def _parseDef(self, id):
self._analysisParts = []
self._statClassList = []
# ([^-[]* #pure text - not '['
#print 'NOWAG id:', id
parts = re.findall('''
# Match pure text (part[0]):
( (?: [^-[]* (?:-(?!>))? )* #1. pure text - not '[' or '-',
#2. separated by a possible '-' that is not before a '>'
#1 and 2 is repeated as long as necessary
[^-[\s]+) #should not end with whitespace,
#as this may belong to the '->'-expression
# Match option clause (part[1])
|( \[ [^[\]]* \] ) #Matches an expression inside brackets '[]'
# Match specification of statistic classes (part[2])
|( \s? \-> \s? .* )
# Match any additional whitespace (part[3])
|(\s*)
''',
id,
flags=re.VERBOSE)
from gold.statistic.AllStatistics import STAT_CLASS_DICT
for part in parts:
if part[0] != '':
self._analysisParts.append(part[0])
if part[1] != '':
self._analysisParts.append(AnalysisOption(part[1]))
if part[2] != '':
statNames = part[2].replace('->', '').replace(' ',
'').split(',')
#self._statClassList = statNames
self._statClassList = [STAT_CLASS_DICT[statName] for statName in statNames \
if STAT_CLASS_DICT.get(statName) is not None]
if len(self._statClassList) == 0:
if len(statNames) == 0:
logMessage(
'No statistic found when parsing analysisDef: ' +
self._analysisLine)
else:
logMessage(
'Specified statistics not found in STAT_CLASS_DICT. Statistics:%s, and keys in STAT_CLASS_DICT: %s'
% (str(statNames), str(STAT_CLASS_DICT)))
if part[3] != '':
self._analysisParts.append(part[3])
def _parseDef(self, id):
self._analysisParts = []
self._statClassList = []
# ([^-[]* #pure text - not '['
#print 'NOWAG id:', id
parts = re.findall('''
# Match pure text (part[0]):
( (?: [^-[]* (?:-(?!>))? )* #1. pure text - not '[' or '-',
#2. separated by a possible '-' that is not before a '>'
#1 and 2 is repeated as long as necessary
[^-[\s]+) #should not end with whitespace,
#as this may belong to the '->'-expression
# Match option clause (part[1])
|( \[ [^[\]]* \] ) #Matches an expression inside brackets '[]'
# Match specification of statistic classes (part[2])
|( \s? \-> \s? .* )
# Match any additional whitespace (part[3])
|(\s*)
''', id, flags=re.VERBOSE)
from gold.statistic.AllStatistics import STAT_CLASS_DICT
for part in parts:
if part[0] != '':
self._analysisParts.append(part[0])
if part[1] != '':
self._analysisParts.append(AnalysisOption(part[1]))
if part[2] != '':
statNames = part[2].replace('->','').replace(' ','').split(',')
#self._statClassList = statNames
self._statClassList = [STAT_CLASS_DICT[statName] for statName in statNames \
if STAT_CLASS_DICT.get(statName) is not None]
if len(self._statClassList)==0:
if len(statNames)==0:
logMessage('No statistic found when parsing analysisDef: ' + self._analysisLine)
else:
logMessage('Specified statistics not found in STAT_CLASS_DICT. Statistics:%s, and keys in STAT_CLASS_DICT: %s' % (str(statNames), str(STAT_CLASS_DICT)) )
if part[3] != '':
self._analysisParts.append(part[3])
def getOptionsBoxStatistic():
return sorted(STAT_CLASS_DICT.keys())
# except Exception,e:
# try:
# _getStatResDict2(track1_Num, track2_Num,a)
# except Exception,e:
# try:
# _getStatResDict2(track1, track2_Num,a)
# except Exception,e:
# print e.__class__, e, traceback.format_exc()
# pass
#print [ k + ' = ' + resultInfoDict[k] + os.linesep \
# for k in sorted(resultInfoDict)]
#import sys
#sys.exit()
statClassList = STAT_CLASS_DICT.values()
for statClass in statClassList:
print statClass
try:
_getStatResDict(track1, track2)
except Exception,e:
try:
_getStatResDict(track1_Num, track2_Num)
except Exception,e:
try:
_getStatResDict(track1, track2_Num)
except Exception,e:
print statClass.__name__ + ': ',e.__class__, e
pass
#from gold.statistic.AllStatistics import STAT_CLASS_DICT
#from gold.application.StatRunner import StatRunner
#from test.gold.track.common.SampleTrack import SampleTrack
#from test.gold.track.common.SampleTrackView import SampleTV, SampleTV_Num
#from gold.track.GenomeRegion import GenomeRegion
from gold.description.AnalysisManager import AnalysisManager
from gold.statistic.AllStatistics import STAT_CLASS_DICT
#class GenerateDefaultAnalysiss:
#def _getSampleTrack(numbers = False):
# if numbers:
# return SampleTrack( SampleTV_Num(numElements=50), True )
# else:
# return SampleTrack( SampleTV(starts=True, ends=True, vals=True, numElements=50), True )
#stats = StatOptions().getStats(_getSampleTrack(), _getSampleTrack() )
stats = STAT_CLASS_DICT.values()
uncoveredStats = [
stat.__name__ for stat in stats
if not (True in [(stat in a.getAllStats())
for a in AnalysisManager.getAllAnalyses()])
]
for stat in uncoveredStats:
print 'Data inspection: ' + stat + ' -> ' + stat
#for statClass in STAT_CLASS_DICT.values():
# try:
# StatRunner.run([GenomeRegion('hg18', 'chr1', 0, 1)], track1, track2, statClass)
# except:
# pass
# except Exception,e:
# try:
# _getStatResDict2(track1_Num, track2_Num,a)
# except Exception,e:
# try:
# _getStatResDict2(track1, track2_Num,a)
# except Exception,e:
# print e.__class__, e, traceback.format_exc()
# pass
#print [ k + ' = ' + resultInfoDict[k] + os.linesep \
# for k in sorted(resultInfoDict)]
#import sys
#sys.exit()
statClassList = STAT_CLASS_DICT.values()
for statClass in statClassList:
print statClass
try:
_getStatResDict(track1, track2)
except Exception,e:
try:
_getStatResDict(track1_Num, track2_Num)
except Exception,e:
try:
_getStatResDict(track1, track2_Num)
except Exception,e:
print statClass.__name__ + ': ',e.__class__, e
pass
def getOptionsBoxStatistic():
return sorted(STAT_CLASS_DICT.keys())