selection.py 文件源码

def regression_apply(row, timepoints, weighted):
    """
    :py:meth:`pandas.DataFrame.apply` apply function for calculating 
    enrichment using linear regression. If *weighted* is ``True`` perform
    weighted least squares; else perform ordinary least squares.

    Weights for weighted least squares are included in *row*.

    Returns a :py:class:`pandas.Series` containing regression coefficients,
    residuals, and statistics.
    """
    # retrieve log ratios from the row
    y = row[['L_{}'.format(t) for t in timepoints]]

    # re-scale the x's to fall within [0, 1]
    xvalues = [x / float(max(timepoints)) for x in timepoints]

    # perform the fit
    X = sm.add_constant(xvalues) # fit intercept
    if weighted:
        W = row[['W_{}'.format(t) for t in timepoints]]
        fit = sm.WLS(y, X, weights=W).fit()
    else:
        fit = sm.OLS(y, X).fit()

    # re-format as a data frame row
    values = np.concatenate([fit.params,  [fit.bse['x1'], fit.tvalues['x1'], 
                            fit.pvalues['x1']], fit.resid])
    index = ['intercept', 'slope', 'SE_slope', 't', 'pvalue_raw'] + \
            ['e_{}'.format(t) for t in timepoints]
    return pd.Series(data=values, index=index)