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
# 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
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),
title=(str(data_set) + str(kmer_size) + "mers" +
str(n) + "factors"))
data_normalized, labels = shuffle(data_normalized,
labelz,
random_state=0)
x = data_normalized
y = labels
param_grid = param_dict[learn_type]
scoring = {
'Acc': 'accuracy',
'AUC': 'roc_auc',
'Precision': 'precision',
'Recall': 'recall',
kmer_size = 7
data = pd.read_pickle(
"/pollard/home/abustion/deep_learning_microbiome/data_AEB/NMF_on_all_data/before_NMF_no_norm.pickle"
)
data_normalized = pd.read_pickle(
"/pollard/home/abustion/deep_learning_microbiome/data_AEB/NMF_on_all_data/before_NMF_with_norm.pickle"
)
factors = 30
for n in range(2, factors + 1):
data_NMF = stats_utils_AEB.NMF_factor(
data,
kmer_size,
n_components=int(n),
title=("ALL_DATA_no_norm_" + str(kmer_size) + "mers" + str(n) +
"factors"))
data_NMF.to_pickle(
"/pollard/home/abustion/deep_learning_microbiome/data_AEB/NMF_on_all_data/after_NMF_no_norm_"
+ str(n) + "factors.pickle")
factors = 30
for n in range(2, factors + 1):
data_NMF = stats_utils_AEB.NMF_factor(
data_normalized,
kmer_size,
n_components=int(n),
title=("ALL_DATA_no_norm_" + str(kmer_size) + "mers" + str(n) +
"factors"))
data_NMF.to_pickle(