From 2df6bfad588813a19dddc72979f6f5e8322fa15a Mon Sep 17 00:00:00 2001
From: Andreas Mueller <amueller@nyu.edu>
Date: Tue, 3 Nov 2015 17:43:46 -0500
Subject: [PATCH] DOC some fixes to the doc build.
---
doc/datasets/rcv1.rst | 4 +-
doc/modules/decomposition.rst | 1 +
doc/modules/feature_selection.rst | 2 +
doc/modules/multiclass.rst | 8 +-
doc/whats_new.rst | 7 +-
examples/applications/face_recognition.py | 4 +-
sklearn/cross_decomposition/pls_.py | 23 +++---
sklearn/datasets/descr/breast_cancer.rst | 89 ++++++++++++-----------
sklearn/datasets/descr/diabetes.rst | 2 +-
sklearn/datasets/descr/digits.rst | 3 +-
sklearn/datasets/descr/iris.rst | 2 +
sklearn/linear_model/base.py | 2 +-
sklearn/preprocessing/data.py | 14 ++--
sklearn/preprocessing/tests/test_data.py | 8 +-
14 files changed, 92 insertions(+), 77 deletions(-)
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/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/whats_new.rst b/doc/whats_new.rst
index 88b8d47512..b5cf4a93bb 100644
--- a/doc/whats_new.rst
+++ b/doc/whats_new.rst
@@ -281,7 +281,7 @@ 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`_.
API changes summary
-------------------
@@ -3313,8 +3313,8 @@ 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
@@ -3774,3 +3774,4 @@ 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
diff --git a/examples/applications/face_recognition.py b/examples/applications/face_recognition.py
index be466e9532..1385bdd1c7 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/sklearn/cross_decomposition/pls_.py b/sklearn/cross_decomposition/pls_.py
index 46961c90b3..a6f27f0810 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``
@@ -655,7 +657,8 @@ class PLSCanonical(_PLS):
Notes
-----
- Matrices :
+ Matrices::
+
T: x_scores_
U: y_scores_
W: x_weights_
@@ -663,19 +666,21 @@ 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 518b2c6dff..a568db5330 100644
--- a/sklearn/datasets/descr/breast_cancer.rst
+++ b/sklearn/datasets/descr/breast_cancer.rst
@@ -18,51 +18,52 @@ 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
@@ -107,11 +108,11 @@ 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 76b0132a2e..28706ac287 100644
--- a/sklearn/datasets/descr/diabetes.rst
+++ b/sklearn/datasets/descr/diabetes.rst
@@ -28,7 +28,7 @@ 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 611363f69a..a30514474f 100644
--- a/sklearn/datasets/descr/digits.rst
+++ b/sklearn/datasets/descr/digits.rst
@@ -1,4 +1,5 @@
- 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 0e918f8b8c..ae05779ca6 100644
--- a/sklearn/datasets/descr/iris.rst
+++ b/sklearn/datasets/descr/iris.rst
@@ -15,6 +15,7 @@ Data Set Characteristics:
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
+
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
@@ -23,6 +24,7 @@ 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/linear_model/base.py b/sklearn/linear_model/base.py
index a6172e5b03..53efca1122 100644
--- a/sklearn/linear_model/base.py
+++ b/sklearn/linear_model/base.py
@@ -394,7 +394,7 @@ 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/preprocessing/data.py b/sklearn/preprocessing/data.py
index 22aac39f44..54ea1ed4fc 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 b32aa6af9d..7a91d46aea 100644
--- a/sklearn/preprocessing/tests/test_data.py
+++ b/sklearn/preprocessing/tests/test_data.py
@@ -970,13 +970,13 @@ 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)
@@ -1336,8 +1336,8 @@ 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