This documentation is for astroML version 0.2

This page

Links

astroML Mailing List

GitHub Issue Tracker

Videos

Scipy 2012 (15 minute talk)

Scipy 2013 (20 minute talk)

Citing

If you use the software, please consider citing astroML.

Logistic Regression of photometryΒΆ

Figure 9.8

Logistic regression for RR Lyrae stars (see caption of figure 9.3 for details). With all four colors, logistic regression achieves a completeness of 0.993 and a contamination of 0.838.

../../_images_1ed/fig_rrlyrae_logreg_1.png
completeness [ 0.98540146  1.          1.          1.        ]
contamination [ 0.88168273  0.8446712   0.84726867  0.84760845]
[-4.29337171]
[[-12.89059477   6.92436876  -4.29337171]]
# Author: Jake VanderPlas
# License: BSD
#   The figure produced by this code is published in the textbook
#   "Statistics, Data Mining, and Machine Learning in Astronomy" (2013)
#   For more information, see http://astroML.github.com
#   To report a bug or issue, use the following forum:
#    https://groups.google.com/forum/#!forum/astroml-general
import numpy as np
from matplotlib import pyplot as plt
from matplotlib import colors

from sklearn.linear_model import LogisticRegression
from astroML.datasets import fetch_rrlyrae_combined
from astroML.utils import split_samples
from astroML.utils import completeness_contamination

#----------------------------------------------------------------------
# This function adjusts matplotlib settings for a uniform feel in the textbook.
# Note that with usetex=True, fonts are rendered with LaTeX.  This may
# result in an error if LaTeX is not installed on your system.  In that case,
# you can set usetex to False.
from astroML.plotting import setup_text_plots
setup_text_plots(fontsize=8, usetex=True)

#----------------------------------------------------------------------
# get data and split into training & testing sets
X, y = fetch_rrlyrae_combined()
X = X[:, [1, 0, 2, 3]]  # rearrange columns for better 1-color results
(X_train, X_test), (y_train, y_test) = split_samples(X, y, [0.75, 0.25],
                                                     random_state=0)

N_tot = len(y)
N_st = np.sum(y == 0)
N_rr = N_tot - N_st
N_train = len(y_train)
N_test = len(y_test)
N_plot = 5000 + N_rr

#----------------------------------------------------------------------
# perform Classification
classifiers = []
predictions = []
Ncolors = np.arange(1, X.shape[1] + 1)

for nc in Ncolors:
    clf = LogisticRegression(class_weight='auto')
    clf.fit(X_train[:, :nc], y_train)
    y_pred = clf.predict(X_test[:, :nc])

    classifiers.append(clf)
    predictions.append(y_pred)

completeness, contamination = completeness_contamination(predictions, y_test)

print "completeness", completeness
print "contamination", contamination

#------------------------------------------------------------
# Compute the decision boundary
clf = classifiers[1]
xlim = (0.7, 1.35)
ylim = (-0.15, 0.4)

xx, yy = np.meshgrid(np.linspace(xlim[0], xlim[1], 71),
                     np.linspace(ylim[0], ylim[1], 81))

print clf.intercept_
print clf.raw_coef_

Z = clf.predict_proba(np.c_[yy.ravel(), xx.ravel()])[:, 1]
Z = Z.reshape(xx.shape)

#----------------------------------------------------------------------
# plot the results
fig = plt.figure(figsize=(5, 2.5))
fig.subplots_adjust(bottom=0.15, top=0.95, hspace=0.0,
                    left=0.1, right=0.95, wspace=0.2)

# left plot: data and decision boundary
ax = fig.add_subplot(121)
im = ax.scatter(X[-N_plot:, 1], X[-N_plot:, 0], c=y[-N_plot:],
                s=4, lw=0, cmap=plt.cm.binary, zorder=2)
im.set_clim(-0.5, 1)

im = ax.imshow(Z, origin='lower', aspect='auto',
               cmap=plt.cm.binary, zorder=1,
               extent=xlim + ylim)
im.set_clim(0, 2)

ax.contour(xx, yy, Z, [0.5], colors='k')

ax.set_xlim(xlim)
ax.set_ylim(ylim)

ax.set_xlabel('$u-g$')
ax.set_ylabel('$g-r$')

# plot completeness vs Ncolors
ax = fig.add_subplot(222)

ax.plot(Ncolors, completeness, 'o-k', ms=6)

ax.xaxis.set_major_locator(plt.MultipleLocator(1))
ax.yaxis.set_major_locator(plt.MultipleLocator(0.2))
ax.xaxis.set_major_formatter(plt.NullFormatter())

ax.set_ylabel('completeness')
ax.set_xlim(0.5, 4.5)
ax.set_ylim(-0.1, 1.1)
ax.grid(True)

# plot contamination vs Ncolors
ax = fig.add_subplot(224)
ax.plot(Ncolors, contamination, 'o-k', ms=6)

ax.xaxis.set_major_locator(plt.MultipleLocator(1))
ax.yaxis.set_major_locator(plt.MultipleLocator(0.2))
ax.xaxis.set_major_formatter(plt.FormatStrFormatter('%i'))
ax.set_xlabel('N colors')
ax.set_ylabel('contamination')
ax.set_xlim(0.5, 4.5)
ax.set_ylim(-0.1, 1.1)
ax.grid(True)

plt.show()