From 20006d0611c941e02af980581a1143ce26e73422 Mon Sep 17 00:00:00 2001
From: Fabian Pedregosa <fabian.pedregosa@inria.fr>
Date: Wed, 26 May 2010 12:10:36 +0200
Subject: [PATCH] Refactoring: Squash samples_generator module into one file.
---
examples/glm/{ols.py => plot_ols.py} | 0
.../nonlinear.py => samples_generator.py} | 27 ++++++++++++++++++-
.../datasets/samples_generator/__init__.py | 0
.../datasets/samples_generator/linear.py | 27 -------------------
scikits/learn/datasets/setup.py | 1 -
5 files changed, 26 insertions(+), 29 deletions(-)
rename examples/glm/{ols.py => plot_ols.py} (100%)
rename scikits/learn/datasets/{samples_generator/nonlinear.py => samples_generator.py} (52%)
mode change 100755 => 100644
delete mode 100644 scikits/learn/datasets/samples_generator/__init__.py
delete mode 100755 scikits/learn/datasets/samples_generator/linear.py
diff --git a/examples/glm/ols.py b/examples/glm/plot_ols.py
similarity index 100%
rename from examples/glm/ols.py
rename to examples/glm/plot_ols.py
diff --git a/scikits/learn/datasets/samples_generator/nonlinear.py b/scikits/learn/datasets/samples_generator.py
old mode 100755
new mode 100644
similarity index 52%
rename from scikits/learn/datasets/samples_generator/nonlinear.py
rename to scikits/learn/datasets/samples_generator.py
index db44141562..11628fac83
--- a/scikits/learn/datasets/samples_generator/nonlinear.py
+++ b/scikits/learn/datasets/samples_generator.py
@@ -1,6 +1,32 @@
import numpy as np
import numpy.random as nr
+def sparse_uncorrelated(nb_samples=100, nb_features=10):
+ """
+ Function creating simulated data with sparse uncorrelated design.
+ (cf.Celeux et al. 2009, Bayesian regularization in regression)
+ X = NR.normal(0,1)
+ Y = NR.normal(X[:,0]+2*X[:,1]-2*X[:,2]-1.5*X[:,3])
+ The number of features is at least 10.
+
+ Parameters
+ ----------
+ nb_samples : int
+ number of samples (defaut is 100).
+ nb_features : int
+ number of features (defaut is 5).
+
+ Returns
+ -------
+ X : numpy array of shape (nb_samples, nb_features) for input samples
+ Y : numpy array of shape (nb_samples) for labels
+ """
+ X = nr.normal(loc=0, scale=1, size=(nb_samples, nb_features))
+ Y = nr.normal(loc=X[:, 0] + 2 * X[:, 1] - 2 * X[:,2] - 1.5 * X[:, 3],
+ scale = np.ones(nb_samples))
+ return X, Y
+
+
def friedman(nb_samples=100, nb_features=10,noise_std=1):
"""
Function creating simulated data with non linearities
@@ -27,4 +53,3 @@ def friedman(nb_samples=100, nb_features=10,noise_std=1):
Y = 10*np.sin(X[:,0]*X[:,1]) + 20*(X[:,2]-0.5)**2 + 10*X[:,3] + 5*X[:,4]
Y += noise_std*nr.normal(loc=0,scale=1,size=(nb_samples))
return X,Y
-
diff --git a/scikits/learn/datasets/samples_generator/__init__.py b/scikits/learn/datasets/samples_generator/__init__.py
deleted file mode 100644
index e69de29bb2..0000000000
diff --git a/scikits/learn/datasets/samples_generator/linear.py b/scikits/learn/datasets/samples_generator/linear.py
deleted file mode 100755
index 8492442812..0000000000
--- a/scikits/learn/datasets/samples_generator/linear.py
+++ /dev/null
@@ -1,27 +0,0 @@
-import numpy as np
-import numpy.random as nr
-
-def sparse_uncorrelated(nb_samples=100, nb_features=10):
- """
- Function creating simulated data with sparse uncorrelated design.
- (cf.Celeux et al. 2009, Bayesian regularization in regression)
- X = NR.normal(0,1)
- Y = NR.normal(X[:,0]+2*X[:,1]-2*X[:,2]-1.5*X[:,3])
- The number of features is at least 10.
-
- Parameters
- ----------
- nb_samples : int
- number of samples (defaut is 100).
- nb_features : int
- number of features (defaut is 5).
-
- Returns
- -------
- X : numpy array of shape (nb_samples, nb_features) for input samples
- Y : numpy array of shape (nb_samples) for labels
- """
- X = nr.normal(loc=0, scale=1, size=(nb_samples, nb_features))
- Y = nr.normal(loc=X[:, 0] + 2 * X[:, 1] - 2 * X[:,2] - 1.5 * X[:, 3],
- scale = np.ones(nb_samples))
- return X, Y
diff --git a/scikits/learn/datasets/setup.py b/scikits/learn/datasets/setup.py
index 579b3fb084..e97f6bd648 100755
--- a/scikits/learn/datasets/setup.py
+++ b/scikits/learn/datasets/setup.py
@@ -3,7 +3,6 @@
def configuration(parent_package='',top_path=None):
from numpy.distutils.misc_util import Configuration
config = Configuration('datasets',parent_package,top_path)
- config.add_subpackage('samples_generator')
config.add_data_dir('data')
config.add_data_dir('descr')
return config
--
GitLab