def plot_learning_curves(num_points,
X_train,
Y_train,
X_test,
Y_test,
positive_class=1,
negative_class=0):
train_set_sizes = [len(X_train) / k for k in range(num_points + 1, 0, -1)]
test_errors = []
training_errors = []
for training_set_size in train_set_sizes:
model = train(X_train, Y_train, training_set_size)
test_error = evaluate(model, X_test, Y_test, positive_class,
negative_class)
training_error = evaluate(model, X_train, Y_train, positive_class,
negative_class)
test_errors.append(test_error)
training_errors.append(training_error)
plt.plot(train_set_sizes,
training_errors,
'bs-',
label='Training accuracy')
plt.plot(train_set_sizes, test_errors, 'g^-', label='Test accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Number of training samples')
plt.title('Augmented Logistic Regression Learning Curve')
plt.legend(loc='lower right')
plt.savefig('../Figures/accuracyPlotAugmented.png', dpi=100)
pylab.show()
def plot_sdss(cat_path):
for catfile in find_files(cat_path, "*merged+sdss.txt"):
# for now ignore the channel 2 files
if catfile.split('/')[-1].split('_')[1] != '1':
continue
print("\nreading catalog: {}".format(catfile))
df = pd.read_table(catfile, sep=' ')
# get rid of negative flux sources, if any
df = df[df.flux > 0]
# convert to magnitudes
mags = spz_jy_to_mags(df.flux * 1e-3, 1)
# print counts per magnitude bin
for i in range(10, 15):
sc = ((df.cl == 3) & (mags > i) & (mags < i + 1)).sum()
xc = ((df.xsc == 1) & (mags > i) & (mags < i + 1)).sum()
msg = "{}th to {}th mag: {} SDSS galaxy sources, {} 2MASS XSC sources"
print(msg.format(i, i + 1, sc, xc))
# print number of sources agreed upon
agree = ((df.xsc == 1) & (df.cl == 3)).sum()
disagree = ((df.xsc == 1) & (df.cl == 6)).sum()
na = ((df.xsc == 1) & (df.cl == 0)).sum()
msg = "{} 2MASS XSC sources classified as galaxies by SDSS"
print(msg.format(agree))
msg = "{} 2MASS XSC sources classified as stars by SDSS"
print(msg.format(disagree))
msg = "{} 2MASS XSC sources not matched to SDSS"
print(msg.format(na))
# plot normed histograms of 2MASS XSC and SDSS galaxy magnitudes
xsc_gals = (mags > 10) & (mags < 15) & (df.xsc == 1)
sdss_gals = (mags > 10) & (mags < 15) & (df.cl == 3)
# mags[xsc_gals].hist(label='2MASS XSC', normed=True)
# mags[sdss_gals].hist(label='SDSS galaxies', normed=True)
plt.hist([mags[xsc_gals].values, mags[sdss_gals].values],
bins=5,
label=['2MASS', 'SDSS'])
plt.xlabel('IRAC1 [mag]')
plt.ylabel('Number Count')
reg = catfile.split('/')[-1].split('_')[0]
plt.title('{} Extended Sources / Galaxies'.format(reg))
plt.legend(loc=2)
name = '{}_2mass_xsc_vs_sdss_hist.png'.format(reg)
outpath = '/'.join(catfile.split('/')[:-1] + [name])
plt.savefig(outpath, dpi=100)
plt.close()
print("created file: {}".format(outpath))
def plot_sdss(cat_path):
for catfile in find_files(cat_path, "*merged+sdss.txt"):
# for now ignore the channel 2 files
if catfile.split('/')[-1].split('_')[1] != '1':
continue
print("\nreading catalog: {}".format(catfile))
df = pd.read_table(catfile, sep=' ')
# get rid of negative flux sources, if any
df = df[df.flux > 0]
# convert to magnitudes
mags = spz_jy_to_mags(df.flux*1e-3, 1)
# print counts per magnitude bin
for i in range(10,15):
sc = ((df.cl == 3) & (mags > i) & (mags < i+1)).sum()
xc = ((df.xsc == 1) & (mags > i) & (mags < i+1)).sum()
msg = "{}th to {}th mag: {} SDSS galaxy sources, {} 2MASS XSC sources"
print(msg.format(i, i+1, sc, xc))
# print number of sources agreed upon
agree = ((df.xsc == 1) & (df.cl == 3)).sum()
disagree = ((df.xsc == 1) & (df.cl == 6)).sum()
na = ((df.xsc == 1) & (df.cl == 0)).sum()
msg = "{} 2MASS XSC sources classified as galaxies by SDSS"
print(msg.format(agree))
msg = "{} 2MASS XSC sources classified as stars by SDSS"
print(msg.format(disagree))
msg = "{} 2MASS XSC sources not matched to SDSS"
print(msg.format(na))
# plot normed histograms of 2MASS XSC and SDSS galaxy magnitudes
xsc_gals = (mags > 10) & (mags < 15) & (df.xsc == 1)
sdss_gals = (mags > 10) & (mags < 15) & (df.cl == 3)
# mags[xsc_gals].hist(label='2MASS XSC', normed=True)
# mags[sdss_gals].hist(label='SDSS galaxies', normed=True)
plt.hist([mags[xsc_gals].values, mags[sdss_gals].values],
bins=5, label=['2MASS', 'SDSS'])
plt.xlabel('IRAC1 [mag]')
plt.ylabel('Number Count')
reg = catfile.split('/')[-1].split('_')[0]
plt.title('{} Extended Sources / Galaxies'.format(reg))
plt.legend(loc=2)
name = '{}_2mass_xsc_vs_sdss_hist.png'.format(reg)
outpath = '/'.join(catfile.split('/')[:-1]+[name])
plt.savefig(outpath, dpi=100)
plt.close()
print("created file: {}".format(outpath))
def submit_time_histogram(arr):
"""
Use Matplotlib to plot a normalized histogram of submit times
"""
from math import ceil, log
try:
import matplotlib.mlab as mlab
from prettyplotlib import plt
except ImportError:
print(
'You must have Matplotlib and Prettyplotlib installed to plot a histogram.'
)
# Use Sturges' formula for number of bins: k = ceiling(log2 n + 1)
k = ceil(log(len(arr), 2) + 1)
n, bins, patches = plt.hist(arr,
k,
normed=1,
facecolor='green',
alpha=0.75)
# throw a PDF plot on top of it
#y = mlab.normpdf(bins, np.mean(arr), np.std(arr))
#l = plt.plot(bins, y, 'r--', linewidth=1)
# Get a Bayesian confidence interval for mean, variance, standard deviation
dmean, dvar, dsd = bayes_mvs(deltas)
# drop a line in at the mean for fun
plt.axvline(dmean[0], color='blue', alpha=0.5)
plt.axvspan(dmean[1][0], dmean[1][1], color='blue', alpha=0.5)
plt.axvline(np.median(deltas), color='y', alpha=0.5)
# Caclulate a Kernel Density Estimate
density = gaussian_kde(deltas)
xs = np.arange(0., np.max(deltas), 0.1)
density.covariance_factor = lambda: .25
density._compute_covariance()
plt.plot(xs, density(xs), color='m')
#FIXME: come up with better legend names
#plt.legend(('Normal Curve', 'Mean', 'Median', 'KDE'))
plt.legend(('Mean', 'Median', 'KDE'))
plt.xlabel('Submit Times (in Seconds)')
plt.ylabel('Probability')
plt.title('Histogram of Worker submit times')
plt.grid(True)
plt.show()
ax1 = plt.gcf().add_subplot(1,1,1)
ax1.plot(times,s,'r',label = 'True Sate')
#m = np.average(particles,weights=weights,axis=1)
#st = np.std(particles,weights=weights,axis=1)
#ext = (0.0,dt*timewindow,code.neurons[-1].theta,code.neurons[0].theta)
#plt.imshow(rates.T,extent=ext,cmap = cm.gist_yarg,aspect = 'auto',interpolation ='nearest')
thetas = [code.neurons[i].theta for i in sptrain]
ax1.plot(times[sptimes],thetas,'yo',label='Observed Spikes')
ax1.plot(times,m,'b',label='Posterior Mean')
ax1.plot(times,m-st,'gray',times,m+st,'gray')
#ax2 = plt.gcf().add_subplot(1,2,2)
#ax2.plot(times,s)
plt.xlabel('Time (in seconds)')
plt.ylabel('Space (in cm)')
plt.legend()
plt.title('State Estimation in a Diffusion System')
if plotting:
#matplotlib.rcParams['font.size']=10
if gaussian:
fig, (ax1,ax2) = ppl.subplots(1,2,figsize = (12,6))
else:
fig, ax2 = ppl.subplots(1)
times = np.arange(0.0,dt*timewindow,dt)
if gaussian:
if sum(sum(spsg)) !=0:
plt.plot(X, Y, label='iSVD u={}'.format(num))
"""
print 'Testing raw SVD => exact reconstruction'
svT = scipy.linalg.diagsvd(s, u.shape[0], vT.shape[1]).dot(vT)
for y in xrange(train.shape[0]):
for x in xrange(train.shape[1]):
colU = u[y, :]
rowV = svT[:, x]
assert np.allclose(train[y, x], single_dot(u, svT, x, y))
"""
##
plt.title('SVD reconstruction error on {}x{} matrix'.format(*train.shape))
plt.xlabel('Low rank approximation (k)')
plt.ylabel('Frobenius norm')
plt.ylim(0, max(svdY))
plt.legend(loc='best')
plt.savefig('reconstruct_fro_{}x{}.pdf'.format(*train.shape))
plt.show(block=True)
##
plt.plot(orthoX,
orthoY,
label="SVD",
color='black',
linewidth=2,
linestyle='--')
for label, X, Y in incr_ortho:
plt.plot(X, Y, label=label)
plt.title('SVD orthogonality error on {}x{} matrix'.format(*train.shape))
plt.xlabel('Low rank approximation (k)')
plt.ylabel('Deviation from orthogonality')
plt.semilogy()
rerr = sum(abs(approxG.node[n]['pageviews'] - G.node[n]['pageviews']) / (G.node[n]['pageviews'] + 1) for n in G.nodes()) / G.number_of_nodes()
np.random.shuffle(nodes)
print 'Pageviews from "real" edge weights'
print '-=-=-=-=-'
display_graph(G)
print
print 'Pageviews from evenly distributed edge weights'
print '-=-=-=-=-'
display_graph(approxG)
plt.plot(np.arange(0, len(rerrs)), rerrs, label='Relative error over time')
plt.xlabel('Iteration')
plt.ylabel('Average pageview relative error per node')
plt.legend()
plt.savefig('error_over_time.pdf')
plt.show(block=True)
plt.plot(np.arange(0, len(werrs)), werrs, label='Weight error over time')
plt.xlabel('Iteration')
plt.ylabel('Average weight error per edge')
plt.legend()
plt.savefig('weight_over_time.pdf')
plt.show(block=True)
fig, ax = plt.subplots(1)
ppl.bar(ax, *orig_weight_data, alpha=0.5, color='black', label='Weight error before')
ppl.bar(ax, np.arange(0, G.number_of_edges()), [abs(G[u][v]['weight'] - approxG[u][v]['weight']) for u, v in G.edges()], alpha=0.8, label='Weight error after')
#plt.ylim(-1, 1)
plt.legend(loc='best')