Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
BlueWhale/train_logreg_profile.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
101 lines (90 sloc)
3.64 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import dnn.loaddata as Loader | |
import sys | |
import os | |
import time | |
import numpy as np | |
import dnn.evaluation as ev | |
import dnn.metaData as metadata | |
import sklearn.metrics as metric | |
from sklearn.linear_model import SGDClassifier as lr | |
nbatchsize=5000 | |
def loadData(ibatch,threshold,ptrain=0.9): | |
#load the dataset | |
dhs=Loader.loadDhs(ibatch) | |
#randomize dataset | |
irnd=np.random.permutation(dhs.shape[0]) | |
ntrain=int(ptrain*dhs.shape[0]) | |
train_dhs=dhs[irnd[:ntrain],:,:] | |
test_dhs=dhs[irnd[ntrain:],:,:] | |
# | |
chip=Loader.loadChip(ibatch,threshold) | |
train_chip=chip[irnd[:ntrain],:,:] | |
test_chip=chip[irnd[ntrain:],:,:] | |
# | |
dna=Loader.loadDna(ibatch) | |
train_dna=dna[irnd[:ntrain],:,:] | |
test_dna=dna[irnd[ntrain:],:,:] | |
return train_dhs, test_dhs, train_chip, test_chip,\ | |
train_dna,test_dna | |
def main(batchid, threshold, num_epochs=500): | |
ibatch=batchid | |
print("Load annotation ...") | |
tf2i=metadata.loadMetaDataMap(metadata.datadir + "annotations/tf_names.txt") | |
cell2i=metadata.loadMetaDataMap(metadata.datadir + "annotations/cells.txt") | |
print("Loading dataset ...") | |
train_dhs,test_dhs, train_chip,test_chip, train_dna,test_dna=loadData(ibatch, threshold) | |
ncell=test_chip.shape[1] | |
ntf=test_chip.shape[2] | |
totaltrainingsize=train_dhs.shape[0] | |
totaltestsize=test_dhs.shape[0] | |
print("Logistic Regression on DHS auPRC: ") | |
thr=1 | |
for ktf in tf2i: | |
X=np.array([],dtype="float") | |
Xtest=np.array([],dtype="float") | |
ytest=np.array([],dtype="float") | |
y=np.array([],dtype="float") | |
for kc in cell2i: | |
if train_chip[0,cell2i[kc],tf2i[ktf]]>=0: | |
if X.shape[0]==0: | |
X=train_dhs[:,:,thr].astype("float")#*train_dhs[:,[cell2i[kc]],thr].astype("float") | |
Xtest=test_dhs[:,:,thr].astype("float")#*test_dhs[:,[cell2i[kc]],thr].astype("float") | |
ytest=test_chip[:,cell2i[kc],tf2i[ktf]].astype("float") | |
y=train_chip[:,cell2i[kc],tf2i[ktf]].astype("float") | |
break | |
else: | |
X=np.concatenate((X,train_dhs[:,:,thr].astype("float"))) | |
Xtest=np.concatenate((Xtest,test_dhs[:,:,thr].astype("float"))) | |
ytest=np.concatenate((ytest,test_chip[:,cell2i[kc],tf2i[ktf]].astype("float"))) | |
y=np.concatenate((y,train_chip[:,cell2i[kc],tf2i[ktf]].astype("float"))) | |
clf = lr(loss='log') | |
clf.fit(X, y) | |
pr=clf.decision_function(Xtest) | |
auprc = metric.average_precision_score(ytest, pr) | |
#auprc=metric.auc(prec,recall) | |
print(ktf+": "+ str(auprc)) | |
if __name__ == '__main__': | |
if ('--help' in sys.argv) or ('-h' in sys.argv) or (len(sys.argv)<=1): | |
print("Trains a neural network on DREAM dataset using Lasagne.") | |
print("Usage: %s batchid threshold [epochs]" % sys.argv[0]) | |
print("") | |
print("model: Specify one of the following model names") | |
for k in dnn.models.build_model: | |
print("\t"+k) | |
print("") | |
print("batchid: Use one of the batches which are number") | |
print(" from 0 to 19") | |
print("threshold: You must either specify 'conservative' or 'relaxed'") | |
print("EPOCHS: number of training epochs to perform (default: 500)") | |
print("") | |
print("Example usage:") | |
print("") | |
print("train_model.py 0 relaxed 10") | |
else: | |
kwargs = {} | |
kwargs['batchid'] = int(sys.argv[1]) | |
kwargs['threshold'] = "conservative" | |
if len(sys.argv) > 2: | |
kwargs['num_epochs'] = int(sys.argv[2]) | |
main(**kwargs) |