prognosis via linear programming. Operations Research, 43(4), pages 570-577,
- July-August 1995.
+ July-August 1995.
- W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques
to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994)
- 163-171.
\ No newline at end of file
+ 163-171.
diff --git a/sklearn/datasets/descr/diabetes.rst b/sklearn/datasets/descr/diabetes.rst
index 192d6c055e..df102a1bec 100644
--- a/sklearn/datasets/descr/diabetes.rst
+++ b/sklearn/datasets/descr/diabetes.rst
@@ -29,7 +29,7 @@ Data Set Characteristics:
:S5:
:S6:
-*Note: Each of these 10 feature variables have been mean centered and scaled by the standard deviation times `n_samples` (i.e. the sum of squares of each column totals 1).
+Note: Each of these 10 feature variables have been mean centered and scaled by the standard deviation times `n_samples` (i.e. the sum of squares of each column totals 1).
Source URL:
http://www4.stat.ncsu.edu/~boos/var.select/diabetes.html
diff --git a/sklearn/datasets/descr/digits.rst b/sklearn/datasets/descr/digits.rst
index 32aaa4de35..a30514474f 100644
--- a/sklearn/datasets/descr/digits.rst
+++ b/sklearn/datasets/descr/digits.rst
@@ -1,4 +1,4 @@
- Optical Recognition of Handwritten Digits Data Set
+Optical Recognition of Handwritten Digits Data Set
===================================================
Notes
diff --git a/sklearn/datasets/descr/iris.rst b/sklearn/datasets/descr/iris.rst
index aa44f6e5ef..6e7aba2ec5 100644
--- a/sklearn/datasets/descr/iris.rst
+++ b/sklearn/datasets/descr/iris.rst
@@ -16,6 +16,7 @@ Data Set Characteristics:
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
+
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
@@ -24,6 +25,7 @@ Data Set Characteristics:
petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
============== ==== ==== ======= ===== ====================
+
:Missing Attribute Values: None
:Class Distribution: 33.3% for each of 3 classes.
:Creator: R.A. Fisher
diff --git a/sklearn/datasets/kddcup99.py b/sklearn/datasets/kddcup99.py
index 9e7696f68c..589749851e 100644
--- a/sklearn/datasets/kddcup99.py
+++ b/sklearn/datasets/kddcup99.py
@@ -81,6 +81,7 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None,
================ ==========================================
SA structure :
+
================ ==========================================
Samples total 976158
Dimensionality 41
@@ -89,6 +90,7 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None,
================ ==========================================
SF structure :
+
================ ==========================================
Samples total 699691
Dimensionality 40
@@ -97,6 +99,7 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None,
================ ==========================================
http structure :
+
================ ==========================================
Samples total 619052
Dimensionality 39
@@ -105,6 +108,7 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None,
================ ==========================================
smtp structure :
+
================ ==========================================
Samples total 95373
Dimensionality 39
diff --git a/sklearn/gaussian_process/gpc.py b/sklearn/gaussian_process/gpc.py
index f9c00a98be..745fab94a1 100644
--- a/sklearn/gaussian_process/gpc.py
+++ b/sklearn/gaussian_process/gpc.py
@@ -137,7 +137,7 @@ class _BinaryGaussianProcessClassifierLaplace(BaseEstimator):
of sqrt(W) is stored.
log_marginal_likelihood_value_: float
- The log-marginal-likelihood of self.kernel_.theta
+ The log-marginal-likelihood of ``self.kernel_.theta``
"""
def __init__(self, kernel=None, optimizer="fmin_l_bfgs_b",
n_restarts_optimizer=0, max_iter_predict=100,
@@ -246,7 +246,7 @@ class _BinaryGaussianProcessClassifierLaplace(BaseEstimator):
Returns
-------
C : array, shape = (n_samples,)
- Predicted target values for X, values are from classes_
+ Predicted target values for X, values are from ``classes_``
"""
check_is_fitted(self, ["X_train_", "y_train_", "pi_", "W_sr_", "L_"])
@@ -270,7 +270,7 @@ class _BinaryGaussianProcessClassifierLaplace(BaseEstimator):
C : array-like, shape = (n_samples, n_classes)
Returns the probability of the samples for each class in
the model. The columns correspond to the classes in sorted
- order, as they appear in the attribute `classes_`.
+ order, as they appear in the attribute ``classes_``.
"""
check_is_fitted(self, ["X_train_", "y_train_", "pi_", "W_sr_", "L_"])
@@ -305,7 +305,7 @@ class _BinaryGaussianProcessClassifierLaplace(BaseEstimator):
theta : array-like, shape = (n_kernel_params,) or None
Kernel hyperparameters for which the log-marginal likelihood is
evaluated. If None, the precomputed log_marginal_likelihood
- of self.kernel_.theta is returned.
+ of ``self.kernel_.theta`` is returned.
eval_gradient : bool, default: False
If True, the gradient of the log-marginal likelihood with respect
@@ -437,7 +437,7 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
"""Gaussian process classification (GPC) based on Laplace approximation.
The implementation is based on Algorithm 3.1, 3.2, and 5.1 of
- ``Gaussian Processes for Machine Learning'' (GPML) by Rasmussen and
+ Gaussian Processes for Machine Learning (GPML) by Rasmussen and
Williams.
Internally, the Laplace approximation is used for approximating the
@@ -539,7 +539,7 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
different kernels used in the one-versus-rest classifiers.
log_marginal_likelihood_value_: float
- The log-marginal-likelihood of self.kernel_.theta
+ The log-marginal-likelihood of ``self.kernel_.theta``
classes_ : array-like, shape = (n_classes,)
Unique class labels.
@@ -624,7 +624,7 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
Returns
-------
C : array, shape = (n_samples,)
- Predicted target values for X, values are from classes_
+ Predicted target values for X, values are from ``classes_``
"""
check_is_fitted(self, ["classes_", "n_classes_"])
X = check_array(X)
@@ -675,7 +675,7 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
be the hyperparameters of the compound kernel or of an individual
kernel. In the latter case, all individual kernel get assigned the
same theta values. If None, the precomputed log_marginal_likelihood
- of self.kernel_.theta is returned.
+ of ``self.kernel_.theta`` is returned.
eval_gradient : bool, default: False
If True, the gradient of the log-marginal likelihood with respect
@@ -720,7 +720,7 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
# theta for compound kernel
return np.mean(
[estimator.log_marginal_likelihood(
- theta[n_dims*i:n_dims*(i+1)])
+ theta[n_dims * i:n_dims * (i + 1)])
for i, estimator in enumerate(estimators)])
else:
raise ValueError("Shape of theta must be either %d or %d. "
diff --git a/sklearn/gaussian_process/gpr.py b/sklearn/gaussian_process/gpr.py
index 85ff65b8a8..3a46153680 100644
--- a/sklearn/gaussian_process/gpr.py
+++ b/sklearn/gaussian_process/gpr.py
@@ -20,8 +20,8 @@ from sklearn.utils.validation import check_X_y, check_array
class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
"""Gaussian process regression (GPR).
- The implementation is based on Algorithm 2.1 of ``Gaussian Processes
- for Machine Learning'' (GPML) by Rasmussen and Williams.
+ The implementation is based on Algorithm 2.1 of Gaussian Processes
+ for Machine Learning (GPML) by Rasmussen and Williams.
In addition to standard sklearn estimator API, GaussianProcessRegressor:
@@ -115,13 +115,13 @@ class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
same as the one passed as parameter but with optimized hyperparameters
L_: array-like, shape = (n_samples, n_samples)
- Lower-triangular Cholesky decomposition of the kernel in X_train_
+ Lower-triangular Cholesky decomposition of the kernel in ``X_train_``
alpha_: array-like, shape = (n_samples,)
Dual coefficients of training data points in kernel space
log_marginal_likelihood_value_: float
- The log-marginal-likelihood of self.kernel_.theta
+ The log-marginal-likelihood of ``self.kernel_.theta``
"""
def __init__(self, kernel=None, alpha=1e-10,
optimizer="fmin_l_bfgs_b", n_restarts_optimizer=0,
@@ -347,7 +347,7 @@ class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
theta : array-like, shape = (n_kernel_params,) or None
Kernel hyperparameters for which the log-marginal likelihood is
evaluated. If None, the precomputed log_marginal_likelihood
- of self.kernel_.theta is returned.
+ of ``self.kernel_.theta`` is returned.
eval_gradient : bool, default: False
If True, the gradient of the log-marginal likelihood with respect
diff --git a/sklearn/gaussian_process/kernels.py b/sklearn/gaussian_process/kernels.py
index a34286e358..6c36d19712 100644
--- a/sklearn/gaussian_process/kernels.py
+++ b/sklearn/gaussian_process/kernels.py
@@ -21,7 +21,6 @@ optimization.
from abc import ABCMeta, abstractmethod
from collections import namedtuple
-import inspect
import math
import numpy as np
@@ -33,13 +32,14 @@ from ..externals import six
from ..base import clone
from sklearn.externals.funcsigs import signature
+
class Hyperparameter(namedtuple('Hyperparameter',
('name', 'value_type', 'bounds',
'n_elements', 'fixed'))):
"""A kernel hyperparameter's specification in form of a namedtuple.
- Entries
- -------
+ Attributes
+ ----------
name : string
The name of the hyperparameter. Note that a kernel using a
hyperparameter with name "x" must have the attributes self.x and
@@ -405,7 +405,7 @@ class CompoundKernel(Kernel):
"""
k_dims = self.k1.n_dims
for i, kernel in enumerate(self.kernels):
- kernel.theta = theta[i*k_dims:(i+1)*k_dims]
+ kernel.theta = theta[i * k_dims:(i + 1) * k_dims]
@property
def bounds(self):
@@ -1316,7 +1316,7 @@ class Matern(RBF):
3 * D * np.exp(-np.sqrt(3 * D.sum(-1)))[..., np.newaxis]
elif self.nu == 2.5:
tmp = np.sqrt(5 * D.sum(-1))[..., np.newaxis]
- K_gradient = 5.0/3.0 * D * (tmp + 1) * np.exp(-tmp)
+ K_gradient = 5.0 / 3.0 * D * (tmp + 1) * np.exp(-tmp)
else:
# approximate gradient numerically
def f(theta): # helper function
diff --git a/sklearn/linear_model/base.py b/sklearn/linear_model/base.py
index fa8678d913..4055a00027 100644
--- a/sklearn/linear_model/base.py
+++ b/sklearn/linear_model/base.py
@@ -403,7 +403,7 @@ class LinearRegression(LinearModel, RegressorMixin):
self.n_jobs = n_jobs
@property
- @deprecated("residues_ is deprecated and will be removed in 0.19")
+ @deprecated("``residues_`` is deprecated and will be removed in 0.19")
def residues_(self):
"""Get the residues of the fitted model."""
return self._residues
diff --git a/sklearn/model_selection/_validation.py b/sklearn/model_selection/_validation.py
index 05673b954e..190ec8c3a9 100644
--- a/sklearn/model_selection/_validation.py
+++ b/sklearn/model_selection/_validation.py
@@ -66,7 +66,7 @@ def cross_val_score(estimator, X, y=None, labels=None, scoring=None, cv=None,
pre_dispatch='2*n_jobs'):
"""Evaluate a score by cross-validation
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
@@ -295,7 +295,7 @@ def cross_val_predict(estimator, X, y=None, labels=None, cv=None, n_jobs=1,
verbose=0, fit_params=None, pre_dispatch='2*n_jobs'):
"""Generate cross-validated estimates for each input data point
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
@@ -394,7 +394,7 @@ def cross_val_predict(estimator, X, y=None, labels=None, cv=None, n_jobs=1,
def _fit_and_predict(estimator, X, y, train, test, verbose, fit_params):
"""Fit estimator and predict values for a given dataset split.
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
@@ -483,7 +483,7 @@ def permutation_test_score(estimator, X, y, labels=None, cv=None,
verbose=0, scoring=None):
"""Evaluate the significance of a cross-validated score with permutations
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
@@ -520,7 +520,7 @@ def permutation_test_score(estimator, X, y, labels=None, cv=None,
See the :mod:`sklearn.model_selection` module for the list of
cross-validation strategies that can be used here.
- Also refer :ref:`cross-validation documentation <_cross_validation>`
+ Also refer :ref:`cross-validation documentation <cross_validation>`
n_permutations : integer, optional
Number of times to permute ``y``.
@@ -618,7 +618,7 @@ def learning_curve(estimator, X, y, labels=None,
test set will be computed. Afterwards, the scores will be averaged over
all k runs for each training subset size.
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <learning_curve>`.
Parameters
----------
@@ -836,7 +836,7 @@ def validation_curve(estimator, X, y, param_name, param_range, labels=None,
will also compute training scores and is merely a utility for plotting the
results.
- Read more in the :ref:`User Guide <validate>`.
+ Read more in the :ref:`User Guide <learning_curve>`.
Parameters
----------
diff --git a/sklearn/neural_network/multilayer_perceptron.py b/sklearn/neural_network/multilayer_perceptron.py
index 3912f1f673..c5c6b13e40 100644
--- a/sklearn/neural_network/multilayer_perceptron.py
+++ b/sklearn/neural_network/multilayer_perceptron.py
@@ -724,7 +724,7 @@ class MLPClassifier(BaseMultilayerPerceptron, ClassifierMixin):
-'constant', is a constant learning rate given by
'learning_rate_init'.
- -'invscaling' gradually decreases the learning rate 'learning_rate_' at
+ -'invscaling' gradually decreases the learning rate ``learning_rate_`` at
each time step 't' using an inverse scaling exponent of 'power_t'.
effective_learning_rate = learning_rate_init / pow(t, power_t)
@@ -1077,7 +1077,7 @@ class MLPRegressor(BaseMultilayerPerceptron, RegressorMixin):
-'constant', is a constant learnign rate given by
'learning_rate_init'.
- -'invscaling' gradually decreases the learning rate 'learning_rate_' at
+ -'invscaling' gradually decreases the learning rate ``learning_rate_`` at
each time step 't' using an inverse scaling exponent of 'power_t'.
effective_learning_rate = learning_rate_init / pow(t, power_t)
diff --git a/sklearn/preprocessing/data.py b/sklearn/preprocessing/data.py
index 98c8b4acf9..3ee4cf91f1 100644
--- a/sklearn/preprocessing/data.py
+++ b/sklearn/preprocessing/data.py
@@ -233,7 +233,7 @@ class MinMaxScaler(BaseEstimator, TransformerMixin):
Per feature maximum seen in the data
data_range_ : ndarray, shape (n_features,)
- Per feature range (data_max_ - data_min_) seen in the data
+ Per feature range ``(data_max_ - data_min_)`` seen in the data
"""
def __init__(self, feature_range=(0, 1), copy=True):
@@ -242,13 +242,13 @@ class MinMaxScaler(BaseEstimator, TransformerMixin):
@property
@deprecated("Attribute data_range will be removed in "
- "0.19. Use data_range_ instead")
+ "0.19. Use ``data_range_`` instead")
def data_range(self):
return self.data_range_
@property
@deprecated("Attribute data_min will be removed in "
- "0.19. Use data_min_ instead")
+ "0.19. Use ``data_min_`` instead")
def data_min(self):
return self.data_min_
@@ -290,7 +290,7 @@ class MinMaxScaler(BaseEstimator, TransformerMixin):
Parameters
----------
- X : array-like, shape [n_samples_, n_features]
+ X : array-like, shape [n_samples, n_features]
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
@@ -504,7 +504,7 @@ class StandardScaler(BaseEstimator, TransformerMixin):
self.copy = copy
@property
- @deprecated("Attribute std_ will be removed in 0.19. Use scale_ instead")
+ @deprecated("Attribute ``std_`` will be removed in 0.19. Use ``scale_`` instead")
def std_(self):
return self.scale_
@@ -551,7 +551,7 @@ class StandardScaler(BaseEstimator, TransformerMixin):
Parameters
----------
- X : {array-like, sparse matrix}, shape [n_samples_, n_features]
+ X : {array-like, sparse matrix}, shape [n_samples, n_features]
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
@@ -742,7 +742,7 @@ class MaxAbsScaler(BaseEstimator, TransformerMixin):
Parameters
----------
- X : {array-like, sparse matrix}, shape [n_samples_, n_features]
+ X : {array-like, sparse matrix}, shape [n_samples, n_features]
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
diff --git a/sklearn/preprocessing/tests/test_data.py b/sklearn/preprocessing/tests/test_data.py
index d87f92d10c..30a85c8ee7 100644
--- a/sklearn/preprocessing/tests/test_data.py
+++ b/sklearn/preprocessing/tests/test_data.py
@@ -956,13 +956,13 @@ def test_deprecation_minmax_scaler():
scaler = MinMaxScaler().fit(X)
depr_message = ("Attribute data_range will be removed in "
- "0.19. Use data_range_ instead")
+ "0.19. Use ``data_range_`` instead")
data_range = assert_warns_message(DeprecationWarning, depr_message,
getattr, scaler, "data_range")
assert_array_equal(data_range, scaler.data_range)
depr_message = ("Attribute data_min will be removed in "
- "0.19. Use data_min_ instead")
+ "0.19. Use ``data_min_`` instead")
data_min = assert_warns_message(DeprecationWarning, depr_message,
getattr, scaler, "data_min")
assert_array_equal(data_min, scaler.data_min)
@@ -1322,8 +1322,8 @@ def test_deprecation_standard_scaler():
rng = np.random.RandomState(0)
X = rng.random_sample((5, 4))
scaler = StandardScaler().fit(X)
- depr_message = ("Function std_ is deprecated; Attribute std_ will be "
- "removed in 0.19. Use scale_ instead")
+ depr_message = ("Function std_ is deprecated; Attribute ``std_`` will be "
+ "removed in 0.19. Use ``scale_`` instead")
std_ = assert_warns_message(DeprecationWarning, depr_message, getattr,
scaler, "std_")
assert_array_equal(std_, scaler.scale_)
--
GitLab