def score_objects(properties, ts, gt, nRules, filter_name=None, group='Image',
show_results=False, results_table=None, overwrite=False):
'''
Trains a Classifier on a training set and scores the experiment
returns the table of scores as a numpy array.
properties -- Properties instance
ts -- TrainingSet instance
gt -- Ground Truth instance
nRules -- number of rules to use
filter_name -- name of a filter to use from the properties file
group -- name of a group to use from the properties file
show_results -- whether or not to show the results in TableViewer
results_table -- table name to save results to or None.
'''
p = properties
#db = DBConnect.getInstance() ## Removed writing to db. Results_table should be 'None' anyway
dm = DataModel.getInstance()
#if group == None:
#group = 'Image'
if results_table:
if db.table_exists(results_table) and not overwrite:
print 'Table "%s" already exists. Delete this table before running scoreall.'%(results_table)
return None
print ''
print 'properties: ', properties
print 'initial training set: ', ts
print 'ground truth training set: ', gt
print '# rules: ', nRules
print 'filter: ', filter_name
print 'grouping by: ', group
print 'show results: ', show_results
print 'results table: ', results_table
print 'overwrite: ', overwrite
print ''
nClasses = len(ts.labels)
nKeyCols = len(image_key_columns())
assert 200 > nRules > 0, '# of rules must be between 1 and 200. Value was %s'%(nRules,)
assert filter_name in p._filters.keys()+[None], 'Filter %s not found in properties file. Valid filters are: %s'%(filter_name, ','.join(p._filters.keys()),)
assert group in p._groups.keys()+['Image', 'None'], 'Group %s not found in properties file. Valid groups are: %s'%(group, ','.join(p._groups.keys()),)
output = StringIO()
logging.info('Training classifier with %s rules...'%nRules)
t0 = time()
weaklearners = fastgentleboostingmulticlass.train(ts.colnames,
nRules, ts.label_matrix,
ts.values, output)
logging.info('Training done in %f seconds'%(time()-t0))
t0 = time()
#def update(frac):
#logging.info('%d%% '%(frac*100.,))
## Score Ground Truth using established classifier
gt_predicted_scores = per_cell_scores(weaklearners, gt.values, gt.colnames)
#plt.hist(gt_predicted_scores)
#plt.show()
gt_predicted_signs = np.sign(gt_predicted_scores)
## Compare Ground Truth score signs with the actual ground truth values
numclasses = ts.labels.size
gt_actual_signs = gt.label_matrix[:,0]
cm_unrotated = metrics.confusion_matrix(gt_actual_signs,gt_predicted_signs)
## sklearn.metrics.confusion_matrix -- 2D confusion matrix is inverted from convention.
## https://github.com/scikit-learn/scikit-learn/issues/1664
cm = np.rot90(np.rot90(cm_unrotated))
fpr, sens, thresholds = metrics.roc_curve(gt_actual_signs,gt_predicted_signs)
spec = 1-fpr
s = np.sum(cm,axis=1)
percent = [100*cm[i,i]/float(s[i]) for i in range(len(s))]
avg = np.mean(percent)
avgTotal = 100 * np.trace(cm) / float(np.sum(cm))
print 'accuracy = %f' % avgTotal
print 'Confusion Matrix = ... '
print cm
my_sens = cm[0,0] / float(cm[0,0] + cm[0,1]) #TP/(TP+FN)
my_spec = cm[1,1] / float(cm[1,1] + cm[1,0]) #TN/(TN+FP)
print 'My_Sensitivity = %f' % my_sens
print 'My_Specificity = %f' % my_spec
print 'Sensitivity = ...'
print sens
print 'Specificity = ...'
print spec
print 'Done calculating'
############
## Confusion Matrix code from here: http://stackoverflow.com/questions/5821125/how-to-plot-confusion-matrix-with-string-axis-rather-than-integer-in-python
conf_arr = cm
norm_conf = []
## This normalizes each *row* to the color map, but I chose to normalize the whole confusion matrix to the same scale
##for i in conf_arr:
##a = 0
##tmp_arr = []
##a = sum(i, 0)
##for j in i:
##tmp_arr.append(float(j)/float(a))
##norm_conf.append(tmp_arr)
norm_conf = conf_arr / float(np.max(conf_arr))
if DISPLAY_CONFUSION_MATRIX:
fig = plt.figure()
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(np.array(norm_conf), cmap=plt.cm.jet,
interpolation='nearest')
width = len(conf_arr)
height = len(conf_arr[0])
for x in xrange(width):
for y in xrange(height):
ax.annotate(str(conf_arr[x][y]), xy=(y, x),
horizontalalignment='center',
verticalalignment='center')
cb = fig.colorbar(res)
#cb.set_cmap = [0,1]
if width == 2 and height == 2:
plt.xticks([0,1],['FP','TN'])
plt.yticks([0,1],['TP','FP'])
else:
alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
plt.xticks(range(width), alphabet[:width])
plt.yticks(range(height), alphabet[:height])
plt.show()
print 'Done'
def score(properties,
ts,
nRules,
filter_name=None,
group='Image',
show_results=False,
results_table=None,
overwrite=False):
'''
Trains a Classifier on a training set and scores the experiment
returns the table of scores as a numpy array.
properties -- Properties instance
ts -- TrainingSet instance
nRules -- number of rules to use
filter_name -- name of a filter to use from the properties file
group -- name of a group to use from the properties file
show_results -- whether or not to show the results in TableViewer
results_table -- table name to save results to or None.
'''
p = properties
db = DBConnect.getInstance()
dm = DataModel.getInstance()
if group == None:
group = 'Image'
if results_table:
if db.table_exists(results_table) and not overwrite:
print 'Table "%s" already exists. Delete this table before running scoreall.' % (
results_table)
return None
print ''
print 'properties: ', properties
print 'training set: ', ts
print '# rules: ', nRules
print 'filter: ', filter_name
print 'grouping by: ', group
print 'show results: ', show_results
print 'results table: ', results_table
print 'overwrite: ', overwrite
print ''
nClasses = len(ts.labels)
nKeyCols = len(image_key_columns())
assert 200 > nRules > 0, '# of rules must be between 1 and 200. Value was %s' % (
nRules, )
assert filter_name in p._filters.keys() + [
None
], 'Filter %s not found in properties file. Valid filters are: %s' % (
filter_name,
','.join(p._filters.keys()),
)
assert group in p._groups.keys() + [
'Image'
], 'Group %s not found in properties file. Valid groups are: %s' % (
group,
','.join(p._groups.keys()),
)
output = StringIO()
logging.info('Training classifier with %s rules...' % nRules)
t0 = time()
weaklearners = fastgentleboostingmulticlass.train(ts.colnames, nRules,
ts.label_matrix,
ts.values, output)
logging.info('Training done in %f seconds' % (time() - t0))
logging.info('Computing per-image class counts...')
t0 = time()
def update(frac):
logging.info('%d%% ' % (frac * 100., ))
keysAndCounts = multiclasssql.PerImageCounts(weaklearners,
filter_name=(filter_name
or None),
cb=update)
keysAndCounts.sort()
logging.info('Counts found in %f seconds' % (time() - t0))
if not keysAndCounts:
logging.error(
'No images are in filter "%s". Please check the filter definition in your properties file.'
% (filter_name))
raise Exception(
'No images are in filter "%s". Please check the filter definition in your properties file.'
% (filter_name))
# AGGREGATE PER_IMAGE COUNTS TO GROUPS IF NOT GROUPING BY IMAGE
if group != 'Image':
logging.info('Grouping %s counts by %s...' % (p.object_name[0], group))
t0 = time()
imData = {}
for row in keysAndCounts:
key = tuple(row[:nKeyCols])
imData[key] = np.array([float(v) for v in row[nKeyCols:]])
groupedKeysAndCounts = np.array([
list(k) + vals.tolist()
for k, vals in dm.SumToGroup(imData, group).items()
],
dtype=object)
nKeyCols = len(dm.GetGroupColumnNames(group))
logging.info('Grouping done in %f seconds' % (time() - t0))
else:
groupedKeysAndCounts = np.array(keysAndCounts, dtype=object)
# FIT THE BETA BINOMIAL
logging.info('Fitting beta binomial distribution to data...')
counts = groupedKeysAndCounts[:, -nClasses:]
alpha, converged = polyafit.fit_betabinom_minka_alternating(counts)
logging.info(' alpha = %s converged = %s' % (alpha, converged))
logging.info(' alpha/Sum(alpha) = %s' % ([a / sum(alpha)
for a in alpha]))
# CONSTRUCT ARRAY OF TABLE DATA
logging.info('Computing enrichment scores for each group...')
t0 = time()
tableData = []
for i, row in enumerate(groupedKeysAndCounts):
# Start this row with the group key:
tableRow = list(row[:nKeyCols])
if group != 'Image':
tableRow += [
len(dm.GetImagesInGroup(group, tuple(row[:nKeyCols])))
]
# Append the counts:
countsRow = [int(v) for v in row[nKeyCols:nKeyCols + nClasses]]
tableRow += [sum(countsRow)]
tableRow += countsRow
if p.area_scoring_column is not None:
# Append the areas
countsRow = [int(v) for v in row[-nClasses:]]
tableRow += [sum(countsRow)]
tableRow += countsRow
# Append the scores:
# compute enrichment probabilities of each class for this image OR group
scores = np.array(dirichletintegrate.score(alpha, np.array(countsRow)))
# clamp to [0,1] to
scores[scores > 1.] = 1.
scores[scores < 0.] = 0.
tableRow += scores.tolist()
# Append the logit scores:
# Special case: only calculate logit of "positives" for 2-classes
if nClasses == 2:
tableRow += [np.log10(scores[0]) - (np.log10(1 - scores[0]))
] # compute logit of each probability
else:
tableRow += [
np.log10(score) - (np.log10(1 - score)) for score in scores
] # compute logit of each probability
tableData.append(tableRow)
tableData = np.array(tableData, dtype=object)
logging.info('Enrichments computed in %f seconds' % (time() - t0))
# CREATE COLUMN LABELS LIST
# if grouping isn't per-image, then get the group key column names.
if group != 'Image':
colnames = dm.GetGroupColumnNames(group)
else:
colnames = list(image_key_columns())
# record the column indices for the keys
key_col_indices = [i for i in range(len(colnames))]
if group != 'Image':
colnames += ['Number_of_Images']
colnames += ['Total_%s_Count' % (p.object_name[0].capitalize())]
for i in xrange(nClasses):
colnames += [
'%s_%s_Count' %
(ts.labels[i].capitalize(), p.object_name[0].capitalize())
]
if p.area_scoring_column is not None:
colnames += ['Total_%s_Area' % (p.object_name[0].capitalize())]
for i in xrange(nClasses):
colnames += [
'%s_%s_Area' %
(ts.labels[i].capitalize(), p.object_name[0].capitalize())
]
for i in xrange(nClasses):
colnames += ['pEnriched_%s' % (ts.labels[i])]
if nClasses == 2:
colnames += ['Enriched_Score_%s' % (ts.labels[0])]
else:
for i in xrange(nClasses):
colnames += ['Enriched_Score_%s' % (ts.labels[i])]
title = results_table or "Enrichments_per_%s" % (group, )
if filter_name:
title += "_filtered_by_%s" % (filter_name, )
title += ' (%s)' % (os.path.split(p._filename)[1])
if results_table:
print 'Creating table %s' % (results_table)
success = db.CreateTableFromData(tableData,
colnames,
results_table,
temporary=False)
if not success:
print 'Failed to create results table :('
if show_results:
import tableviewer
tableview = tableviewer.TableViewer(None, title=title)
if results_table and overwrite:
tableview.load_db_table(results_table)
else:
tableview.table_from_array(tableData, colnames, group,
key_col_indices)
tableview.set_fitted_col_widths()
tableview.Show()
return tableData
ts = '/Users/afraser/Desktop/MyTrainingSet3.txt'
nRules = 5
filter = 'MAPs'
# props = '/Users/afraser/Desktop/2007_10_19_Gilliland_LeukemiaScreens_Validation_v2_AllBatches_DuplicatesFiltered_FullBarcode.properties'
# ts = '/Users/afraser/Desktop/trainingvalidation3d.txt'
# nRules = 50
# filter = 'afraser_test'
p.LoadFile(props)
trainingSet = TrainingSet(p)
trainingSet.Load(ts)
output = StringIO()
print('Training classifier with ' + str(nRules) + ' rules...')
weaklearners = fastgentleboostingmulticlass.train(trainingSet.colnames,
nRules,
trainingSet.label_matrix,
trainingSet.values,
output)
table = PerImageCounts(weaklearners, filter_name=filter)
table.sort()
labels = ['table', 'image'] + list(trainingSet.labels) + list(
trainingSet.labels)
print(labels)
for row in table:
print(row)
# app = wx.PySimpleApp()
# grid = DataGrid(numpy.array(table), labels, key_col_indices=[0,1])
# grid.Show()
# app.MainLoop()
# props = '/Volumes/imaging_analysis/2007_10_19_Gilliland_LeukemiaScreens/Screen3_1Apr09_run3/2007_10_19_Gilliland_LeukemiaScreens_Validation_v2_AllBatches_DuplicatesFiltered_FullBarcode_testSinglePlate.properties'
# ts = '/Volumes/imaging_analysis/2007_10_19_Gilliland_LeukemiaScreens/Screen3_1Apr09_run3/trainingvalidation3b.txt'
props = "../Properties/nirht_area_test.properties"
ts = "/Users/afraser/Desktop/MyTrainingSet3.txt"
nRules = 5
filter = "MAPs"
# props = '/Users/afraser/Desktop/2007_10_19_Gilliland_LeukemiaScreens_Validation_v2_AllBatches_DuplicatesFiltered_FullBarcode.properties'
# ts = '/Users/afraser/Desktop/trainingvalidation3d.txt'
# nRules = 50
# filter = 'afraser_test'
p.LoadFile(props)
trainingSet = TrainingSet(p)
trainingSet.Load(ts)
output = StringIO()
print "Training classifier with " + str(nRules) + " rules..."
weaklearners = fastgentleboostingmulticlass.train(
trainingSet.colnames, nRules, trainingSet.label_matrix, trainingSet.values, output
)
table = PerImageCounts(weaklearners, filter_name=filter)
table.sort()
labels = ["table", "image"] + list(trainingSet.labels) + list(trainingSet.labels)
print labels
for row in table:
print row
# app = wx.PySimpleApp()
# grid = DataGrid(numpy.array(table), labels, key_col_indices=[0,1])
# grid.Show()
# app.MainLoop()
def score_objects(properties,
ts,
gt,
nRules,
filter_name=None,
group='Image',
show_results=False,
results_table=None,
overwrite=False):
'''
Trains a Classifier on a training set and scores the experiment
returns the table of scores as a numpy array.
properties -- Properties instance
ts -- TrainingSet instance
gt -- Ground Truth instance
nRules -- number of rules to use
filter_name -- name of a filter to use from the properties file
group -- name of a group to use from the properties file
show_results -- whether or not to show the results in TableViewer
results_table -- table name to save results to or None.
'''
p = properties
#db = DBConnect.getInstance() ## Removed writing to db. Results_table should be 'None' anyway
dm = DataModel.getInstance()
#if group == None:
#group = 'Image'
if results_table:
if db.table_exists(results_table) and not overwrite:
print 'Table "%s" already exists. Delete this table before running scoreall.' % (
results_table)
return None
print ''
print 'properties: ', properties
print 'initial training set: ', ts
print 'ground truth training set: ', gt
print '# rules: ', nRules
print 'filter: ', filter_name
print 'grouping by: ', group
print 'show results: ', show_results
print 'results table: ', results_table
print 'overwrite: ', overwrite
print ''
nClasses = len(ts.labels)
nKeyCols = len(image_key_columns())
assert 200 > nRules > 0, '# of rules must be between 1 and 200. Value was %s' % (
nRules, )
assert filter_name in p._filters.keys() + [
None
], 'Filter %s not found in properties file. Valid filters are: %s' % (
filter_name,
','.join(p._filters.keys()),
)
assert group in p._groups.keys() + [
'Image', 'None'
], 'Group %s not found in properties file. Valid groups are: %s' % (
group,
','.join(p._groups.keys()),
)
output = StringIO()
logging.info('Training classifier with %s rules...' % nRules)
t0 = time()
weaklearners = fastgentleboostingmulticlass.train(ts.colnames, nRules,
ts.label_matrix,
ts.values, output)
logging.info('Training done in %f seconds' % (time() - t0))
t0 = time()
#def update(frac):
#logging.info('%d%% '%(frac*100.,))
## Score Ground Truth using established classifier
gt_predicted_scores = per_cell_scores(weaklearners, gt.values, gt.colnames)
#plt.hist(gt_predicted_scores)
#plt.show()
gt_predicted_signs = np.sign(gt_predicted_scores)
## Compare Ground Truth score signs with the actual ground truth values
numclasses = ts.labels.size
gt_actual_signs = gt.label_matrix[:, 0]
cm_unrotated = metrics.confusion_matrix(gt_actual_signs,
gt_predicted_signs)
## sklearn.metrics.confusion_matrix -- 2D confusion matrix is inverted from convention.
## https://github.com/scikit-learn/scikit-learn/issues/1664
cm = np.rot90(np.rot90(cm_unrotated))
fpr, sens, thresholds = metrics.roc_curve(gt_actual_signs,
gt_predicted_signs)
spec = 1 - fpr
s = np.sum(cm, axis=1)
percent = [100 * cm[i, i] / float(s[i]) for i in range(len(s))]
avg = np.mean(percent)
avgTotal = 100 * np.trace(cm) / float(np.sum(cm))
print 'accuracy = %f' % avgTotal
print 'Confusion Matrix = ... '
print cm
my_sens = cm[0, 0] / float(cm[0, 0] + cm[0, 1]) #TP/(TP+FN)
my_spec = cm[1, 1] / float(cm[1, 1] + cm[1, 0]) #TN/(TN+FP)
print 'My_Sensitivity = %f' % my_sens
print 'My_Specificity = %f' % my_spec
print 'Sensitivity = ...'
print sens
print 'Specificity = ...'
print spec
print 'Done calculating'
############
## Confusion Matrix code from here: http://stackoverflow.com/questions/5821125/how-to-plot-confusion-matrix-with-string-axis-rather-than-integer-in-python
conf_arr = cm
norm_conf = []
## This normalizes each *row* to the color map, but I chose to normalize the whole confusion matrix to the same scale
##for i in conf_arr:
##a = 0
##tmp_arr = []
##a = sum(i, 0)
##for j in i:
##tmp_arr.append(float(j)/float(a))
##norm_conf.append(tmp_arr)
norm_conf = conf_arr / float(np.max(conf_arr))
if DISPLAY_CONFUSION_MATRIX:
fig = plt.figure()
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(np.array(norm_conf),
cmap=plt.cm.jet,
interpolation='nearest')
width = len(conf_arr)
height = len(conf_arr[0])
for x in xrange(width):
for y in xrange(height):
ax.annotate(str(conf_arr[x][y]),
xy=(y, x),
horizontalalignment='center',
verticalalignment='center')
cb = fig.colorbar(res)
#cb.set_cmap = [0,1]
if width == 2 and height == 2:
plt.xticks([0, 1], ['FP', 'TN'])
plt.yticks([0, 1], ['TP', 'FP'])
else:
alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
plt.xticks(range(width), alphabet[:width])
plt.yticks(range(height), alphabet[:height])
plt.show()
print 'Done'
def score(properties, ts, nRules, filter_name=None, group='Image',
show_results=False, results_table=None, overwrite=False):
'''
Trains a Classifier on a training set and scores the experiment
returns the table of scores as a numpy array.
properties -- Properties instance
ts -- TrainingSet instance
nRules -- number of rules to use
filter_name -- name of a filter to use from the properties file
group -- name of a group to use from the properties file
show_results -- whether or not to show the results in TableViewer
results_table -- table name to save results to or None.
'''
p = properties
db = DBConnect.getInstance()
dm = DataModel.getInstance()
if group == None:
group = 'Image'
if results_table:
if db.table_exists(results_table) and not overwrite:
print 'Table "%s" already exists. Delete this table before running scoreall.'%(results_table)
return None
print ''
print 'properties: ', properties
print 'training set: ', ts
print '# rules: ', nRules
print 'filter: ', filter_name
print 'grouping by: ', group
print 'show results: ', show_results
print 'results table: ', results_table
print 'overwrite: ', overwrite
print ''
nClasses = len(ts.labels)
nKeyCols = len(image_key_columns())
assert 200 > nRules > 0, '# of rules must be between 1 and 200. Value was %s'%(nRules,)
assert filter_name in p._filters.keys()+[None], 'Filter %s not found in properties file. Valid filters are: %s'%(filter_name, ','.join(p._filters.keys()),)
assert group in p._groups.keys()+['Image'], 'Group %s not found in properties file. Valid groups are: %s'%(group, ','.join(p._groups.keys()),)
output = StringIO()
logging.info('Training classifier with %s rules...'%nRules)
t0 = time()
weaklearners = fastgentleboostingmulticlass.train(ts.colnames,
nRules, ts.label_matrix,
ts.values, output)
logging.info('Training done in %f seconds'%(time()-t0))
logging.info('Computing per-image class counts...')
t0 = time()
def update(frac):
logging.info('%d%% '%(frac*100.,))
keysAndCounts = multiclasssql.PerImageCounts(weaklearners, filter_name=(filter_name or None), cb=update)
keysAndCounts.sort()
logging.info('Counts found in %f seconds'%(time()-t0))
if not keysAndCounts:
logging.error('No images are in filter "%s". Please check the filter definition in your properties file.'%(filter_name))
raise Exception('No images are in filter "%s". Please check the filter definition in your properties file.'%(filter_name))
# AGGREGATE PER_IMAGE COUNTS TO GROUPS IF NOT GROUPING BY IMAGE
if group != 'Image':
logging.info('Grouping %s counts by %s...' % (p.object_name[0], group))
t0 = time()
imData = {}
for row in keysAndCounts:
key = tuple(row[:nKeyCols])
imData[key] = np.array([float(v) for v in row[nKeyCols:]])
groupedKeysAndCounts = np.array([list(k)+vals.tolist() for k, vals in dm.SumToGroup(imData, group).items()], dtype=object)
nKeyCols = len(dm.GetGroupColumnNames(group))
logging.info('Grouping done in %f seconds'%(time()-t0))
else:
groupedKeysAndCounts = np.array(keysAndCounts, dtype=object)
# FIT THE BETA BINOMIAL
logging.info('Fitting beta binomial distribution to data...')
counts = groupedKeysAndCounts[:,-nClasses:]
alpha, converged = polyafit.fit_betabinom_minka_alternating(counts)
logging.info(' alpha = %s converged = %s'%(alpha, converged))
logging.info(' alpha/Sum(alpha) = %s'%([a/sum(alpha) for a in alpha]))
# CONSTRUCT ARRAY OF TABLE DATA
logging.info('Computing enrichment scores for each group...')
t0 = time()
tableData = []
for i, row in enumerate(groupedKeysAndCounts):
# Start this row with the group key:
tableRow = list(row[:nKeyCols])
if group != 'Image':
tableRow += [len(dm.GetImagesInGroup(group, tuple(row[:nKeyCols])))]
# Append the counts:
countsRow = [int(v) for v in row[nKeyCols:nKeyCols+nClasses]]
tableRow += [sum(countsRow)]
tableRow += countsRow
if p.area_scoring_column is not None:
# Append the areas
countsRow = [int(v) for v in row[-nClasses:]]
tableRow += [sum(countsRow)]
tableRow += countsRow
# Append the scores:
# compute enrichment probabilities of each class for this image OR group
scores = np.array( dirichletintegrate.score(alpha, np.array(countsRow)) )
# clamp to [0,1] to
scores[scores>1.] = 1.
scores[scores<0.] = 0.
tableRow += scores.tolist()
# Append the logit scores:
# Special case: only calculate logit of "positives" for 2-classes
if nClasses==2:
tableRow += [np.log10(scores[0])-(np.log10(1-scores[0]))] # compute logit of each probability
else:
tableRow += [np.log10(score)-(np.log10(1-score)) for score in scores] # compute logit of each probability
tableData.append(tableRow)
tableData = np.array(tableData, dtype=object)
logging.info('Enrichments computed in %f seconds'%(time()-t0))
# CREATE COLUMN LABELS LIST
# if grouping isn't per-image, then get the group key column names.
if group != 'Image':
colnames = dm.GetGroupColumnNames(group)
else:
colnames = list(image_key_columns())
# record the column indices for the keys
key_col_indices = [i for i in range(len(colnames))]
if group != 'Image':
colnames += ['Number_of_Images']
colnames += ['Total_%s_Count'%(p.object_name[0].capitalize())]
for i in xrange(nClasses):
colnames += ['%s_%s_Count'%(ts.labels[i].capitalize(), p.object_name[0].capitalize())]
if p.area_scoring_column is not None:
colnames += ['Total_%s_Area'%(p.object_name[0].capitalize())]
for i in xrange(nClasses):
colnames += ['%s_%s_Area'%(ts.labels[i].capitalize(), p.object_name[0].capitalize())]
for i in xrange(nClasses):
colnames += ['pEnriched_%s'%(ts.labels[i])]
if nClasses==2:
colnames += ['Enriched_Score_%s'%(ts.labels[0])]
else:
for i in xrange(nClasses):
colnames += ['Enriched_Score_%s'%(ts.labels[i])]
title = results_table or "Enrichments_per_%s"%(group,)
if filter_name:
title += "_filtered_by_%s"%(filter_name,)
title += ' (%s)'%(os.path.split(p._filename)[1])
if results_table:
print 'Creating table %s'%(results_table)
success = db.CreateTableFromData(tableData, colnames, results_table, temporary=False)
if not success:
print 'Failed to create results table :('
if show_results:
import tableviewer
tableview = tableviewer.TableViewer(None, title=title)
if results_table and overwrite:
tableview.load_db_table(results_table)
else:
tableview.table_from_array(tableData, colnames, group, key_col_indices)
tableview.set_fitted_col_widths()
tableview.Show()
return tableData
