def fit_skew_t_pdf(
_1d_array,
skew_t_model=None,
fit_fixed_location=None,
fit_fixed_scale=None,
fit_initial_location=None,
fit_initial_scale=None,
):
if skew_t_model is None:
skew_t_model = ACSkewT_gen()
kwargs = {}
if fit_fixed_location is not None:
kwargs['floc'] = fit_fixed_location
if fit_fixed_scale is not None:
kwargs['fscale'] = fit_fixed_scale
if fit_initial_location is not None:
kwargs['loc'] = fit_initial_location
else:
kwargs['loc'] = _1d_array.mean()
if fit_initial_scale is not None:
kwargs['scale'] = fit_initial_scale
else:
kwargs['scale'] = _1d_array.std()
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array,
**kwargs,
)
if 32 < abs(shape):
warn('Refitting with the median to be the fixed location ...')
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array,
floc=median(_1d_array),
)
return _1d_array.size, location, scale, degree_of_freedom, shape
def fit_skew_t_pdf(_1d_array,
fit_initial_location=None,
fit_initial_scale=None):
_1d_array = _1d_array[
~check_nd_array_for_bad(_1d_array, raise_for_bad=False)]
keyword_arguments = {}
mean = _1d_array.mean()
if abs(mean) <= ALMOST_ZERO:
mean = 0
keyword_arguments["loc"] = mean
keyword_arguments["scale"] = _1d_array.std() / 2
skew_t_model = ACSkewT_gen()
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
if 24 < abs(shape):
warn("Refitting with fixed scale ...")
keyword_arguments["fscale"] = keyword_arguments["scale"]
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
if 24 < abs(shape):
warn("Refitting with fixed location ...")
keyword_arguments["floc"] = keyword_arguments["loc"]
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
return _1d_array.size, location, scale, degree_of_freedom, shape
def _fit_essentiality(f_x_s):
f_x_f = DataFrame(index=f_x_s.index,
columns=['N', 'DF', 'Shape', 'Location', 'Scale'])
for i, (f_i, f_v) in enumerate(f_x_s.iterrows()):
print('Fitting {} (@{}/{}) ...'.format(f_i, i, f_x_s.shape[0]))
# Fit skew-t PDF and save
skew_t = ACSkewT_gen()
f_v.dropna(inplace=True)
df, shape, location, scale = skew_t.fit(f_v)
f_x_f.ix[f_i, :] = f_v.size, df, shape, location, scale
return f_x_f
def _fit_essentiality(args):
feature_x_sample, plot, directory_path, bar_df, n_xgrids, overwrite, show_plot = args
feature_x_fit = DataFrame(
index=feature_x_sample.index,
columns=['N', 'DF', 'Shape', 'Location', 'Scale'])
# TODO: paralellize
for i, (f_i, f_v) in enumerate(feature_x_sample.iterrows()):
print_log('Fitting {} (@{}) ...'.format(f_i, i))
# Fit skew-t PDF on this gene
f_v.dropna(inplace=True)
skew_t = ACSkewT_gen()
n = f_v.size
df, shape, location, scale = skew_t.fit(f_v)
feature_x_fit.ix[f_i, :] = n, df, shape, location, scale
# Plot
if plot:
# Make an output filepath
if directory_path:
filepath = join(directory_path, 'essentiality_plots',
'{}.png'.format(f_i))
else:
filepath = None
_plot_essentiality(feature_x_sample.ix[f_i, :],
get_amp_mut_del(bar_df, f_i),
n=n,
df=df,
shape=shape,
location=location,
scale=scale,
n_x_grids=n_xgrids,
filepath=filepath,
overwrite=overwrite,
show_plot=show_plot)
return feature_x_fit
def fit_skew_t_pdf(
_1d_array,
fit_fixed_location=None,
fit_fixed_scale=None,
fit_initial_location=None,
fit_initial_scale=None,
):
_1d_array = _1d_array[
~check_nd_array_for_bad(_1d_array, raise_for_bad=False)]
keyword_arguments = {}
guessed_location = _1d_array.mean()
guessed_scale = _1d_array.std() / 2
if fit_fixed_location is not None:
keyword_arguments["floc"] = fit_fixed_location
if fit_fixed_scale is not None:
keyword_arguments["fscale"] = fit_fixed_scale
if fit_initial_location is not None:
keyword_arguments["loc"] = fit_initial_location
else:
keyword_arguments["loc"] = guessed_location
if fit_initial_scale is not None:
keyword_arguments["scale"] = fit_initial_scale
else:
keyword_arguments["scale"] = guessed_scale
skew_t_model = ACSkewT_gen()
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
if 24 < abs(shape):
warn("Refitting with scale = (standard deviation / 2) ...")
keyword_arguments["fscale"] = guessed_scale
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
if 24 < abs(shape):
warn("Refitting with location = mean ...")
keyword_arguments["floc"] = guessed_location
degree_of_freedom, shape, location, scale = skew_t_model.fit(
_1d_array, **keyword_arguments)
return _1d_array.size, location, scale, degree_of_freedom, shape
