Output#
- class scipy.odr.Output(output)[source]#
The Output class stores the output of an ODR run.
Notes
Takes one argument for initialization, the return value from the function
odr. The attributes listed as “optional” above are only present ifodrwas run withfull_output=1.- Attributes:
- betandarray
Estimated parameter values, of shape (q,).
- sd_betandarray
Standard deviations of the estimated parameters, of shape (p,).
- cov_betandarray
Covariance matrix of the estimated parameters, of shape (p,p). Note that this cov_beta is not scaled by the residual variance res_var, whereas sd_beta is. This means
np.sqrt(np.diag(output.cov_beta * output.res_var))is the same result as output.sd_beta.- deltandarray, optional
Array of estimated errors in input variables, of same shape as x.
- epsndarray, optional
Array of estimated errors in response variables, of same shape as y.
- xplusndarray, optional
Array of
x + delta.- yndarray, optional
Array
y = fcn(x + delta).- res_varfloat, optional
Residual variance.
- sum_squarefloat, optional
Sum of squares error.
- sum_square_deltafloat, optional
Sum of squares of delta error.
- sum_square_epsfloat, optional
Sum of squares of eps error.
- inv_condnumfloat, optional
Inverse condition number (cf. ODRPACK UG p. 77).
- rel_errorfloat, optional
Relative error in function values computed within fcn.
- workndarray, optional
Final work array.
- work_inddict, optional
Indices into work for drawing out values (cf. ODRPACK UG p. 83).
- infoint, optional
Reason for returning, as output by ODRPACK (cf. ODRPACK UG p. 38).
- stopreasonlist of str, optional
info interpreted into English.
Methods
pprint()Pretty-print important results.