def main():
# f.1. read user defined variables
fileLocations, genomeAnnotation = optionReader.main()
# f.2. read sequence data
sampleNames = dataReader.main(fileLocations)
# f.3. generate barcode-specific FASTQ files
# working in a parallel environment
numberOfThreads = len(sampleNames)
print('Initialized parallel analysis using {} threads...'.format(
numberOfThreads))
hydra = multiprocessing.pool.Pool(numberOfThreads)
instances = [[fileLocations, sampleName] for sampleName in sampleNames]
tempo = hydra.map(barcodeWorkerSingleWithBarcode.main, instances)
print('... completed.')
# working in serial
#for sampleName in sampleNames:
# print(sampleName)
# barcodeWorkerSingleWithBarcode.main(fileLocations,sampleName)
# f.4. run quantification pipelines for each barcode-specific FASTQ file
# f.5. map reads
#readMapper.main(fileLocations,sampleNames)
#readMapperSingle.main(fileLocations,genomeAnnotation,sampleNames)
readMapperSingleWithBarcode.main(fileLocations, genomeAnnotation,
sampleNames)
# f.6. generate histograms of read maping for highesta buundace transcripts.
return None
def task(args):
(data_type, repr_dim), seed, (algName, _, makeAlg) = args
logging.info("datatype = %s, seed = %d, algorithm = %s", data_type, seed, algName)
# read the data sets
logging.info("Reading data...")
y_train, x_train, y_test, x_test = dataReader.main("%s_%d" % (data_type, seed))
data_dim = x_train.shape[1]
logging.info(" * training set: %d x %d" % x_train.shape)
logging.info(" * testing set: %d x %d" % x_test.shape)
# init rng
np.random.seed(seed)
logging.info("Running and evaluating the algorithm...")
logging.info(" * using representation with dimension = %d", repr_dim)
# init the algorithm
alg = makeAlg(data_dim, repr_dim)
# create output dir if does not exist
ensure_dir_exists('res')
# define the progress saving function
progress_filename = 'res/progress-encdec-mse-%s-%d-%s.txt' % (data_type, seed, algName)
progress_file = open(progress_filename, 'w', encoding='utf-8')
def save_progress():
x_test_pred = alg.decode(alg.encode(x_test))
rel_mse = relative_mean_squared_error(x_test, x_test_pred)
progress_file.write("%g\n" % rel_mse)
# fit to the training data
alg.learn(x_train,
log_file_prefix=("log/%s-%d-%s" % (data_type, seed, algName)),
callbacks=[save_progress])
# TODO: remove?
x_test = x_train
# test with the testing data
x_test_pred = alg.decode(alg.encode(x_test))
ensure_dir_exists('pred')
pred_filename = 'pred/final-encdec-%s-%d-%s' % (data_type, seed, algName)
if save_pred:
np.save(pred_filename, x_test_pred)
#from sklearn import metrics
#mse = metrics.mean_squared_error(x_test, x_test_pred,
# multioutput='uniform_average')
#explained_var = metrics.explained_variance_score(x_test, x_test_pred,
# multioutput='uniform_average')
mse = mean_squared_error(x_test, x_test_pred)
rel_mse = relative_mean_squared_error(x_test, x_test_pred)
logging.info("Result: rel_mse = %g", rel_mse)
logging.info("Writing results to a file...")
res_filename = 'res/final-encdec-mse-%s-%d-%s.txt' % (data_type, seed, algName)
with open(res_filename, 'w', encoding='utf-8') as f:
f.write("data = %-16s seed = %-4d alg = %-10s " % (data_type, seed, algName))
f.write("mse = %.6f " % mse)
f.write("rel_mse = %.6f " % rel_mse)
f.write("\n")
def task(args):
data_type, seed, (algName, _, makeAlg) = args
logging.info("datatype = %s, seed = %d, algorithm = %s", data_type, seed, algName)
# read the data sets
logging.info("Reading data...")
y_train, x_train, y_test, x_test = dataReader.main("%s_%d" % (data_type, seed))
data_dim = x_train.shape[1]
logging.info(" * training set: %d x %d" % x_train.shape)
logging.info(" * testing set: %d x %d" % x_test.shape)
# init rng
np.random.seed(seed)
x_test = x_train
logging.info("Running and evaluating the algorithm...")
# init the algorithm
alg = makeAlg(data_dim, repr_dim)
# create output dir if does not exist
ensure_dir_exists('res')
from sklearn.decomposition import PCA as sk_PCA
pca = sk_PCA(n_components=repr_dim)
pca.fit(x_train)
y_train = pca.transform(x_train)
y_test = pca.transform(x_test)
# define the progress saving function
progress_filename = 'res/progress-enc-mse-%s-%d-%s.txt' % (data_type, seed, algName)
progress_file = open(progress_filename, 'w', encoding='utf-8')
def save_progress():
y_test_pred = alg.encode(x_test)
rel_mse = relative_mean_squared_error(y_test, y_test_pred)
progress_file.write("%g\n" % rel_mse)
# fit
alg.learn(x_train, y_train,
log_file_prefix=("log/%s-%d-%s" % (data_type, seed, algName)),
callbacks=[save_progress])
#tiled = False
tiled = (n_projections[0], len(data_types) * n_projections[1])
#figsize = (12.0, 9.0)
figsize = (6.0, 6.0)
#print(mpl.rcParams['axes.color_cycle'])
if tiled:
plt.figure(figsize=(tiled[0] * figsize[0], tiled[1] * figsize[1]))
for d, data_type in enumerate(data_types):
print("data = %s ..." % data_type)
s = 0
seed = seeds[s]
y_train, x_train, y_test, x_test = dataReader.main("%s_%d" %
(data_type, seed))
x_test = x_train
x = x_test
x = x[1:1000, :]
for i in range(n_projections[1] * n_projections[0]):
if tiled:
plt.subplot(tiled[1], tiled[0],
d * n_projections[1] * tiled[0] + i + 1)
else:
plt.figure(figsize=figsize)
ax = plt.gca()
a = 2 * i
b = 2 * i + 1
plt.plot(x[:, a], x[:, b], '.k', label="data")
plt.xlim([-1.2, 1.2])
plt.ylim([-1.2, 1.2])