def compute_timing_info_for_all_fits(data, fitter, fits):
genes = data.gene_names
regions = data.region_names
r2ds = data.region_to_dataset()
bin_edges = fits.change_distribution_params.bin_edges
bin_centers = fits.change_distribution_params.bin_centers
mu = init_array(np.NaN, len(genes), len(regions))
std = init_array(np.NaN, len(genes), len(regions))
weights = init_array(np.NaN, len(genes), len(regions), len(bin_centers))
for ig,g in enumerate(genes):
for ir,r in enumerate(regions):
dsfits = fits[r2ds[r]]
fit = dsfits.get((g,r))
if fit is None:
continue
mu[ig,ir], std[ig,ir] = fit.change_distribution_mean_std
weights[ig,ir,:] = fit.change_distribution_weights
return Bunch(
bin_edges = bin_edges,
bin_centers = bin_centers,
weights = weights,
mu=mu,
std=std,
genes=genes,
regions=regions,
age_scaler=data.age_scaler,
)
def compute_timing_info_for_all_fits(data, fitter, fits):
genes = data.gene_names
regions = data.region_names
r2ds = data.region_to_dataset()
bin_edges = fits.change_distribution_params.bin_edges
bin_centers = fits.change_distribution_params.bin_centers
mu = init_array(np.NaN, len(genes), len(regions))
std = init_array(np.NaN, len(genes), len(regions))
weights = init_array(np.NaN, len(genes), len(regions), len(bin_centers))
for ig, g in enumerate(genes):
for ir, r in enumerate(regions):
dsfits = fits[r2ds[r]]
fit = dsfits.get((g, r))
if fit is None:
continue
mu[ig, ir], std[ig, ir] = fit.change_distribution_mean_std
weights[ig, ir, :] = fit.change_distribution_weights
return Bunch(
bin_edges=bin_edges,
bin_centers=bin_centers,
weights=weights,
mu=mu,
std=std,
genes=genes,
regions=regions,
age_scaler=data.age_scaler,
)
def _add_dataset_correlation_fits_from_results_dictionary(dataset, ds_fits, dct_results):
"""This function converts the results of the job_splitting which is a flat dictionary to structures which
are easier to use and integrated into the dataset fits
"""
region_to_ix_original_inds = {}
for ir,r in enumerate(dataset.region_names):
series = dataset.get_several_series(dataset.gene_names,r)
region_to_ix_original_inds[r] = series.original_inds
for (ir,loo_point), levels in dct_results.iteritems():
n_iterations = len(levels)
r = dataset.region_names[ir]
if loo_point is None:
# Global fit - collect the parameters (theta, sigma, L) and compute a correlation matrix for the region
# the hack of using the key (None,r) to store these results can be removed if/when dataset fits is changed from a dictionary to a class with several fields
k = (None,r)
if k not in ds_fits:
ds_fits[k] = n_iterations*[None]
for iLevel, level in enumerate(levels):
ds_fits[k][iLevel] = level
level.correlations = covariance_to_correlation(level.sigma)
else:
# LOO point - collect the predictions
ix,iy = loo_point
g = dataset.gene_names[iy]
fit = ds_fits[(g,r)]
if not hasattr(fit, 'with_correlations'):
fit.with_correlations = [
Bunch(LOO_predictions=init_array(np.NaN, len(dataset.ages))) # NOTE: we place the predictions at the original indexes (before NaN were removed by the get_series)
for _ in xrange(n_iterations)
]
for iLevel, level_prediction in enumerate(levels):
orig_ix = region_to_ix_original_inds[r][ix]
fit.with_correlations[iLevel].LOO_predictions[orig_ix] = level_prediction
def _add_dataset_correlation_fits_from_results_dictionary(
dataset, ds_fits, dct_results):
"""This function converts the results of the job_splitting which is a flat dictionary to structures which
are easier to use and integrated into the dataset fits
"""
region_to_ix_original_inds = {}
for ir, r in enumerate(dataset.region_names):
series = dataset.get_several_series(dataset.gene_names, r)
region_to_ix_original_inds[r] = series.original_inds
for (ir, loo_point), levels in dct_results.iteritems():
n_iterations = len(levels)
r = dataset.region_names[ir]
if loo_point is None:
# Global fit - collect the parameters (theta, sigma, L) and compute a correlation matrix for the region
# the hack of using the key (None,r) to store these results can be removed if/when dataset fits is changed from a dictionary to a class with several fields
k = (None, r)
if k not in ds_fits:
ds_fits[k] = n_iterations * [None]
for iLevel, level in enumerate(levels):
ds_fits[k][iLevel] = level
level.correlations = covariance_to_correlation(level.sigma)
else:
# LOO point - collect the predictions
ix, iy = loo_point
g = dataset.gene_names[iy]
fit = ds_fits[(g, r)]
if not hasattr(fit, 'with_correlations'):
fit.with_correlations = [
Bunch(
LOO_predictions=init_array(np.NaN, len(dataset.ages))
) # NOTE: we place the predictions at the original indexes (before NaN were removed by the get_series)
for _ in xrange(n_iterations)
]
for iLevel, level_prediction in enumerate(levels):
orig_ix = region_to_ix_original_inds[r][ix]
fit.with_correlations[iLevel].LOO_predictions[
orig_ix] = level_prediction
def save_as_mat_files(data, fitter, fits, has_change_distributions):
for dataset in data.datasets:
filename = join(cache_dir(), fit_results_relative_path(dataset,fitter) + '.mat')
dataset_fits = fits[dataset.name]
print 'Saving mat file to {}'.format(filename)
shape = fitter.shape
gene_names = dataset.gene_names
gene_idx = {g:i for i,g in enumerate(gene_names)}
n_genes = len(gene_names)
region_names = dataset.region_names
region_idx = {r:i for i,r in enumerate(region_names)}
n_regions = len(region_names)
write_theta = shape.can_export_params_to_matlab()
if write_theta:
theta = init_array(np.NaN, shape.n_params(), n_genes,n_regions)
else:
theta = np.NaN
fit_scores = init_array(np.NaN, n_genes,n_regions)
LOO_scores = init_array(np.NaN, n_genes,n_regions)
fit_predictions = init_array(np.NaN, *dataset.expression.shape)
LOO_predictions = init_array(np.NaN, *dataset.expression.shape)
high_res_predictions = init_array(np.NaN, cfg.n_curve_points_to_plot, n_genes, n_regions)
scaled_high_res_ages = np.linspace(dataset.ages.min(), dataset.ages.max(), cfg.n_curve_points_to_plot)
original_high_res_ages = scalers.unify(dataset.age_scaler).unscale(scaled_high_res_ages)
if has_change_distributions:
change_distribution_bin_centers = fits.change_distribution_params.bin_centers
n_bins = len(change_distribution_bin_centers)
change_distribution_weights = init_array(np.NaN, n_bins, n_genes, n_regions)
else:
change_distribution_bin_centers = []
change_distribution_weights = []
for (g,r),fit in dataset_fits.iteritems():
series = dataset.get_one_series(g,r)
ig = gene_idx[g]
ir = region_idx[r]
fit_scores[ig,ir] = fit.fit_score
LOO_scores[ig,ir] = fit.LOO_score
if write_theta and fit.theta is not None:
theta[:,ig,ir] = fit.theta
if fit.fit_predictions is not None:
fit_predictions[series.original_inds,ig,ir] = fit.fit_predictions
if fit.LOO_predictions is not None:
LOO_predictions[series.original_inds,ig,ir] = fit.LOO_predictions
if fit.theta is not None:
high_res_predictions[:,ig,ir] = shape.f(fit.theta, scaled_high_res_ages)
change_weights = getattr(fit,'change_distribution_weights',None)
if change_weights is not None:
change_distribution_weights[:,ig,ir] = change_weights
mdict = dict(
gene_names = list_of_strings_to_matlab_cell_array(gene_names),
region_names = list_of_strings_to_matlab_cell_array(region_names),
theta = theta,
fit_scores = fit_scores,
LOO_scores = LOO_scores,
fit_predictions = fit_predictions,
LOO_predictions = LOO_predictions,
high_res_predictions = high_res_predictions,
high_res_ages = original_high_res_ages,
change_distribution_bin_centers = change_distribution_bin_centers,
change_distribution_weights = change_distribution_weights,
)
savemat(filename, mdict, oned_as='column')
def save_as_mat_files(data, fitter, fits, has_change_distributions):
for dataset in data.datasets:
filename = join(cache_dir(),
fit_results_relative_path(dataset, fitter) + '.mat')
dataset_fits = fits[dataset.name]
print 'Saving mat file to {}'.format(filename)
shape = fitter.shape
gene_names = dataset.gene_names
gene_idx = {g: i for i, g in enumerate(gene_names)}
n_genes = len(gene_names)
region_names = dataset.region_names
region_idx = {r: i for i, r in enumerate(region_names)}
n_regions = len(region_names)
write_theta = shape.can_export_params_to_matlab()
if write_theta:
theta = init_array(np.NaN, shape.n_params(), n_genes, n_regions)
else:
theta = np.NaN
fit_scores = init_array(np.NaN, n_genes, n_regions)
LOO_scores = init_array(np.NaN, n_genes, n_regions)
fit_predictions = init_array(np.NaN, *dataset.expression.shape)
LOO_predictions = init_array(np.NaN, *dataset.expression.shape)
high_res_predictions = init_array(np.NaN, cfg.n_curve_points_to_plot,
n_genes, n_regions)
scaled_high_res_ages = np.linspace(dataset.ages.min(),
dataset.ages.max(),
cfg.n_curve_points_to_plot)
original_high_res_ages = scalers.unify(
dataset.age_scaler).unscale(scaled_high_res_ages)
if has_change_distributions:
change_distribution_bin_centers = fits.change_distribution_params.bin_centers
n_bins = len(change_distribution_bin_centers)
change_distribution_weights = init_array(np.NaN, n_bins, n_genes,
n_regions)
else:
change_distribution_bin_centers = []
change_distribution_weights = []
for (g, r), fit in dataset_fits.iteritems():
series = dataset.get_one_series(g, r)
ig = gene_idx[g]
ir = region_idx[r]
fit_scores[ig, ir] = fit.fit_score
LOO_scores[ig, ir] = fit.LOO_score
if write_theta and fit.theta is not None:
theta[:, ig, ir] = fit.theta
if fit.fit_predictions is not None:
fit_predictions[series.original_inds, ig,
ir] = fit.fit_predictions
if fit.LOO_predictions is not None:
LOO_predictions[series.original_inds, ig,
ir] = fit.LOO_predictions
if fit.theta is not None:
high_res_predictions[:, ig,
ir] = shape.f(fit.theta,
scaled_high_res_ages)
change_weights = getattr(fit, 'change_distribution_weights', None)
if change_weights is not None:
change_distribution_weights[:, ig, ir] = change_weights
mdict = dict(
gene_names=list_of_strings_to_matlab_cell_array(gene_names),
region_names=list_of_strings_to_matlab_cell_array(region_names),
theta=theta,
fit_scores=fit_scores,
LOO_scores=LOO_scores,
fit_predictions=fit_predictions,
LOO_predictions=LOO_predictions,
high_res_predictions=high_res_predictions,
high_res_ages=original_high_res_ages,
change_distribution_bin_centers=change_distribution_bin_centers,
change_distribution_weights=change_distribution_weights,
)
savemat(filename, mdict, oned_as='column')
