def run_moana(trainname, testname, n):
DataPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + trainname + '.csv'
matrix = ExpMatrix.read_tsv(DataPath, sep=',')
LabelsPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + trainname + '_label.csv'
truelab = pd.read_csv(LabelsPath, header=0, index_col=0, sep=',')
data = ExpMatrix(X=matrix.X, genes=matrix.genes, cells=matrix.cells)
data.genes.name = 'Genes'
data.cells.name = 'Cells'
data.index.name = 'Genes'
data.columns.name = 'Cells'
l = CellAnnVector(cells=data.cells, data=truelab['x'].values)
now = time.time()
tracemalloc.start()
clf = CellTypeClassifier()
clf.fit(matrix=data, cell_labels=l)
snapshot = tracemalloc.take_snapshot()
mem_train = display_top(snapshot)
later = time.time()
time_train = int(later - now)
DataPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + testname + '.csv'
matrix = ExpMatrix.read_tsv(DataPath, sep=',')
data = ExpMatrix(X=matrix.X, genes=matrix.genes, cells=matrix.cells)
data.genes.name = 'Genes'
data.cells.name = 'Cells'
data.index.name = 'Genes'
data.columns.name = 'Cells'
now = time.time()
tracemalloc.start()
predictions = clf.predict(data)
snapshot = tracemalloc.take_snapshot()
mem_test = display_top(snapshot)
later = time.time()
time_test = int(later - now)
predictions = np.asarray(predictions)
pred = pd.DataFrame(predictions)
LabelsPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + testname + '_label.csv'
truelab = pd.read_csv(LabelsPath, header=0, index_col=None, sep=',')
os.chdir("/dora/nobackup/yuec/scclassify/benchmark/moanna/vary_train")
truelab.to_csv(n + "_moana_True.csv", index=False)
pred.to_csv(n + "_moana_Pred.csv", index=False)
return mem_train, time_train, mem_test, time_test
def run_SVMreject(trainname, testname, n):
trainDataPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + trainname + '.csv'
trainLabelsPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + trainname + '_label.csv'
testDataPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + testname + '.csv'
testLabelsPath = '/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' + testname + '_label.csv'
# read the data
train = pd.read_csv(trainDataPath, index_col=0, sep=',')
test = pd.read_csv(testDataPath, index_col=0, sep=',')
y_train = pd.read_csv(trainLabelsPath, header=0, index_col=0, sep=',')
y_train = y_train['x'].ravel()
y_test = pd.read_csv(testLabelsPath, header=0, index_col=0, sep=',')
y_test = y_test['x'].ravel()
truelab = []
pred = []
train = train.transpose()
test = test.transpose()
now = time.time()
tracemalloc.start()
Classifier = LinearSVC()
clf = CalibratedClassifierCV(Classifier)
clf.fit(train, y_train)
snapshot = tracemalloc.take_snapshot()
mem_train = display_top(snapshot)
later = time.time()
time_train = int(later - now)
now = time.time()
tracemalloc.start()
predicted = clf.predict(test)
snapshot = tracemalloc.take_snapshot()
mem_test = display_top(snapshot)
later = time.time()
time_test = int(later - now)
prob = np.max(clf.predict_proba(test), axis=1)
unlabeled = np.where(prob < 0.7)
predicted[unlabeled] = 'Unassigned'
truelab = y_test
pred = predicted
truelab = pd.DataFrame(truelab)
pred = pd.DataFrame(pred)
os.chdir("/dora/nobackup/yuec/scclassify/benchmark/SVMreject/vary_test")
truelab.to_csv(n + "_SVMreject_true.csv", index=False)
pred.to_csv(n + "_SVMreject_pred.csv", index=False)
return mem_train, time_train, mem_test, time_test
def run_scVI(trainname, testname, n):
#trainDataPath = "/Users/yue/Dropbox (Sydney Uni)/scclassify/scRNAseq_Benchmark_datasets/Pancreatic_data/Segerstolpe/Filtered_Segerstolpe_HumanPancreas_data.csv"
#train = pd.read_csv(trainDataPath,index_col=0,sep=',')
#trainLabelsPath = "/Users/yue/Dropbox (Sydney Uni)/scclassify/scRNAseq_Benchmark_datasets/Pancreatic_data/Segerstolpe/Labels.csv"
#trainlabels = pd.read_csv(trainLabelsPath, header=0,index_col=None, sep=',')
#testDataPath = "/Users/yue/Dropbox (Sydney Uni)/scclassify/scRNAseq_Benchmark_datasets/Pancreatic_data/Xin/Filtered_Xin_HumanPancreas_data.csv"
#test = pd.read_csv(testDataPath,index_col=0,sep=',')
#testLabelsPath = "/Users/yue/Dropbox (Sydney Uni)/scclassify/scRNAseq_Benchmark_datasets/Pancreatic_data/Xin/Labels.csv"
#testlabels = pd.read_csv(testLabelsPath, header=0,index_col=None, sep=',')
train = pd.read_csv(
'/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' +
trainname + '.csv',
index_col=0,
sep=',')
test = pd.read_csv(
'/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' +
testname + '.csv',
index_col=0,
sep=',')
trainlabel = pd.read_csv(
'/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' +
trainname + '_label.csv',
header=0,
index_col=0,
sep=',')
testlabel = pd.read_csv(
'/albona/nobackup/biostat/datasets/singlecell/tabulaMuris_benchmark/' +
testname + '_label.csv',
header=0,
index_col=0,
sep=',')
newdata = pd.concat([train, test], axis=1)
newlabel = pd.concat([trainlabel, testlabel], axis=0)
#train = '/Users/yue/Dropbox (Sydney Uni)/scclassify/countmatrix/logcount/xin.csv'
#save labels as csv file with header and index column
#trainlabels.to_csv('trainLabels_scvi.csv')
#train.to_csv('trainData_scvi.csv')
#testlabels.to_csv('testLabels_scvi.csv')
#test.to_csv('testData_scvi.csv')
os.chdir("/dora/nobackup/yuec/scclassify/benchmark/scVI/vary_test")
newdata.to_csv('data_scvi.csv')
newlabel.to_csv('labels_scvi.csv')
data = CsvDataset('data_scvi.csv',
save_path="",
sep=",",
labels_file="labels_scvi.csv",
gene_by_cell=True)
n_epochs = 100
truelab = []
pred = []
## this semisupervised trainer automatically uses a part of the input data for training and a part for testing
now = time.time()
tracemalloc.start()
scanvi = SCANVI(data.nb_genes, data.n_batches, data.n_labels)
trainer_scanvi = SemiSupervisedTrainer(scanvi, data, frequency=5)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
indices=(list(range(0, trainlabel.shape[0]))), shuffle=False)
trainer_scanvi.labelled_set.to_monitor = ['ll', 'accuracy']
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=(list(
range(trainlabel.shape[0],
trainlabel.shape[0] + testlabel.shape[0]))),
shuffle=False)
trainer_scanvi.unlabelled_set.to_monitor = ['ll', 'accuracy']
trainer_scanvi.train(n_epochs)
snapshot = tracemalloc.take_snapshot()
mem_train = display_top(snapshot)
later = time.time()
time_train = int(later - now)
## labels of test set are in y_pred
## labels are returned in numbers, should be mapped back to the real labels
## indices are permutated
now = time.time()
tracemalloc.start()
y_true, y_pred = trainer_scanvi.unlabelled_set.compute_predictions()
snapshot = tracemalloc.take_snapshot()
mem_test = display_top(snapshot)
later = time.time()
time_test = int(later - now)
truelab.extend(y_true)
pred.extend(y_pred)
truelab = pd.DataFrame(truelab)
pred = pd.DataFrame(pred)
os.chdir("/dora/nobackup/yuec/scclassify/benchmark/scVI/vary_test")
truelab.to_csv(n + "_scVI_True.csv", index=False)
pred.to_csv(n + "_scVI_Pred.csv", index=False)
return mem_train, time_train, mem_test, time_test