def beta_dist(data_sets, kmer_size, n_factor):
# Loop over all data sets
for data_set in data_sets:
data_set = data_set[0]
# Retrieve diseased data and labels
allowed_labels = ['0', '1']
kmer_cnts, accessions, labelz, domain_labels = load_kmer_cnts_jf.load_kmers(
kmer_size, data_set, allowed_labels)
print("LOADED DATASET " + str(data_set[0]) + ": " +
str(len(kmer_cnts)) + " SAMPLES")
labelz = np.asarray(labelz)
labelz = labelz.astype(np.int)
# Conduct NMF and resave to data_normalized
if n_factor == 0:
data_normalized = normalize(kmer_cnts, axis=1, norm='l1')
data_normalized, labels = shuffle(data_normalized,
labelz,
random_state=0)
x = data_normalized
y = labels
else:
data_normalized = normalize(kmer_cnts, axis=1, norm='l1')
data_normalized = stats_utils_AEB.NMF_factor(
data_normalized,
kmer_size,
n_components=int(n_factor),
title=(str(data_set) + str(kmer_size) + "mers" +
str(n_factor) + "factors"))
data_normalized, labels = shuffle(data_normalized,
labelz,
random_state=0)
x = data_normalized
y = labels
return x, y
'w',
newline='') as csvfile:
fieldnames = [
'dataset', 'kmer_size', 'n_splits', 'n_repeats', 'acc', 'auc',
'precision', 'recall', 'f1', 'model', 'NMF_factors', 'params'
]
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
# Loop over all data sets
for data_set in data_sets_to_use:
data_set = data_set[0]
# Retrieve diseased data and labels
allowed_labels = ['0', '1']
kmer_cnts, accessions, labelz, domain_labels = load_kmer_cnts_jf.load_kmers(
kmer_size, data_set, allowed_labels)
print("LOADED DATASET " + str(data_set[0]) + ": " +
str(len(kmer_cnts)) + " SAMPLES")
labelz = np.asarray(labelz)
labelz = labelz.astype(np.int)
# Conduct NMF and resave to data_normalized
#enter in desired no.factors
for n in [0, 5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100]:
if n == 0:
data_normalized = normalize(kmer_cnts, axis=1, norm='l1')
data_normalized, labels = shuffle(data_normalized,
labelz,
random_state=0)
x = data_normalized
y = labels
backend = K.backend()
import load_kmer_cnts_jf
import deep_learning_models
#################
# Load the data #
#################
kmer_size = 7
#data_sets_healthy=['HMP', 'Qin_et_al','RA','MetaHIT','Feng','Karlsson_2013','LiverCirrhosis','Zeller_2014']
data_sets_healthy = ['MetaHIT']
allowed_labels = ['0']
kmer_cnts_healthy, accessions_healthy, labels_healthy, domain_labels = load_kmer_cnts_jf.load_kmers(
kmer_size, data_sets_healthy, allowed_labels)
data_sets_diseased = ['MetaHIT']
allowed_labels = ['1']
kmer_cnts_diseased, accessions_diseased, labels_diseased, domain_labels = load_kmer_cnts_jf.load_kmers(
kmer_size, data_sets_diseased, allowed_labels)
kmer_cnts = np.concatenate((kmer_cnts_healthy, kmer_cnts_diseased))
accessions = np.concatenate((accessions_healthy, accessions_diseased))
labels = np.concatenate((labels_healthy, labels_diseased))
labels = np.asarray(labels)
labels = labels.astype(np.int)
healthy = np.where(labels == 0)
disease = np.where(labels == 1)
################# # Load the data # ################# #kmer_size=3 kmer_size=5 #kmer_size=10 #data_set='Qin_et_al' #data_set='RA' #data_set='MetaHIT' data_set='HMP' data_sets=['HMP'] kmer_cnts, accessions, labels =load_kmer_cnts_jf.load_kmers(kmer_size,data_sets) labels=np.asarray(labels) healthy=np.where(labels=='0') disease=np.where(labels=='1') data=pd.DataFrame(kmer_cnts) data_normalized = normalize(data, axis = 1, norm = 'l1') ################################ # set up a model (autoencoder) ################################ input_dim=len(data_normalized[0]) # this is the number of input kmers encoding_dim=10