def compute_SVM_results(i_train, i_test, n_components=5):
classifiers = []
predictions = []
Xtests = []
ytests = []
Xtrains = []
ytrains = []
for i in range(len(attributes)):
Xtrain = X[i][i_train]
Xtest = X[i][i_test]
ytrain = y[i][i_train]
ytest = y[i][i_test]
clf = GMMBayes(n_components,
min_covar=1E-5,
covariance_type='full',
random_state=0)
clf.fit(Xtrain, ytrain)
y_pred = clf.predict(Xtest)
classifiers.append(clf)
predictions.append(y_pred)
return classifiers, predictions
def test_too_many_components_warning():
X = np.random.normal(0, 1, size=(3, 2))
y = np.zeros(3)
ncm = 5
clf = GMMBayes(ncm)
with pytest.warns(UserWarning,
match="Expected n_samples >= "
"n_components but got "):
clf.fit(X, y)
def test_incompatible_shapes_exception():
X = np.random.normal(0, 1, size=(100, 2))
y = np.zeros(99)
ncm = 1
clf = GMMBayes(ncm)
with pytest.raises(Exception) as e:
assert clf.fit(X, y)
assert str(e.value) == "X and y have incompatible shapes"
def test_incompatible_number_of_components_exception():
X = np.random.normal(0, 1, size=(100, 2))
y = np.zeros(100)
ncm = [1, 2, 3]
clf = GMMBayes(ncm)
with pytest.raises(Exception) as e:
assert clf.fit(X, y)
assert str(e.value) == ("n_components must be compatible with "
"the number of classes")
def test_gmm2d():
x1 = np.random.normal(0, 1, size=(100, 2))
x2 = np.random.normal(10, 1, size=(100, 2))
X = np.vstack((x1, x2))
y = np.zeros(200)
y[100:] = 1
for ncm in (1, 2, 3):
clf = GMMBayes(ncm)
clf.fit(X, y)
predicted = clf.predict(X)
assert_allclose(y, predicted)
def test_gmm1d():
x1 = np.random.normal(0, 1, size=100)
x2 = np.random.normal(10, 1, size=100)
X = np.concatenate((x1, x2)).reshape((200, 1))
y = np.zeros(200)
y[100:] = 1
ncm = 1
clf = GMMBayes(ncm)
clf.fit(X, y)
predicted = clf.predict(X)
assert_allclose(y, predicted)
def compute_GMMbayes(Ncolors, Ncomp):
classifiers = []
predictions = []
for ncm in Ncomp:
classifiers.append([])
predictions.append([])
for nc in Ncolors:
clf = GMMBayes(ncm, min_covar=1E-5, covariance_type='full')
clf.fit(X_train[:, :nc], y_train)
y_pred = clf.predict(X_test[:, :nc])
classifiers[-1].append(clf)
predictions[-1].append(y_pred)
return classifiers, predictions
def compute_GMMbayes(Ncolors, Ncomp):
classifiers = []
predictions = []
for ncm in Ncomp:
classifiers.append([])
predictions.append([])
for nc in Ncolors:
clf = GMMBayes(ncm, min_covar=1E-5, covariance_type='full')
clf.fit(X_train[:, :nc], y_train)
y_pred = clf.predict(X_test[:, :nc])
classifiers[-1].append(clf)
predictions[-1].append(y_pred)
return classifiers, predictions
def compute_SVM_results(i_train, i_test, n_components=5):
classifiers = []
predictions = []
Xtests = []
ytests = []
Xtrains = []
ytrains = []
for i in range(len(attributes)):
Xtrain = X[i][i_train]
Xtest = X[i][i_test]
ytrain = y[i][i_train]
ytest = y[i][i_test]
clf = GMMBayes(n_components, min_covar=1E-5, covariance_type='full')
clf.fit(Xtrain, ytrain)
y_pred = clf.predict(Xtest)
classifiers.append(clf)
predictions.append(y_pred)
return classifiers, predictions
def gmm_bayes_analysis(X_train, X_test, y_train, y_test):
clf = GMMBayes()
t1 = time.time()
clf.fit(X_train, y_train)
t2 = time.time()
t_train = t2 - t1
t1 = time.time()
score = clf.score(X_test, y_test)
t2 = time.time()
t_test = t2 - t1
# Generate graphs/data for analysis
tpr, fpr, roc_auc = roc_calc(GMMBayes(), X_train, X_test, y_train, y_test)
return tpr, fpr, roc_auc, t_train, t_test, score
#posterior[m] = knc.predict_proba(X_test)
print "Error-Correcting Output Code: ", np.mean(
accuracy) / 0.72, np.std(accuracy) / 0.72
print k
for i in range(0, 6):
for j in range(0, 6):
print '{:5.2f} '.format(box[i, j] / 100.0),
print
#end GNB
box = np.zeros([6, 6])
accuracy = np.zeros(100)
for m in range(0, 100):
gmm = GMMBayes(n_components=3)
y_pred = gmm.fit(X_train, y_train).predict(X_test)
for i in range(0, len(y_pred)):
if y_pred[i] == y_test[i]:
n = n + 1
accuracy[m] = accuracy[m] + 1
box[y_test[i] - 1,
y_pred[i] - 1] = box[y_test[i] - 1, y_pred[i] - 1] + 1
print "Gaussian Mixture Models, n_components=3: ", np.mean(
accuracy) / 0.72, np.std(accuracy) / 0.72
for i in range(0, 6):
for j in range(0, 6):
print '{:5.2f} '.format(box[i, j] / 100.0),
print
box = np.zeros([6, 6])
ytrain = y[i][i_train]
ytest = y[i][i_test]
print "Xtrain",Xtrain.shape
print "ytrain",ytrain.shape
print Xtrain
print ytrain
print np.isnan(Xtrain).sum()
print np.isnan(ytrain).sum()
n_componentss = np.arange(5,7)
scores = np.zeros(len(n_componentss))
for j,n_components in enumerate(n_componentss):
clf = GMMBayes(n_components, min_covar=1E-5, covariance_type='full',
random_state=0)
clf.fit(Xtrain, ytrain)
y_pred = clf.predict(Xtest)
print y_pred
print "score, ", (y_pred==ytest).sum()
#fpr, tpr, thresholds = roc_curve(ytest, y_prob)
#aucs[j]= auc(fpr,tpr)
scores[j]=1.*(y_pred==ytest).sum()
imax = np.argmax(scores)
print "optimal N is ",n_componentss[imax]
N_comp = n_componentss[imax]
clf = GMMBayes(N_comp, min_covar=1E-5, covariance_type='full',
random_state=0)
clf.fit(Xtrain, ytrain)
X_test = sample2
y_test = labels[272:, i]
else:
X_train = training
y_train = labels[:172, i]
X_test = sampletest
y_test = labels[172:, i]
if i >= 2: j = 3
else: j = 6
accuracy = np.zeros(72)
posterior = np.empty([10000, 72, 6])
box = np.zeros([6, 6])
for m in range(0, 100):
gmm = GMMBayes(n_components=6)
gmm.fit(X_train, y_train)
y_pred = gmm.predict(X_test)
n = 0
for i in range(0, len(y_pred)):
if y_pred[i] == y_test[i]:
#print i, y_pred[i], y_test[i]
n = n + 1
accuracy[i] = accuracy[i] + 1
box[y_test[i] - 1,
y_pred[i] - 1] = box[y_test[i] - 1, y_pred[i] - 1] + 1
posterior[m] = gmm.predict_proba(X_test)
print 30, 20, sum(accuracy[0:8]) / 8.0, sum(accuracy[8:18]) / 10.0, sum(
accuracy[18:30]) / 12.0, sum(accuracy[30:43]) / 13.0, sum(
accuracy[43:56]) / 13.0, sum(
np.random.shuffle(training_data_full)
n_samples = training_data_full.shape[0]
training_set = training_data_full[:n_samples*0.8, :]
test_set = training_data_full[n_samples*0.8:, :]
features = training_set[:, :-1]
labels = training_set[:, -1]
# Fit and plot
pl.figure()
ax1 = pl.subplot(121)
ax2 = pl.subplot(122)
for n_clusters in [2]:
print n_clusters
gmmb = GMMBayes(n_clusters)
gmmb.fit(features, labels)
scores = gmmb.predict_proba(features)
fpr, tpr, thresholds = roc_curve(labels, scores[:,1])
ax1.plot(fpr, tpr, label='%d clusters'%n_clusters)
if n_clusters == 15:
ax2.hist(scores[labels==0, 1], bins=100, normed=True,
alpha=0.5, label='Background')
ax2.hist(scores[labels==1, 1], bins=100, normed=True,
alpha=0.5, label='Signal')
ax2.legend(loc='best')
#np.save('fpr_tpr_GMMBayes_15clusters.npy', np.vstack([fpr, tpr]))
for i in range(0,5):
if i==1 or i==3:
X_train = training2
y_train = labels[100:172,i]
X_test = sample2
y_test = labels[272:,i]
else:
X_train = training
y_train = labels[:172,i]
X_test = sampletest
y_test = labels[172:,i]
ncomp = 0
ncorrect = 0
for j in range(1,9):
gmm = GMMBayes(n_components=j)
gmm.fit(X_train, y_train)
y_pred = gmm.predict(X_test)
n=0
for k in range(0,len(y_pred)):
if y_pred[k] == y_test[k]:
#print i, y_pred[i], y_test[i]
n = n+1
if n > ncorrect:
ncorrect = n
ncomp = j
print '{:3d}/{:3d}, {:2.2%}, n_components={:d}'.format(ncorrect, len(y_test),
ncorrect*1.0/len(y_test), ncomp)
'''
X_test = sample2
y_test = labels[272:,i]
else:
X_train = training
y_train = labels[:172,i]
X_test = sampletest
y_test = labels[172:,i]
if i>=2: j=3
else: j=6
accuracy = np.zeros(72)
posterior = np.empty([10000,72,6])
box = np.zeros([6,6])
for m in range(0,100):
gmm = GMMBayes(n_components=6)
gmm.fit(X_train, y_train)
y_pred = gmm.predict(X_test)
n=0
for i in range(0,len(y_pred)):
if y_pred[i] == y_test[i]:
#print i, y_pred[i], y_test[i]
n = n+1
accuracy[i] = accuracy[i]+1
box[y_test[i]-1,y_pred[i]-1] = box[y_test[i]-1,y_pred[i]-1] + 1
posterior[m] = gmm.predict_proba(X_test)
print 30, 20, sum(accuracy[0:8])/8.0, sum(accuracy[8:18])/10.0, sum(accuracy[18:30])/12.0, sum(accuracy[30:43])/13.0, sum(accuracy[43:56])/13.0, sum(accuracy[56:72])/16.0, sum(accuracy)/72.0
means = np.empty([72,6])
stds = np.empty([72,6])
grid = np.empty([6,6])
for i in range(0, 5):
if i == 1 or i == 3:
X_train = training2
y_train = labels[100:172, i]
X_test = sample2
y_test = labels[272:, i]
else:
X_train = training
y_train = labels[:172, i]
X_test = sampletest
y_test = labels[172:, i]
ncomp = 0
ncorrect = 0
for j in range(1, 9):
gmm = GMMBayes(n_components=j)
gmm.fit(X_train, y_train)
y_pred = gmm.predict(X_test)
n = 0
for k in range(0, len(y_pred)):
if y_pred[k] == y_test[k]:
#print i, y_pred[i], y_test[i]
n = n + 1
if n > ncorrect:
ncorrect = n
ncomp = j
print '{:3d}/{:3d}, {:2.2%}, n_components={:d}'.format(
ncorrect, len(y_test), ncorrect * 1.0 / len(y_test), ncomp)
'''
def onpick(event):
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()
