def topic_distribution(name = None, study = None, order = None, **options):
'''Given a model p_z,p_w_z,p_d_z, we can plot the document's distribution
using p(z|d) = normalized((p(d|z)*p(z))) '''
m = microbplsa.MicrobPLSA()
m.open_model(name = name, study = study, **options) #get model from the results file
#return document's distribution
p_z_d = m.model.document_topics()
Z,N =p_z_d.shape #number of samples
if order is not None:
p_z_d = p_z_d[:,order]
n = np.arange(N)
width = 25.0/float(N) #scale width of bars by number of samples
p = [] #list of plots
colors = plt.cm.rainbow(np.linspace(0, 1, Z))
Lab = Labelling(m, ignore_continuous = False)
Lab.metadata(non_labels = ['BarcodeSequence'])
R = Lab.correlate()
labels_r = Lab.assignlabels(R,num_labels = 1)
labels, r = zip(*labels_r)
labels = [l.replace('(','\n(') for l in labels]
#sort and organize labels and topics so they are always plotted in the same order
labelsUnsorted = zipper(labels,range(0,Z))
labelsUnsorted.sort()
labels, Zrange = zip(*labelsUnsorted)
Zrange = list(Zrange)
p.append(plt.bar(n, p_z_d[Zrange[0],:], width, color=colors[0], linewidth = 0))
height = p_z_d[Zrange[0],:]
for i,z in enumerate(Zrange[1:]):
p.append(plt.bar(n, p_z_d[z,:], width, color=colors[i+1], bottom=height, linewidth = 0))
height += p_z_d[z,:]
plt.ylabel('Probability P(z|d)')
plt.xlabel('Sample')
plt.title('Sample\'s topic distribution')
#plt.xticks(np.arange(0,width/2.0,N*width), ['S'+str(n) for n in range(1,N)])
topiclegend = ['Topic' + str(Zrange[labels.index(l)]+1) + ': '+ l + '\n ('+ str(r[Zrange[labels.index(l)]]) + ')' for l in labels]
fontP = FontProperties()
if N >60:
fontP.set_size('xx-small')
else: fontP.set_size('small')
ax = plt.subplot(111)
ratio = float(N)*0.5
ax.set_aspect(ratio)
ax.tick_params(axis = 'x', colors='w') #remove tick labels by setting them the same color as background
box = ax.get_position()
ax.set_position([box.x0, box.y0, 0.5, box.height])
if order is not None:
plt.xticks(n, order, size = 'xx-small')
if Z > 12:
columns = 2
else: columns = 1
plt.legend(p, topiclegend, prop = fontP, title = 'Topic Label', loc='center left', bbox_to_anchor=(1, 0.5), ncol = columns)
return plt
def makePCA(datafile, num_components):
m = microbplsa.MicrobPLSA()
m.open_data(datafile = dataFile) #get data of OTU abundances per sample
X = m.datamatrix.T
plsa = m.open_model(modelFile = resultfile) #get model from the results file
#return document's distribution
p_d_z = plsa.p_d_z
N,Z =p_d_z.shape
#get topic labels
if MANUAL_LABELS:
labels = MANUAL_LABELS
else:
Lab = Labelling(study, Z, ignore_continuous = False)
Lab.metadata(non_labels = ['BarcodeSequence'])
R = Lab.correlate()
labels_r = Lab.assignlabels(R,num_labels = 1)
labels, r = zip(*labels_r)
labels = [l.replace('(','\n(') for l in labels]
#get primary topic per sample
topics = []
for i, row in enumerate(p_d_z):
max_topic_index = np.argmax(row)
topics.append(max_topic_index)
topics = np.array(topics)
pca = PCA(n_components=num_components, whiten = True)
pca.fit(X)
X_r = pca.fit(X).transform(X)
# Percentage of variance explained for each components
print('Explained variance ratio (first two components): %s'
% str(pca.explained_variance_ratio_))
#initiate plot and colors
colors = [float(c)/float(Z) for c in range(0,Z)]
colors = plt.cm.rainbow(np.linspace(0, 1, Z))
fig = plt.figure(1, figsize=(4, 3))
plt.clf()
ax = plt.subplot(111, projection ='3d')
if num_components == 2:
for c, i, l in zip(colors, range(0,Z), labels):
ax.plot(X_r[topics == i, 0], X_r[topics == i, 1], 'o', color=c, label=l)
box = ax.get_position()
ax.set_position([box.x0, box.y0, 0.5, box.height])
elif num_components == 3:
for c, i, l in zip(colors, range(0,Z), labels):
ax.plot(X_r[topics == i, 0], X_r[topics == i, 1], X_r[topics == i, 2], 'o', color=c, label=l)
fontP = FontProperties()
if Z > 12:
columns = 2
else: columns = 1
box = ax.get_position()
ax.set_position([box.x0, box.y0, 0.5, box.height])
plt.legend(prop = fontP, loc='center left', bbox_to_anchor=(1, 0.5), ncol = columns)
plt.title('PCA of Study %s with Z=%s' %(study, str(z)))
plt.show()
return None
'''
Created on 22/01/2014
author: sperez8
Shows how to use Labelling class
'''
from labelling import Labelling
study = '1526'
simple = False
for Z in range(2,39):
Lab = Labelling(study, Z, debug = False,ignore_continuous = False, adjusted_metadata = True)
if simple:
labels = Lab.getlabels()
else:
Lab.metadata(non_labels = ['BarcodeSequence'])
m = list(Lab.metadatamatrix[:,7])
transf = {'DRY':1, "SAFE":2, "DIPPING":3, "UNDER_ISH":4}
M = [transf[n] for n in m]
print M
if 5 in M: print "DDJDJD "
import sys
sys.exit()
sys.exit()
R = Lab.correlate()
labels = Lab.assignlabels(R,num_labels = 8)
Lab.save_labels(labels)
f = '/Users/sperez/git/microbPLSA/MicrobProcessor/Results/study_' + study + '_' + str(
z) + '_topics_.txt'
datafile = '/Users/sperez/Documents/PLSAfun/EMPL data/study_' + study + '_split_library_seqs_and_mapping/study_' + study + '_closed_reference_otu_table.biom'
m = microbplsa.MicrobPLSA()
plsa = m.open_model(f) #get model from the results file
p_z_d = plsa.document_topics() #return document's distribution
Z, N = p_z_d.shape #number of samples
Lab = Labelling(study, Z, ignore_continuous=False,
adjusted_metadata=True) #get labels!
x, y, z = Lab.metadata(non_labels=[])
print y
R = Lab.correlate()
labels_r = Lab.assignlabels(R, num_labels=1)
print labels_r
oldlabels, r = zip(*labels_r)
goodlabels = []
for lab, r in labels_r:
if r > CORRELATION_THRESHOLD or r < -CORRELATION_THRESHOLD:
goodlabels.append(lab)
print("Only %i/%i passed the correlation threshold of %1.1f" %
(len(goodlabels), len(oldlabels), CORRELATION_THRESHOLD))
labels = [replace(l, ' (', '_') for l in oldlabels]
labels = [replace(l, ' ', '_') for l in labels]
labels = [replace(l, ')', '') for l in labels]
labels = [replace(l, ':', '_') for l in labels]
labels = [replace(l, '.', '_') for l in labels]
labels = [replace(l, '-', '_') for l in labels]
def makePCA(datafile, num_components):
m = microbplsa.MicrobPLSA()
m.open_data(datafile=dataFile) #get data of OTU abundances per sample
X = m.datamatrix.T
plsa = m.open_model(modelFile=resultfile) #get model from the results file
#return document's distribution
p_d_z = plsa.p_d_z
N, Z = p_d_z.shape
#get topic labels
if MANUAL_LABELS:
labels = MANUAL_LABELS
else:
Lab = Labelling(study, Z, ignore_continuous=False)
Lab.metadata(non_labels=['BarcodeSequence'])
R = Lab.correlate()
labels_r = Lab.assignlabels(R, num_labels=1)
labels, r = zip(*labels_r)
labels = [l.replace('(', '\n(') for l in labels]
#get primary topic per sample
topics = []
for i, row in enumerate(p_d_z):
max_topic_index = np.argmax(row)
topics.append(max_topic_index)
topics = np.array(topics)
pca = PCA(n_components=num_components, whiten=True)
pca.fit(X)
X_r = pca.fit(X).transform(X)
# Percentage of variance explained for each components
print('Explained variance ratio (first two components): %s' %
str(pca.explained_variance_ratio_))
#initiate plot and colors
colors = [float(c) / float(Z) for c in range(0, Z)]
colors = plt.cm.rainbow(np.linspace(0, 1, Z))
fig = plt.figure(1, figsize=(4, 3))
plt.clf()
ax = plt.subplot(111, projection='3d')
if num_components == 2:
for c, i, l in zip(colors, range(0, Z), labels):
ax.plot(X_r[topics == i, 0],
X_r[topics == i, 1],
'o',
color=c,
label=l)
box = ax.get_position()
ax.set_position([box.x0, box.y0, 0.5, box.height])
elif num_components == 3:
for c, i, l in zip(colors, range(0, Z), labels):
ax.plot(X_r[topics == i, 0],
X_r[topics == i, 1],
X_r[topics == i, 2],
'o',
color=c,
label=l)
fontP = FontProperties()
if Z > 12:
columns = 2
else:
columns = 1
box = ax.get_position()
ax.set_position([box.x0, box.y0, 0.5, box.height])
plt.legend(prop=fontP,
loc='center left',
bbox_to_anchor=(1, 0.5),
ncol=columns)
plt.title('PCA of Study %s with Z=%s' % (study, str(z)))
plt.show()
return None
Z = 8
only_continuous = True
f = '/Users/sperez/git/microbPLSA/MicrobProcessor/Results/study_'+study +'_'
end = '_topics_.txt'
datafile = f+str(Z)+end
format = 'pdf'
Lab = Labelling(study, Z)
metatable, factor_types, factors = Lab.metadata()
R = Lab.correlate()
labels_r = Lab.assignlabels(R)
labels, r = zip(*labels_r)
labels = [l.replace('(','\n(') for l in labels]
m = microbplsa.MicrobPLSA()
plsa = m.open_model(datafile) #get model from the results file
#return document's distribution
p_z_d = plsa.document_topics()
colorlabel = list(metatable[:,1])
if format == 'svg':
import matplotlib
CORRELATION_THRESHOLD = 0.0
pcoordfile = _root_dir +'/D3/pcplots/topics.js'
f = '/Users/sperez/git/microbPLSA/MicrobProcessor/Results/study_'+study +'_'+str(z)+'_topics_.txt'
datafile = '/Users/sperez/Documents/PLSAfun/EMPL data/study_'+study+'_split_library_seqs_and_mapping/study_'+study+'_closed_reference_otu_table.biom'
m = microbplsa.MicrobPLSA()
plsa = m.open_model(f) #get model from the results file
p_z_d = plsa.document_topics() #return document's distribution
Z,N =p_z_d.shape #number of samples
Lab = Labelling(study, Z, ignore_continuous = False, adjusted_metadata = True) #get labels!
x,y,z = Lab.metadata(non_labels = [])
print y
R = Lab.correlate()
labels_r = Lab.assignlabels(R,num_labels = 1)
print labels_r
oldlabels, r = zip(*labels_r)
goodlabels = []
for lab, r in labels_r:
if r > CORRELATION_THRESHOLD or r < -CORRELATION_THRESHOLD:
goodlabels.append(lab)
print ("Only %i/%i passed the correlation threshold of %1.1f"%(len(goodlabels), len(oldlabels), CORRELATION_THRESHOLD))
labels = [replace(l,' (', '_') for l in oldlabels]
labels = [replace(l,' ', '_') for l in labels]
labels = [replace(l,')','') for l in labels]
labels = [replace(l,':', '_') for l in labels]
labels = [replace(l,'.', '_') for l in labels]
labels = [replace(l,'-', '_') for l in labels]
samplenames = Lab.metadatamatrix[:,0]
study = '1526'
Z = 8
only_continuous = True
f = '/Users/sperez/git/microbPLSA/MicrobProcessor/Results/study_' + study + '_'
end = '_topics_.txt'
datafile = f + str(Z) + end
format = 'pdf'
Lab = Labelling(study, Z)
metatable, factor_types, factors = Lab.metadata()
R = Lab.correlate()
labels_r = Lab.assignlabels(R)
labels, r = zip(*labels_r)
labels = [l.replace('(', '\n(') for l in labels]
m = microbplsa.MicrobPLSA()
plsa = m.open_model(datafile) #get model from the results file
#return document's distribution
p_z_d = plsa.document_topics()
colorlabel = list(metatable[:, 1])
if format == 'svg':
import matplotlib
matplotlib.use('SVG')
else: