def read_Hemato(override=False, verbose=False):
preprocessed_path = select_path(os.path.join(DATA_DIR,
'HEMATO_preprocessed'),
create_new=True)
if override:
shutil.rmtree(preprocessed_path)
os.mkdir(preprocessed_path)
# ====== copy the dataset from scVI ====== #
if not os.path.exists(os.path.join(preprocessed_path, 'X')):
try:
from scvi.dataset import HematoDataset
except ImportError:
raise RuntimeError("Require `scVI` package for HEMATO dataset")
gene_dataset = HematoDataset(
save_path=os.path.join(DOWNLOAD_DIR, 'HEMATO/'))
X = gene_dataset._X
gene_names = np.array(gene_dataset.gene_names)
assert len(gene_names) == X.shape[1]
y = gene_dataset.meta.values[:, 1:]
label_names = np.array(gene_dataset.cell_types_levels)
assert len(label_names) == y.shape[1]
cell_names = np.array(['Cell#%d' % i for i in range(X.shape[0])])
_save_data_to_path(preprocessed_path, X, y, gene_names, label_names,
cell_names, verbose)
# create a binary classes for testing
label_names = np.array(["Erythroblasts", "Granulocytes"])
min_y = np.min(gene_dataset.labels)
max_y = np.max(gene_dataset.labels)
y_val = 2 * (gene_dataset.labels - min_y) / (max_y - min_y) - 1
y_bin = np.argmax(
np.hstack((
gene_dataset.meta.iloc[:, 1].values[:, None], # Er
gene_dataset.meta.iloc[:, 2].values[:, None])), # Gr
axis=-1)
with open(os.path.join(preprocessed_path, 'labels_name'), 'wb') as f:
pickle.dump(label_names, f)
with open(os.path.join(preprocessed_path, 'labels_bin'), 'wb') as f:
pickle.dump(y_bin, f)
with open(os.path.join(preprocessed_path, 'labels_val'), 'wb') as f:
pickle.dump(y_val, f)
# ====== read preprocessed data ====== #
ds = Dataset(preprocessed_path, read_only=True)
return ds
def _read_scvi_dataset(name, clazz_name, override, verbose):
preprocessed_path = select_path(os.path.join(DATA_DIR,
'%s_preprocessed' % name),
create_new=True)
if override:
shutil.rmtree(preprocessed_path)
os.mkdir(preprocessed_path)
# ====== copy the dataset from scVI ====== #
if not os.path.exists(os.path.join(preprocessed_path, 'X')):
try:
import scvi.dataset as scvi_dataset
except ImportError:
raise RuntimeError("Require `scVI` package for PBMC dataset")
clazz = getattr(scvi_dataset, clazz_name)
gene_dataset = clazz(save_path=DOWNLOAD_DIR)
X = gene_dataset._X
if hasattr(X, 'todense'):
X = np.array(X.todense())
gene_names = np.array(gene_dataset.gene_names)
# convert gene identifier to gene symbol (i.e. name)
if hasattr(gene_dataset, 'de_metadata'):
from sisua.data.utils import get_gene_id2name
meta = gene_dataset.de_metadata
converter = {i: j for i, j in zip(meta.ENSG, meta.GS)}
pbmc8kconverter = get_gene_id2name()
gene_names = np.array([
pbmc8kconverter[i] if i in pbmc8kconverter else converter[i]
for i in gene_names
])
assert len(gene_names) == X.shape[1]
label_names = np.array(gene_dataset.cell_types)
y = one_hot(gene_dataset.labels.ravel(), nb_classes=len(label_names))
assert len(label_names) == y.shape[1]
cell_names = np.array(['Cell#%d' % i for i in range(X.shape[0])])
_save_data_to_path(preprocessed_path, X, y, gene_names, label_names,
cell_names, verbose)
# ====== read preprocessed data ====== #
ds = Dataset(preprocessed_path, read_only=True)
return ds
import os
import pickle
import numpy as np
from scipy.io import savemat
from odin import fuel as F, visual as V
from odin.utils import ctext, Progbar, get_exppath, select_path
from odin.stats import train_valid_test_split, sampling_iter
from odin.preprocessing.signal import segment_axis
HOME_PATH = os.path.expanduser('~')
# fixed path to 'voxceleb1_wav' folder
PATH_TO_WAV = select_path('/media/data2/SRE_DATA/voxceleb',
'/mnt/sdb1/SRE_DATA/voxceleb',
os.path.join(HOME_PATH, 'data', 'voxceleb'),
os.path.join(HOME_PATH, 'voxceleb'),
create_new=False)
# path to folder contains experiment results
PATH_EXP = get_exppath('voxceleb')
# output path for acoustic features directory
PATH_ACOUSTIC_FEAT = os.path.join(PATH_EXP, 'voxceleb_feat')
if not os.path.exists(PATH_ACOUSTIC_FEAT):
os.mkdir(PATH_ACOUSTIC_FEAT)
# ====== remove '_quarter' if you want full training data ====== #
FILE_LIST = "voxceleb_files_quarter"
TRAIN_LIST = "voxceleb_sys_train_with_labels_quarter"
TRIAL_LIST = "voxceleb_trials"
# ====== Load the file list ====== #
ds = F.load_voxceleb_list()
WAV_FILES = {} # dictionary mapping 'file_path' -> 'file_name'
EXP_DIR = get_exppath('sre', override=False)
# this folder store extracted vectors for training backend and extracting scores
VECTORS_DIR = os.path.join(EXP_DIR, 'vectors')
if not os.path.exists(VECTORS_DIR):
os.mkdir(VECTORS_DIR)
# this folder store the results
RESULT_DIR = os.path.join(EXP_DIR, 'results')
if not os.path.exists(RESULT_DIR):
os.mkdir(RESULT_DIR)
# this folder store the analysis
ANALYSIS_DIR = os.path.join(EXP_DIR, 'analysis')
if not os.path.exists(ANALYSIS_DIR):
os.mkdir(ANALYSIS_DIR)
# ====== raw data ====== #
PATH_BASE = select_path('/media/data2/SRE_DATA',
'/mnt/sda1/SRE_DATA',
'/mnt/sdb1/SRE_DATA',
default='')
# path to directory contain following folders:
##############
# * fisher
# * mx6
# * sre04
# * sre05
# * sre06
# * sre08
# * sre10
# * swb
# * voxceleb1
# * voxceleb2
###############
# * musan
import pickle
import numpy as np
from scipy.io import savemat
from odin import fuel as F, visual as V
from odin.utils import ctext, Progbar, get_exppath, select_path
from odin.stats import train_valid_test_split, sampling_iter
from odin.preprocessing.signal import segment_axis
HOME_PATH = os.path.expanduser('~')
# fixed path to 'voxceleb1_wav' folder
PATH_TO_WAV = select_path(
'/media/data2/SRE_DATA/voxceleb',
'/mnt/sdb1/SRE_DATA/voxceleb',
os.path.join(HOME_PATH, 'data', 'voxceleb'),
os.path.join(HOME_PATH, 'voxceleb'),
create_new=False
)
# path to folder contains experiment results
PATH_EXP = get_exppath('voxceleb')
# output path for acoustic features directory
PATH_ACOUSTIC_FEAT = os.path.join(PATH_EXP, 'voxceleb_feat')
if not os.path.exists(PATH_ACOUSTIC_FEAT):
os.mkdir(PATH_ACOUSTIC_FEAT)
# ====== remove '_quarter' if you want full training data ====== #
FILE_LIST = "voxceleb_files_quarter"
TRAIN_LIST = "voxceleb_sys_train_with_labels_quarter"
TRIAL_LIST = "voxceleb_trials"
# ====== Load the file list ====== #
ds = F.load_voxceleb_list()
import os
from os.path import expanduser
from odin.utils import get_script_path, select_path
DEFAULT_BASE_DIR = expanduser("~")
if 'SISUA_DATA' in os.environ:
DATA_DIR = os.environ['SISUA_DATA']
if not os.path.exists(DATA_DIR):
os.mkdir(DATA_DIR)
elif os.path.isfile(DATA_DIR):
raise RuntimeError("Store data path at '%s' must be a folder" %
DATA_DIR)
else:
DATA_DIR = select_path(os.path.join(DEFAULT_BASE_DIR, 'bio_data'),
create_new=True)
DOWNLOAD_DIR = select_path(os.path.join(DATA_DIR, 'downloads'),
create_new=True)
# PATH for saving experiments results
if 'SISUA_EXP' in os.environ:
EXP_DIR = os.environ['SISUA_EXP']
if not os.path.exists(EXP_DIR):
os.mkdir(EXP_DIR)
elif os.path.isfile(EXP_DIR):
raise RuntimeError("Experiment path at '%s' must be a folder" %
EXP_DIR)
else:
EXP_DIR = select_path(os.path.join(DEFAULT_BASE_DIR, 'bio_exp'),
create_new=True)
# this folder store extracted vectors for training backend and extracting scores
VECTORS_DIR = os.path.join(EXP_DIR, 'vectors')
if not os.path.exists(VECTORS_DIR):
os.mkdir(VECTORS_DIR)
# this folder store the results
RESULT_DIR = os.path.join(EXP_DIR, 'results')
if not os.path.exists(RESULT_DIR):
os.mkdir(RESULT_DIR)
# this folder store the analysis
ANALYSIS_DIR = os.path.join(EXP_DIR, 'analysis')
if not os.path.exists(ANALYSIS_DIR):
os.mkdir(ANALYSIS_DIR)
# ====== raw data ====== #
PATH_BASE = select_path(
'/media/data2/SRE_DATA',
'/mnt/sda1/SRE_DATA',
'/mnt/sdb1/SRE_DATA',
default='')
# path to directory contain following folders:
##############
# * fisher
# * mx6
# * sre04
# * sre05
# * sre06
# * sre08
# * sre10
# * swb
# * voxceleb1
# * voxceleb2
###############
# Const
# ===========================================================================
# top 5000 variable genes
_URL_5000 = b'aHR0cHM6Ly9zMy5hbWF6b25hd3MuY29tL2FpLWRhdGFzZXRzL0dTRTEwMDg2Nl9QQk1DLnJhd0Nv\ndW50RGF0YS41MDAwLmh2Zy5jc3Yuemlw\n'
_MD5_5000 = '46150f63e5a3c81d4f07445a759faa2b'
# raw Count Gene
_URL_FULL = b'aHR0cHM6Ly9zMy5hbWF6b25hd3MuY29tL2FpLWRhdGFzZXRzL0dTRTEwMDg2Nl9QQk1DLnJhd0Nv\ndW50RGF0YS5jc3Yuemlw\n'
_MD5_FULL = '7481cc9d20adef4d06fdb601d9d99e77'
# protein
_URL_PROTEIN = b'aHR0cHM6Ly9zMy5hbWF6b25hd3MuY29tL2FpLWRhdGFzZXRzL0dTRTEwMDg2Nl9QQk1DLnJhd0Nv\ndW50UHJvdGVpbi5jc3Yuemlw\n'
_MD5_PROTEIN = '7dc5f64c2916d864568f1b739679717e'
_CITEseq_PBMC_PREPROCESSED = select_path(os.path.join(
DATA_DIR, 'PBMC_citeseq_preprocessed'),
create_new=True)
_5000_PBMC_PREPROCESSED = select_path(os.path.join(
DATA_DIR, 'PBMC_citeseq_5000_preprocessed'),
create_new=True)
_PASSWORD = '******'
# ===========================================================================
# Main
# ===========================================================================
def read_CITEseq_PBMC(override=False,
verbose=True,
filtered_genes=False) -> SingleCellOMIC:
download_path = os.path.join(
