Hello! I’m trying to perform GLM on the parcel level (my data is already preprocessed and averaged across voxels). I’ve found the run_glm function from nilearn, but I don’t understand how to interpret my output and how I can get betas from this 
Thank you very much for your time
labels, results = run_glm(data_for_glm, design_matrix)
labels
array(['0.73', '0.51', '0.46', '0.67', '0.76', '0.74', '0.47', '0.41',
'0.45', '0.55', '0.52', '0.53', '0.7', '0.28', '0.66', '0.45',
'0.71', '0.45', '0.66', '0.58', '0.62', '0.5', '0.59', '0.05',
'0.62', '0.53', '0.41', '0.47', '0.51', '0.33', '0.49', '0.25',
'0.4', '0.2', '0.24', '0.02', '0.25', '0.18', '0.29', '0.14',
'0.06', '0.32', '0.45', '0.53', '0.38', '0.6', '0.45', '0.57',
'0.28', '0.71', '0.53', '0.49', '0.3', '0.38', '0.28', '0.46',
'0.26', '-0.07', '0.05', '0.3', '0.17', '0.18', '0.33', '0.43',
'0.35', '0.3', '0.56', '0.46', '0.52', '0.6', '0.59', '0.47',
'0.38', '0.39', '0.38', '0.38', '0.49', '0.54', '0.49', '0.3',
'0.46', '0.56', '0.55', '0.63', '0.43', '0.45', '0.41', '0.7',
'0.47', '0.12', '0.48', '0.1', '0.34', '0.11', '0.62', '0.36',
'0.45', '0.2', '0.2', '0.36', '0.18', '0.0', '0.18', '0.09',
'0.29', '0.13', '0.23', '0.22', '0.24', '0.01', '0.1', '0.01',
'0.19', '-0.04', '0.02', '0.65', '0.72', '0.15', '0.1', '0.14',
'0.28', '0.11', '0.05', '0.22', '0.24', '0.03', '0.03', '0.19',
'0.26', '0.53', '0.26', '0.42', '0.69', '0.5', '0.05', '0.33',
'0.64', '0.49', '0.54', '0.66', '0.42', '0.58', '0.73', '0.8',
'0.83', '0.7', '0.47', '0.75', '0.83', '0.66', '0.76', '0.53',
'0.11', '0.34', '0.23', '0.68', '0.55', '0.69', '0.49', '0.18',
'0.23', '0.19', '0.23', '0.09', '0.14', '0.0', '0.08', '-0.08',
'0.42', '0.46', '0.28', '0.21', '0.06', '0.22', '0.41', '0.46',
'0.32', '0.1', '0.16', '0.13', '0.77', '0.45', '0.5', '0.7',
'0.67', '0.81', '0.49', '0.32', '0.51', '0.47', '0.22', '0.32',
'0.77', '0.21', '0.7', '0.44', '0.59', '0.56', '0.46', '0.43',
'0.52', '0.54', '0.4', '0.0', '0.44', '0.34', '0.23', '0.34',
'0.11', '0.39', '0.6', '0.09', '0.32', '0.34', '0.16', '0.12',
'0.14', '0.21', '0.07', '0.19', '0.04', '0.19', '0.38', '0.37',
'0.33', '0.41', '0.41', '0.61', '0.46', '0.58', '0.4', '0.48',
'0.41', '0.25', '0.13', '0.11', '0.01', '0.2', '0.13', '0.2',
'0.38', '0.34', '0.31', '0.39', '0.47', '0.28', '0.48', '0.61',
'0.6', '0.48', '0.62', '0.67', '0.41', '0.45', '0.46', '0.63',
'0.5', '0.5', '0.48', '0.46', '0.1', '0.53', '0.66', '0.48',
'0.52', '0.54', '0.55', '0.55', '0.4', '0.21', '0.44', '0.1',
'-0.02', '0.03', '0.47', '0.43', '0.49', '0.4', '0.22', '0.27',
'0.17', '0.13', '0.15', '0.16', '0.08', '0.18', '0.22', '0.34',
'0.31', '0.08', '0.23', '0.11', '0.15', '0.03', '0.11', '0.46',
'0.65', '0.0', '0.1', '0.06', '0.01', '0.0', '0.31', '0.09',
'0.27', '0.01', '0.26', '0.23', '0.3', '0.47', '0.35', '0.34',
'0.4', '-0.08', '0.14', '0.14', '0.6', '0.7', '0.22', '0.3', '0.4',
'0.38', '0.47', '0.66', '0.36', '0.22', '0.38', '0.6', '0.67',
'0.32', '0.81', '0.24', '0.13', '0.24', '0.0', '0.66', '0.6',
'0.62', '0.36', '0.16', '0.04', '0.21', '0.13', '0.1', '0.42',
'-0.01', '0.01', '0.09', '0.28', '0.53', '0.61', '0.09', '0.07',
'0.09', '0.11', '0.28', '0.08', '0.24', '0.21', '0.19'],
dtype='<U5')
results
{np.str_('-0.01'): <nilearn.glm.regression.RegressionResults at 0x7d523efcaa80>,
np.str_('-0.02'): <nilearn.glm.regression.RegressionResults at 0x7d523f143a10>,
np.str_('-0.04'): <nilearn.glm.regression.RegressionResults at 0x7d52457aeba0>,
np.str_('-0.07'): <nilearn.glm.regression.RegressionResults at 0x7d52478fc290>,
np.str_('-0.08'): <nilearn.glm.regression.RegressionResults at 0x7d523efc1f70>,
np.str_('0.0'): <nilearn.glm.regression.RegressionResults at 0x7d523efc20c0>,
np.str_('0.01'): <nilearn.glm.regression.RegressionResults at 0x7d523efc1b80>,
np.str_('0.02'): <nilearn.glm.regression.RegressionResults at 0x7d5249a106b0>,
np.str_('0.03'): <nilearn.glm.regression.RegressionResults at 0x7d5249a11cd0>,
np.str_('0.04'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a56d0>,
np.str_('0.05'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a40e0>,
np.str_('0.06'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a43e0>,
np.str_('0.07'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a6c30>,
np.str_('0.08'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a56a0>,
np.str_('0.09'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a4470>,
np.str_('0.1'): <nilearn.glm.regression.RegressionResults at 0x7d523f0a4080>,
np.str_('0.11'): <nilearn.glm.regression.RegressionResults at 0x7d523efd6360>,
np.str_('0.12'): <nilearn.glm.regression.RegressionResults at 0x7d523efd5e20>,
np.str_('0.13'): <nilearn.glm.regression.RegressionResults at 0x7d523efd67b0>,
np.str_('0.14'): <nilearn.glm.regression.RegressionResults at 0x7d523efd4cb0>,
np.str_('0.15'): <nilearn.glm.regression.RegressionResults at 0x7d523efd69f0>,
np.str_('0.16'): <nilearn.glm.regression.RegressionResults at 0x7d523efd5ee0>,
np.str_('0.17'): <nilearn.glm.regression.RegressionResults at 0x7d523efd4f20>,
np.str_('0.18'): <nilearn.glm.regression.RegressionResults at 0x7d523efb9cd0>,
np.str_('0.19'): <nilearn.glm.regression.RegressionResults at 0x7d523efb8650>,
np.str_('0.2'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f4770>,
np.str_('0.21'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f4e60>,
np.str_('0.22'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f51c0>,
np.str_('0.23'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f4d70>,
np.str_('0.24'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f4ef0>,
np.str_('0.25'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f6900>,
np.str_('0.26'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f51f0>,
np.str_('0.27'): <nilearn.glm.regression.RegressionResults at 0x7d523f1f78f0>,
np.str_('0.28'): <nilearn.glm.regression.RegressionResults at 0x7d523f20aa80>,
np.str_('0.29'): <nilearn.glm.regression.RegressionResults at 0x7d523f20ad50>,
np.str_('0.3'): <nilearn.glm.regression.RegressionResults at 0x7d523f376780>,
np.str_('0.31'): <nilearn.glm.regression.RegressionResults at 0x7d523f375670>,
np.str_('0.32'): <nilearn.glm.regression.RegressionResults at 0x7d523f375eb0>,
np.str_('0.33'): <nilearn.glm.regression.RegressionResults at 0x7d52478c5910>,
np.str_('0.34'): <nilearn.glm.regression.RegressionResults at 0x7d52478c6db0>,
np.str_('0.35'): <nilearn.glm.regression.RegressionResults at 0x7d52478c67e0>,
np.str_('0.36'): <nilearn.glm.regression.RegressionResults at 0x7d52478c67b0>,
np.str_('0.37'): <nilearn.glm.regression.RegressionResults at 0x7d52478c4f50>,
np.str_('0.38'): <nilearn.glm.regression.RegressionResults at 0x7d52478c5340>,
np.str_('0.39'): <nilearn.glm.regression.RegressionResults at 0x7d52478c7020>,
np.str_('0.4'): <nilearn.glm.regression.RegressionResults at 0x7d52478c7b60>,
np.str_('0.41'): <nilearn.glm.regression.RegressionResults at 0x7d524ca17470>,
np.str_('0.42'): <nilearn.glm.regression.RegressionResults at 0x7d523f2517f0>,
np.str_('0.43'): <nilearn.glm.regression.RegressionResults at 0x7d523f2514f0>,
np.str_('0.44'): <nilearn.glm.regression.RegressionResults at 0x7d52457b8e00>,
np.str_('0.45'): <nilearn.glm.regression.RegressionResults at 0x7d524792c3b0>,
np.str_('0.46'): <nilearn.glm.regression.RegressionResults at 0x7d524792fc20>,
np.str_('0.47'): <nilearn.glm.regression.RegressionResults at 0x7d523efc6720>,
np.str_('0.48'): <nilearn.glm.regression.RegressionResults at 0x7d523efc5be0>,
np.str_('0.49'): <nilearn.glm.regression.RegressionResults at 0x7d523c35e810>,
np.str_('0.5'): <nilearn.glm.regression.RegressionResults at 0x7d523c35c140>,
np.str_('0.51'): <nilearn.glm.regression.RegressionResults at 0x7d523c35f3e0>,
np.str_('0.52'): <nilearn.glm.regression.RegressionResults at 0x7d523c35c3b0>,
np.str_('0.53'): <nilearn.glm.regression.RegressionResults at 0x7d523c35da60>,
np.str_('0.54'): <nilearn.glm.regression.RegressionResults at 0x7d523c35f740>,
np.str_('0.55'): <nilearn.glm.regression.RegressionResults at 0x7d523c35c380>,
np.str_('0.56'): <nilearn.glm.regression.RegressionResults at 0x7d523c35c410>,
np.str_('0.57'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fb30>,
np.str_('0.58'): <nilearn.glm.regression.RegressionResults at 0x7d523c35f620>,
np.str_('0.59'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fe30>,
np.str_('0.6'): <nilearn.glm.regression.RegressionResults at 0x7d523c35c320>,
np.str_('0.61'): <nilearn.glm.regression.RegressionResults at 0x7d523c35db20>,
np.str_('0.62'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fdd0>,
np.str_('0.63'): <nilearn.glm.regression.RegressionResults at 0x7d523c35f6b0>,
np.str_('0.64'): <nilearn.glm.regression.RegressionResults at 0x7d523c35da30>,
np.str_('0.65'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fb90>,
np.str_('0.66'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fce0>,
np.str_('0.67'): <nilearn.glm.regression.RegressionResults at 0x7d523c35da90>,
np.str_('0.68'): <nilearn.glm.regression.RegressionResults at 0x7d523c35fcb0>,
np.str_('0.69'): <nilearn.glm.regression.RegressionResults at 0x7d523c35e930>,
np.str_('0.7'): <nilearn.glm.regression.RegressionResults at 0x7d523c35e5a0>,
np.str_('0.71'): <nilearn.glm.regression.RegressionResults at 0x7d523c35ff80>,
np.str_('0.72'): <nilearn.glm.regression.RegressionResults at 0x7d523c370bf0>,
np.str_('0.73'): <nilearn.glm.regression.RegressionResults at 0x7d523c373440>,
np.str_('0.74'): <nilearn.glm.regression.RegressionResults at 0x7d523c3731d0>,
np.str_('0.75'): <nilearn.glm.regression.RegressionResults at 0x7d523c372720>,
np.str_('0.76'): <nilearn.glm.regression.RegressionResults at 0x7d523c373110>,
np.str_('0.77'): <nilearn.glm.regression.RegressionResults at 0x7d523c370c20>,
np.str_('0.8'): <nilearn.glm.regression.RegressionResults at 0x7d523c3736b0>,
np.str_('0.81'): <nilearn.glm.regression.RegressionResults at 0x7d523c3724e0>,
np.str_('0.83'): <nilearn.glm.regression.RegressionResults at 0x7d523c372570>}