def getData(self, histDataAsWell):
'''
Ici sur toutes les experiences dans self.expList on construit l'histogramme de toutes les features numeriques
'''
histDict = defaultdict(list)
_,r, _, _,_, length, _, _, _ = histConcatenation(self.settings.data_folder, self.expList, self.settings.mitocheck_file,
self.settings.quality_control_file, verbose=self.verbose)
for feature in self.currInterestFeatures:
for i in range(len(length)):
histDict[feature].append(r[np.sum(length[:i]):np.sum(length[:i+1]),featuresSaved.index(feature)])
histogrammes, bins = computingBins(histDict, [self.bin_size for k in range(len(self.currInterestFeatures))], self.bin_type, iter_=self.iter_ )
return histogrammes, bins
def collectingData(iter_, expList, debut, fin):
folder = "/cbio/donnees/aschoenauer/workspace2/Xb_screen/resultData/experiment_clustering/"
histDict = defaultdict(list)
_, r, _, who, ctrlStatus, length, genes, siRNAs, _ = histConcatenation(
"/share/data20T/mitocheck/tracking_results",
expList[debut:fin],
"/cbio/donnees/aschoenauer/workspace2/Xb_screen/data/mitocheck_siRNAs_target_genes_Ens72.txt",
"/cbio/donnees/aschoenauer/workspace2/Xb_screen/data/qc_export.txt",
)
for i in range(len(length)):
for k, feature in enumerate(interestFeatures):
histDict[feature].append(r[np.sum(length[:i]) : np.sum(length[: i + 1]), featuresSaved.index(feature)])
f = open("../resultData/experiment_clustering/distExp_ctrl_quantile_10.pkl")
bins = pickle.load(f)
f.close()
histogrammes, bins = computingBins(histDict, [10 for k in range(16)], "quantile", previous_binning=bins)
f = open(os.path.join(folder, "data_{}.pkl".format(iter_)), "w")
pickle.dump((histogrammes, who, ctrlStatus, genes, siRNAs), f)
f.close()
def _dataPrep(self, pcaParameter):
histDict = defaultdict(list)
ctrlExp = appendingControl(self.expList)
ctrlExp = countingDone(ctrlExp)
np.random.shuffle(ctrlExp)
ctrlExp = ctrlExp[: int(0.2 * len(self.expList))]
if self.verbose:
print ctrlExp
self.expList.extend(ctrlExp)
_, r, _, _, _, length, _, _, _ = histConcatenation(
self.settings.data_folder,
self.expList,
self.settings.mitocheck_file,
self.settings.quality_control_file,
verbose=self.verbose,
)
for i in range(len(length)):
for k, feature in enumerate(self.currInterestFeatures):
histDict[feature].append(r[np.sum(length[:i]) : np.sum(length[: i + 1]), featuresSaved.index(feature)])
f = open(
os.path.join(self.settings.result_folder, "distExp_ctrl_{}_{}.pkl".format(self.bins_type, self.bin_size))
)
bins = pickle.load(f)
f.close()
histogrammes, bins = computingBins(
histDict,
[self.bin_size for k in range(len(self.currInterestFeatures))],
self.bins_type,
previous_binning=bins,
)
print histogrammes.shape
return histogrammes, bins