baseline.py 文件源码

def __init__(self,
                 labels_fname,
                 regions_fname=None,
                 max_n_rows=None,
                 load_cached=True):
        self.labels_fname = labels_fname
        self.regions_fname = regions_fname
        self.max_n_rows = max_n_rows
        self._hash = None
        self.load_cached = load_cached
        # extract the sample names from the header
        #assert labels_fname.endswith("labels.tsv.gz"), \
        #    "Unrecognized labels filename '%s'" % labels_fname
        self._init_header_data(labels_fname)
        # extract the factor from the filename
        self.factor = os.path.basename(labels_fname).split('.')[0]

        # if we want to use a cached version...
        if self.load_cached is True:
            try:
                print "Loading '%s'" % self.cached_fname
                self.h5store = h5py.File(self.cached_fname)
                self.data = pd.read_hdf(self.cached_fname, 'data')
            except KeyError:
                self.data = self._build_dataframe()
                self.data.to_hdf(self.cached_fname, 'data')
                print self.h5store
        else:
            self.data = self._build_dataframe()

        return