calculations.py 文件源码

def calculate_residual_correlation_matrix(returns):
    # find the market return constraining on the selected companies (first PCA)
    # regress each stock on that and find correlation of residuals
    returns_matrix = returns.as_matrix().transpose()
    covar_matrix = np.cov(returns_matrix)
    pca = decomposition.PCA(n_components=1)
    pca.fit(covar_matrix)
    X = pca.transform(covar_matrix)
    regr = linear_model.LinearRegression()
    dim = covar_matrix.shape[1]
    res = np.zeros(shape=(dim,dim))
    for x in range(0, dim):
        regr = linear_model.LinearRegression()
        regr = regr.fit(X, covar_matrix[:,x])
        res[:,x] = covar_matrix[:,x] - regr.predict(X)

    res_corr = np.corrcoef(res)
    return pd.DataFrame(res_corr, index = returns.columns, columns = returns.columns)