def test_split_samples():
X = np.arange(100.)
y = np.arange(100.)
X_divisions, y_divisions = split_samples(X, y)
assert (len(X_divisions[0]) == len(y_divisions[0]) == 75)
assert (len(X_divisions[1]) == len(y_divisions[1]) == 25)
assert (len(set(X_divisions[0]) | set(X_divisions[1])) == 100)
#----------------------------------------------------------------------
# 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 LDA
classifiers = []
predictions = []
Ncolors = np.arange(1, X.shape[1] + 1)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from astroML.utils import split_samples
from astroML.utils import completeness_contamination
from sklearn.metrics import roc_curve
signal = np.load('ClassSample_training_1.npy')
background = np.load('ClassSample_training_0.npy')
data = np.concatenate([signal, background])
data = data[~np.isnan(data).any(axis=1)]
(features_train, features_test), (labels_train, labels_test) = split_samples(data[:,:8], data[:,8], fractions=[0.75,0.25])
fig_roc = plt.figure()
ax_roc = fig_roc.add_subplot(111)
featureIDs = np.arange(2, data.shape[1]+1)
classification = []
predictions = []
scores = []
for i in featureIDs:
logr = LogisticRegression()
logr.fit(features_train[:,:i], labels_train)
labels_pred = logr.predict_proba(features_test[:,:i])[:,1]
classification.append(logr)
predictions.append(labels_pred)
fpr, tpr, thresholds = roc_curve(labels_test, labels_pred)
ax_roc.plot(fpr, tpr, label="%d features"%(i))
# print fpr, tpr
ax_roc.set_xlabel("False positive rate")
ax_roc.set_ylabel("True positive rate")
# 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
import numpy as np
from matplotlib import pyplot as plt
from sklearn.naive_bayes import GaussianNB
from astroML.datasets import fetch_rrlyrae_combined
from astroML.utils import split_samples
from astroML.utils import completeness_contamination
#----------------------------------------------------------------------
# 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 Naive Bayes
classifiers = []
predictions = []
Ncolors = np.arange(1, X.shape[1] + 1)
order = np.array([1, 0, 2, 3])
def main():
parser = argparse.ArgumentParser(description=
'Perform Dimensionality Reduction')
parser.add_argument('--alg', type=str, default='MLLE',
help='Algorithm to reduce dimensionality.')
parser.add_argument('catalog', type=str,
help='Specify the catalog on which to perform DimReduce.')
args = parser.parse_args()
#dat = Table.read('catalogs/ZEST_catalog_colors.fits')
#training_sample = dat[0:10000]
#testing_sample = dat[10001:20000]
#zkeys = ['cc', 'aa', 'm20', 'gg']
base = os.path.basename(args.catalog)
filename = os.path.splitext(base)[0]
dat = Table.read(args.catalog)
mkeys = ['elipt', 'C', 'A_1a', 'G', 'M20']#
#dat.remove_column('color')
if 'color' not in dat.colnames:
if 'kaggle' in sample:
dat = prep_catalog.color_data2(dat, 'gz2class')
if 'direct' in sample:
dat = prep_catalog.color_data(dat, 'zclass')
dat.write(args.catalog, overwrite=True)
#dat = prep_catalog.adjust_asym(dat, mkeys[2])
#train, traincols, targets = prep_catalog.whiten_data(dat, mkeys)
n_neighbors = [10,12,15,20]
#n_neighbors = [7]
n_components = 3
for i, n_neigh in enumerate(n_neighbors):
if args.alg in ['MLLE', 'LLE', 'LTSA', 'HLLE']:
if args.alg == 'MLLE':
method = 'modified'
elif args.alg == 'LLE':
method = 'standard'
elif args.alg == 'LTSA':
method = 'ltsa'
elif args.alg == 'HLLE':
method = 'hessian'
#replace_panoptes(dat)
#pdb.set_trace()
#sample = 'directbig_panoptes'
X, y = prep_catalog.whiten_data(dat, mkeys)
(dat1, dat2),(thing1,thing2) = split_samples(dat, dat,[0.75, 0.35],
random_state=0)
(X_train, X_test), (y_train, y_test) = split_samples(X, y,
[0.75, 0.35], random_state=0)
y_train = simplify_classlabels(y_train)
y_test = simplify_classlabels(y_test)
#filename = 'modified_7_directbig_new'
X_train = X
y_train = simplify_classlabels(y)
#'''
#sample ='direct_zcut'
#Y_train, Y_test = open_previous_LLE(filename)
#cut = np.where(X1['REDSHIFT'] <= 0.05)
#X1_cut = X1[cut]
#QC_plots(X1_cut)
#Y_train = np.array(Y_train)[cut]
#col_train = np.array(col_train)[cut]
#X = Table(X)
#cut_out_mixedup_region(X, np.array(Y_train))
#'''
print "performing "+method+" LLE with",n_neigh,\
"nearest neighbors"
print "on training sample of",len(X_train),"objects"
t0 = time()
A = LLE(n_neigh, n_components, eigen_solver='auto', method=method)
error = A.fit(X_train).reconstruction_error_
Y_train = A.fit_transform(X_train)
Y_test = A.transform(X_train)
t1 = time()
#'''
metadata = {'method':method, 'N':n_neigh, 'd':n_components,
'error':error, 'time':t1-t0, 'sample':filename+'_total'}
save_dimreduce(dat, Y_train, y_train, metadata, filename+'_total')
#metadata = {'method':method, 'N':n_neigh, 'd':n_components,
# 'error':error, 'time':t1-t0, 'sample':filename+'_test'}
#save_dimreduce(X2, Y_test, y_test, metadata, filename+'_test')
# plot in 3D
plot_dimreduce_3D(Y_train, y_train[:,1], Y_test, y_test[:,1],
method, n_neigh, error, t1-t0, filename, two=False)
#====================================================================#
elif args.alg == 'ISO':
method='IsoMap'
print "performing IsoMap with",n_neigh,"nearest neighbors"
print "on training sample of",len(dat),"objects"
t0 = time()
A = Isomap(n_neigh, n_components, eigen_solver='dense')
error = A.fit(train).reconstruction_error()
Y = A.fit_transform(train)
#Y2 = A.transform(test)
t1 = time()
print "%s: %.2g sec" %(args.alg, t1-t0)
print "reconstruction error: ", error
print "begin plotting"
plot_dimreduce(Y, traincols, method, n_neigh, sample, axis=0)
plot_dimreduce(Y, traincols, method, n_neigh, sample, axis=1)
plot_dimreduce(Y, traincols, method, n_neigh, sample, axis=2)
plot_dimreduce_3D(Y, traincols, Y, traincols, method,
n_neigh, (t1-t0), error, sample)
elif args.alg == 'LDA':
print "performing LDA"
X, Xc, y = prep_catalog.whiten_data(dat, mkeys)
(X_train, X_test), (y_train, y_test) = split_samples(X, y,
[0.75, 0.25], random_state=0)
DRclf = LDA(3, priors=None)
#DRclf.fit(X_train, y_train)
DRtrain = DRclf.fit(X_train, y_train).transform(X_train)
DRtest = DRclf.fit(X_train, y_train).transform(X_test)
classes = np.unique(y_train)
colors = np.array(['darkred', 'red', 'lightsalmon',
'darkgreen', 'lightgreen', 'lightseagreen',
'indigo', 'darkviolet', 'plum'])
plot_LDA_3D(DRtrain, y_train, classes, colors, sample)
pdb.set_trace()
#classifiers = []
#predictions = []
#Nparams = np.arange(1, X.shape[1]+1)
#for nc in Nparams:
clf = LDA()
clf.fit(DRtrain, y_train)
y_pred = clf.predict(DRtest)
matchesLDA = (y_pred == y_test)
print np.sum(matchesLDA)
pdb.set_trace()
#------------------------------------------
from sklearn.neighbors import KNeighborsClassifier
knc = KNeighborsClassifier(5)
knc.fit(DRtrain, y_train)
y_pred = knc.predict(DRtest)
matchesKNN = (y_pred == y_test)
print np.sum(matchesKNN)
pdb.set_trace()
#------------------------------------------
from astroML.classification import GMMBayes
gmmb = GMMBayes(9)
gmmb.fit(DRtrain, y_train)
y_pred = gmmb.predict(DRtest)
matchesGMMB = (y_pred == y_test)
print np.sum(matchesGMMB)
pdb.set_trace()
#------------------------------------------
# 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)
pdb.set_trace()
im = ax.scatter(X[:, 3], X[:, 4], color=Xc, cmap=plt.cm.Spectral,
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, 1.5)
#ax.contour(xx, yy, Z, [0.5], colors='k')
#ax.set_xlim(xlim)
#ax.set_ylim(ylim)
ax.set_xlabel('$G$')
ax.set_ylabel('$M20$')
#pred, true = classification_loss(predictions, y_test)
#completeness, contamination = completeness_contamination(pred, true)
pdb.set_trace()
#'''
#t0 = time()
#A = LDA(n_components, priors=None)
#Y = A.fit_transform(train, targets)
#Y2 = A.fit(train, targets).transform(train)
#t1 = time()
#print "%s: %.2g sec" %(args.alg, t1-t0)
predict = A.predict(train)
#print "Predicted classes:", predict
#pdb.set_trace()
#pdb.set_trace()
#'''
plot_LDA_3D(Y2, targets, classes, colors, sample)
plot_LDA(Y2, targets, classes, colors, sample, axis=0)
plot_LDA(Y2, targets, classes, colors, sample, axis=1)
plot_LDA(Y2, targets, classes, colors, sample, axis=2)
pdb.set_trace()