def randomize_dataset(self, new_seed):
"""
Sample a new self.df of the same length, but with a new seed.
"""
self.df = self._load_nb_examples(seed=new_seed)
self.df.rename(symbol_map(self.df.columns),
axis="columns",
inplace=True)
if self.normalize:
self.df = self.df - self.df.mean(axis=0)
def __init__(self, relabel_genes=True, datastore=None, randomize=False):
if datastore is None:
self.datastore = os.path.dirname(os.path.abspath(__file__))
else:
self.datastore = datastore
self.load_data()
self.nx_graph = nx.relabel.relabel_nodes(self.nx_graph, symbol_map(self.nx_graph.nodes))
# Randomize
self.randomize = randomize
if self.randomize:
print("Randomizing the graph")
self.nx_graph = nx.relabel.relabel_nodes(self.nx_graph, randmap(self.nx_graph.nodes))
def load_data(self):
self.hdf5 = h5py.File(name=self.file_path, mode='r')
self.expression_data = self.hdf5['expression_data']
self.nrows, self.ncols = self.expression_data.shape
# Load all gene names to memory
self.genes = [x.decode() for x in self.hdf5['gene_names'][()].tolist()]
if self.load_full:
self.df = pd.DataFrame(data=self.expression_data[()],
columns=self.genes)
else:
self.df = self._load_nb_examples()
self.df.rename(symbol_map(self.df.columns),
axis="columns",
inplace=True)
if self.normalize:
self.df = self.df - self.df.mean(axis=0)
def load_data(self):
csv_file = at.get(self.at_hash, datastore=self.datastore)
hdf_file = csv_file.split(".gz")[0] + ".hdf5"
if not os.path.isfile(hdf_file):
print("We are converting a CSV dataset of TCGA to HDF5. Please wait a minute, this only happens the first "
"time you use the TCGA dataset.")
df = pd.read_csv(csv_file, compression="gzip", sep="\t")
df = df.set_index('Sample')
df = df.transpose()
df.to_hdf(hdf_file, key="data", complevel=5)
self.df = pd.read_hdf(hdf_file)
self.df.rename(symbol_map(self.df.columns), axis="columns", inplace=True)
self.df = self.df - self.df.mean(axis=0)
#self.df = self.df / self.df.variance()
self.sample_names = self.df.index.values.tolist()
self.node_names = np.array(self.df.columns.values.tolist()).astype("str")
self.nb_nodes = self.df.shape[1]
self.labels = [0 for _ in range(self.df.shape[0])]
def __init__(self, relabel_genes=True, datastore="./data"):
self.datastore = datastore
self.load_data()
self.nx_graph = nx.relabel.relabel_nodes(
self.nx_graph, symbol_map(self.nx_graph.nodes))
def __init__(self, relabel_genes=True):
self.load_data()
self.nx_graph = nx.relabel.relabel_nodes(
self.nx_graph, symbol_map(self.nx_graph.nodes))
