diff --git a/dist/pcntoolkit-0.30.post2-py3.12.egg b/dist/pcntoolkit-0.30.post2-py3.12.egg deleted file mode 100644 index 69167a63..00000000 Binary files a/dist/pcntoolkit-0.30.post2-py3.12.egg and /dev/null differ diff --git a/pcntoolkit/model/hbr.py b/pcntoolkit/model/hbr.py index f1fc5d98..275b24e9 100644 --- a/pcntoolkit/model/hbr.py +++ b/pcntoolkit/model/hbr.py @@ -7,24 +7,23 @@ @author: augub """ -from __future__ import print_function -from __future__ import division +from __future__ import division, print_function + from collections import OrderedDict +from functools import reduce +from itertools import product +import arviz as az import numpy as np import pymc as pm import pytensor -import arviz as az import xarray -from itertools import product -from functools import reduce from scipy import stats +from util.utils import create_poly_basis, expand_all -from util.utils import create_poly_basis -from util.utils import expand_all -from pcntoolkit.util.utils import cartesian_product -from pcntoolkit.util.bspline import BSplineBasis from pcntoolkit.model.SHASH import * +from pcntoolkit.util.bspline import BSplineBasis +from pcntoolkit.util.utils import cartesian_product def create_poly_basis(X, order): @@ -708,7 +707,7 @@ def Rhats(self, var_names=None, thin=1, resolution=100): testvars = az.extract(idata, group='posterior', var_names=var_names, combined=False) testvar_names = [var for var in list( - testvars.data_vars.keys()) if not '_samples' in var] + testvars.data_vars.keys()) if '_samples' not in var] rhat_dict = {} for var_name in testvar_names: var = np.stack(testvars[var_name].to_numpy())[:, ::thin] @@ -795,12 +794,21 @@ def get_new_dim_size(tup): dims = dims + pb.batch_effect_dim_names if self.name.startswith("slope") or self.name.startswith("offset_slope"): dims = dims + ["basis_functions"] - self.dist = from_posterior( - param=self.name, - samples=samples.to_numpy(), - shape=new_shape, - distribution=dist, - dims=dims, + if dims == []: + self.dist = from_posterior( + param=self.name, + samples=samples.to_numpy(), + shape=new_shape, + distribution=dist, + freedom=pb.configs["freedom"], + ) + else: + self.dist = from_posterior( + param=self.name, + samples=samples.to_numpy(), + shape=new_shape, + distribution=dist, + dims=dims, freedom=pb.configs["freedom"], ) diff --git a/pcntoolkit/normative.py b/pcntoolkit/normative.py index 3b0fdc47..9d20040b 100755 --- a/pcntoolkit/normative.py +++ b/pcntoolkit/normative.py @@ -1145,7 +1145,7 @@ def transfer(covfile, respfile, testcov=None, testresp=None, maskfile=None, if testcov is not None: yhat, s2 = nm.predict_on_new_sites(Xte, batch_effects_test) if testresp is not None: - Z[:, i] = nm.get_mcmc_zscores(Xte, Yte[:, i:i+1], **kwargs) + Z[:, i] = nm.get_mcmc_zscores(Xte, Yte[:, i:i+1], tsbefile=tsbefile, **kwargs) # We basically use normative.predict script here. if alg == 'blr': diff --git a/pcntoolkit/normative_model/norm_hbr.py b/pcntoolkit/normative_model/norm_hbr.py index e8a9b5d0..1631487b 100644 --- a/pcntoolkit/normative_model/norm_hbr.py +++ b/pcntoolkit/normative_model/norm_hbr.py @@ -317,10 +317,6 @@ def predict(self, Xs, X=None, Y=None, **kwargs): pred=pred_type, **kwargs, ) - # else: - # raise ValueError( - # "This is a transferred model. Please use predict_on_new_sites function." - # ) return yhat.squeeze(), s2.squeeze() @@ -339,6 +335,8 @@ def transfer(self, X, y, batch_effects): :return: The instance of the NormHBR object. """ self.hbr.transfer(X, y, batch_effects) + self.batch_effects_maps = [{v: i for i, v in enumerate(np.unique(batch_effects[:, j]))} + for j in range(batch_effects.shape[1])] self.configs["transferred"] = True return self @@ -452,7 +450,7 @@ def tune( ] X_dummy, batch_effects_dummy, Y_dummy = self.hbr.generate( - X_dummy, batch_effects_dummy, samples + X_dummy, batch_effects_dummy, samples, self.batch_effects_maps ) if informative_prior: @@ -490,7 +488,7 @@ def merge( X_dummy_ranges) X_dummy1, batch_effects_dummy1, Y_dummy1 = self.hbr.generate( - X_dummy1, batch_effects_dummy1, samples + X_dummy1, batch_effects_dummy1, samples, self.batch_effects_maps ) X_dummy2, batch_effects_dummy2, Y_dummy2 = nm.hbr.generate( X_dummy2, batch_effects_dummy2, samples @@ -512,7 +510,7 @@ def merge( def generate(self, X, batch_effects, samples=10): X, batch_effects, generated_samples = self.hbr.generate( - X, batch_effects, samples + X, batch_effects, samples, self.batch_effects_maps ) return X, batch_effects, generated_samples diff --git a/pcntoolkit/normative_parallel.py b/pcntoolkit/normative_parallel.py index fce6aaf3..6e557769 100755 --- a/pcntoolkit/normative_parallel.py +++ b/pcntoolkit/normative_parallel.py @@ -822,8 +822,8 @@ def collect_nm(processing_dir, if meta_data['outscaler'] in ['standardize', 'minmax', 'robminmax']: Y_scalers.append(meta_data['scaler_resp']) - meta_data['mean_resp'] = np.squeeze(np.column_stack(mY)) - meta_data['std_resp'] = np.squeeze(np.column_stack(sY)) + meta_data['mean_resp'] = [np.squeeze(np.concatenate(mY))] + meta_data['std_resp'] = [np.squeeze(np.concatenate(sY))] meta_data['scaler_cov'] = X_scalers meta_data['scaler_resp'] = Y_scalers diff --git a/pyproject.toml b/pyproject.toml index d61394b7..b61bf071 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "pcntoolkit" -version = "0.32.0" +version = "0.33.0" description = "Predictive Clinical Neuroscience Toolkit" authors = ["Andre Marquand"] license = "GNU GPLv3" diff --git a/tests/test_HBR.ipynb b/tests/test_HBR.ipynb index b17388dc..8239c443 100644 --- a/tests/test_HBR.ipynb +++ b/tests/test_HBR.ipynb @@ -36,7 +36,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
\n", - "Sampling for 16 seconds
\n", + "Sampling for a minute
\n", "\n", " Estimated Time to Completion:\n", " now\n", @@ -154,9 +154,9 @@ " \n", " \n", "