Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Choice p labels #30

Merged
merged 3 commits into from
Feb 13, 2024
Merged

Choice p labels #30

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
14c0282
return upper boundary crossing as choice p in cpn training data
AlexanderFengler Feb 13, 2024
922235d
align _cpn_get_processed_data_for_theta with _mlp_get_processes_data_…
AlexanderFengler Feb 13, 2024
814c894
black
AlexanderFengler Feb 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 13 additions & 52 deletions ssms/dataset_generators/lan_mlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,9 +270,9 @@ def _mlp_get_processed_data_for_theta(self, random_seed_tuple):
kde_data = self._make_kde_data(simulations=simulations, theta=theta)

if len(simulations["metadata"]["possible_choices"]) == 2:
cpn_labels = np.expand_dims(simulations["choice_p"][0, 0], axis=0)
cpn_labels = np.expand_dims(simulations["choice_p"][0, 1], axis=0)
cpn_no_omission_labels = np.expand_dims(
simulations["choice_p_no_omission"][0, 0], axis=0
simulations["choice_p_no_omission"][0, 1], axis=0
)
else:
cpn_labels = simulations["choice_p"]
Expand Down Expand Up @@ -313,63 +313,24 @@ def _cpn_get_processed_data_for_theta(self, random_seed_tuple):
theta=theta_dict, random_seed=random_seed_tuple[1]
)

# Compute the choice probabilities
out_dict = {}
out_dict["choice_p"] = np.zeros(
(1, len(simulations["metadata"]["possible_choices"]))
)
out_dict["choice_p_no_omission"] = np.zeros(
(1, len(simulations["metadata"]["possible_choices"]))
)
out_dict["omission_p"] = {}
out_dict["theta"] = np.expand_dims(theta, axis=0)

for k, choice in enumerate(simulations["metadata"]["possible_choices"]):
out_dict["choice_p"][k] = np.array(
[
(simulations["choices"] == choice).sum()
/ simulations["choices"].flatten().shape[0]
]
)
out_dict["choice_p_no_omission"][k] = np.array(
[
(simulations["choices"][simulations["rts"] != -999] == choice).sum()
/ simulations["choices"].flatten().shape[0]
]
if len(simulations["metadata"]["possible_choices"]) == 2:
cpn_labels = np.expand_dims(simulations["choice_p"][0, 1], axis=0)
cpn_no_omission_labels = np.expand_dims(
simulations["choice_p_no_omission"][0, 1], axis=0
)

out_dict["omission_p"] = np.expand_dims(
np.array(
[
(simulations["rts"] == -999).sum()
/ simulations["choices"].flatten().shape[0]
]
),
axis=0,
)
out_dict["nogo_p"] = np.expand_dims(
np.array(
[
(simulations["rts"] == -999)
| (
simulations["choices"]
!= simulations["metadata"]["possible_choices"][0]
)
]
),
axis=0,
)
out_dict["go_p"] = 1 - out_dict["nogo_p"]
else:
cpn_labels = simulations["choice_p"]
cpn_no_omission_labels = simulations["choice_p_no_omission"]

return {
"cpn_data": np.expand_dims(theta, axis=0),
"cpn_labels": out_dict["choice_p"],
"cpn_labels": cpn_labels,
"cpn_no_omission_data": np.expand_dims(theta, axis=0),
"cpn_no_omission_labels": out_dict["choice_p_no_omission"],
"cpn_no_omission_labels": cpn_no_omission_labels,
"opn_data": np.expand_dims(theta, axis=0),
"opn_labels": out_dict["omission_p"],
"opn_labels": simulations["omission_p"],
"gonogo_data": np.expand_dims(theta, axis=0),
"gonogo_labels": out_dict["nogo_p"],
"gonogo_labels": simulations["nogo_p"],
"theta": np.expand_dims(theta, axis=0),
}

Expand Down
Loading