def _init(self):
if self._standalone is True:
return
# should download files from synapse if required.
self._download_data('D9C1_goldstandard.gct.zip', 'syn4595275')
# now unzip and read the gs on the go
z = ZIP()
z.loadZIPFile(self.get_pathname('D9C1_goldstandard.gct.zip'))
data = z.read('D9C1_goldstandard.gct')
self.goldstandard = pd.read_csv(BytesIO(data), sep='[ \t]',
skiprows=2, engine='python')
self.goldstandard.drop(['Description'], axis=1, inplace=True)
self.goldstandard.set_index('Name', inplace=True)
self.goldstandard.columns = [x.strip() for x in self.goldstandard.columns]
# get template for SC1, SC2, SC3
self._download_data('D9C1_template_sc1.gct.zip', 'syn4595283')
self.unzip('D9C1_template_sc1.gct.zip')
self._download_data('D9C1_template_sc2.zip', 'syn4595587')
self._download_data('D9C1_template_sc3.zip', 'syn4595588')
# download gold standard for sc2
filename = self.getpath_gs( 'D9C1_goldstandard_sc2.txt')
self.gs_priority = pd.read_csv(filename, sep='\t', header=None)
def download_all_data(self):
"""Download all large data sets from Synapse"""
pb = progress_bar(5)
# load the large gold standard file from D5C2 synapse main page
filename = self._download_data('DREAM5_GoldStandard_probes.zip',
'syn2898469')
pb.animate(1)
z = ZIP()
z.loadZIPFile(filename)
data = z.read('Answers.txt')
self.gs = pd.read_csv(StringIO.StringIO(data), sep='\t')
# download 4 other filenames from dreamtools synapse project
self._download_data('all_8mers.txt', 'syn4483185')
pb.animate(2)
self._download_data('8mers_gs.txt', 'syn4483187')
pb.animate(3)
self._download_data('probe35_gs.txt', 'syn4483184')
pb.animate(4)
self._download_data('probes35.txt', 'syn4483183')
pb.animate(5)
def download_all_data(self):
"""Download all large data sets from Synapse"""
pb = progress_bar(5)
# load the large gold standard file from D5C2 synapse main page
filename = self._download_data('DREAM5_GoldStandard_probes.zip',
'syn2898469')
pb.animate(1)
z = ZIP()
z.loadZIPFile(filename)
data = z.read('Answers.txt')
self.gs = pd.read_csv(BytesIO(data), sep='\t')
# download 4 other filenames from dreamtools synapse project
self._download_data('all_8mers.txt', 'syn4483185')
pb.animate(2)
self._download_data('8mers_gs.txt', 'syn4483187')
pb.animate(3)
self._download_data('probe35_gs.txt', 'syn4483184')
pb.animate(4)
self._download_data('probes35.txt', 'syn4483183')
pb.animate(5)
def _score_sc2_sc3(self, filename):
# looks like exactly same function in sc2/sc3
# feature file is not used either in original code ?!
# this should be a zip file with 2 files.
z = ZIP()
z.loadZIPFile(filename)
# there should be 2 files, one ending in gct one in txt
assert len(z.filenames) == 2, "There should be 2 files in the zip archive"
for filename in z.filenames:
if filename.endswith('gct'):
prediction = z.read(filename)
prediction = self._read_gct(prediction)
elif filename.endswith('txt'):
feature = z.read(filename)
feature = self._read_feature(feature)
# first column should be the names
feature.set_index(0, inplace=True)
else:
raise ValueError("there should be only 2 files. \n" +
"One ending with gct extension (prediction)\n" +
"One ending with txt extension (feature)")
#assert feature.shape == (2647,10)
assert prediction.shape == (2647,44)
self.prediction = prediction
self.feature = feature
# in SC2, only a subset of predictive features (2647 out of 17.000) are used
df1 = self.goldstandard.ix[self.gs_priority[0]]
self.df1 = df1
scores = []
df2 = self.prediction
N = len(df1)
scores = [df2.ix[i].corr(df1.ix[i], method='spearman') for i in range(0, N)]
self.scores = scores
final_score = sum(scores)/float(len(scores))
return {'score': final_score}
def unzip(self, filename):
"""Simple method to extract all files contained in an archive"""
from dreamtools.core.ziptools import ZIP
z = ZIP()
z.loadZIPFile(self.get_pathname(filename)), z.extractall(self.directory)
def unzip(self, filename):
"""Simple method to extract all files contained in an archive"""
from dreamtools.core.ziptools import ZIP
z = ZIP()
z.loadZIPFile(self.get_pathname(filename)), z.extractall(
self.directory)
def test_zip():
z = ZIP()
try:
z.loadZIPFile('p')
except:
pass
