common.py 文件源码

def compute_bulk_smushing(self):
        """Get average signal from each plate ('bulk') and find 2d embedding"""

        grouped = self.genes.groupby(self.cell_metadata[self.SAMPLE_MAPPING])

        if os.path.exists(self.bulk_smushed_cache_file):
            smushed = pd.read_csv(self.bulk_smushed_cache_file, names=[0, 1],
                                  header=0, index_col=0)
            # if the set of plates hasn't changed, return the cached version
            if set(grouped.groups) == set(smushed.index):
                return smushed

        # if the cache was missing or invalid, compute a new projection
        medians = grouped.median()
        smusher = TSNE(random_state=0, perplexity=10, metric='cosine')
        smushed = pd.DataFrame(smusher.fit_transform(medians),
                               index=medians.index)

        smushed.to_csv(self.bulk_smushed_cache_file)

        return smushed