_sourcetracker.py 文件源码

def intersect_and_sort_samples(sample_metadata, feature_table):
    '''Return input tables retaining only shared samples, row order equivalent.

    Parameters
    ----------
    sample_metadata : pd.DataFrame
        Contingency table with rows, columns = samples, metadata.
    feature_table : pd.DataFrame
        Contingency table with rows, columns = samples, features.

    Returns
    -------
    sample_metadata, feature_table : pd.DataFrame, pd.DataFrame
        Input tables with unshared samples removed and ordered equivalently.

    Raises
    ------
    ValueError
        If no shared samples are found.
    '''
    shared_samples = np.intersect1d(sample_metadata.index, feature_table.index)
    if shared_samples.size == 0:
        raise ValueError('There are no shared samples between the feature '
                         'table and the sample metadata. Ensure that you have '
                         'passed the correct files.')
    elif (shared_samples.size == sample_metadata.shape[0] ==
          feature_table.shape[0]):
        s_metadata = sample_metadata.copy()
        s_features = feature_table.copy()
    else:
        s_metadata = sample_metadata.loc[np.in1d(sample_metadata.index,
                                                 shared_samples), :].copy()
        s_features = feature_table.loc[np.in1d(feature_table.index,
                                               shared_samples), :].copy()
    return s_metadata, s_features.loc[s_metadata.index, :]