def setup_class(self):
"""
Create 2 gaussian models and some data with noise.
Create a fitter for the two models keeping the amplitude parameter
common for the two models.
"""
self.g1 = models.Gaussian1D(10, mean=14.9, stddev=.3)
self.g2 = models.Gaussian1D(10, mean=13, stddev=.4)
self.jf = JointFitter([self.g1, self.g2],
{self.g1: ['amplitude'],
self.g2: ['amplitude']}, [9.8])
self.x = np.arange(10, 20, .1)
y1 = self.g1(self.x)
y2 = self.g2(self.x)
with NumpyRNGContext(_RANDOM_SEED):
n = np.random.randn(100)
self.ny1 = y1 + 2 * n
self.ny2 = y2 + 2 * n
self.jf(self.x, self.ny1, self.x, self.ny2)
* `LinearLSQFitter`: `calc_uncertainties=False`
* `LevMarLSQFitter`: `calc_uncertainties=False`
* `SimplexLSQFitter`, `SLSQPLSQFitter`: N/A
* `JointFitter`: `models`, jointparameters`, `initvals` (must be given)
"""
if fitter_name.lower().startswith("lev") or fitter_name.lower().startswith(
"lm"):
return LevMarLSQFitter(**kwargs)
elif fitter_name.lower().startswith("lin"):
return LinearLSQFitter(**kwargs)
elif fitter_name.lower().startswith("sl"):
return SLSQPLSQFitter(**kwargs)
elif fitter_name.lower().startswith("sim"):
return SimplexLSQFitter(**kwargs)
elif fitter_name.lower().startswith("jo"):
return JointFitter(**kwargs)
else:
return fitter_name(**kwargs)
# ^ assume the `fitter_name` is already an astropy fitter
def get_model(model_name, *args, **kwargs):
""" Finds and returns the model with the given name.
For instance, it's customary to put degrees as args/kwargs for polynomial models:
`get_model("chebyshev2d", 2, 2)` or `get_model("chebyshev2d", x_degree=2,
y_degree=2)` return `Chebyshev2D(x_degree=2, y_degree=2)`.
For other cases, it depends: `get_model("gaussian1d")` returns
`Gaussian1D`, but sometimes you may want to initialize it with initial
values: `get_model("gaussian1d", amplitude=1, mean=0, stddev=1)`.
"""
# Try to find the model even if there are typos
