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

Jump to bottom

Address FutureWarning From pandas.concat In gempyor #245

Merged
merged 4 commits into from
Jul 11, 2024
Merged

Address FutureWarning From pandas.concat In gempyor #245

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9e1bbce
Reduced multiple pd.concat calls into one
TimothyWillard Jun 28, 2024
55df84b
Merge updates from main into bug/address-gempyor-test-suite-future-we…
TimothyWillard Jun 28, 2024
7bd75af
Merge updates from main into bug/address-gempyor-test-suite-future-we…
TimothyWillard Jul 11, 2024
88d6559
Remove unneeded `set_index`
TimothyWillard Jul 11, 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
69 changes: 31 additions & 38 deletions flepimop/gempyor_pkg/src/gempyor/outcomes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def compute_all_multioutcomes(
bypass_seir_xr: xr.Dataset = None,
):
"""Compute delay frame based on temporally varying input. We load the seir sim corresponding to sim_id to write"""
hpar = pd.DataFrame(columns=["subpop", "quantity", "outcome", "value"])
hpar_list = []
all_data = {}
dates = pd.date_range(modinf.ti, modinf.tf, freq="D")

Expand Down Expand Up @@ -381,29 +381,24 @@ def compute_all_multioutcomes(
probabilities = np.repeat(probabilities[:, np.newaxis], len(dates), axis=1).T # duplicate in time
delays = np.repeat(delays[:, np.newaxis], len(dates), axis=1).T # duplicate in time
delays = np.round(delays).astype(int)
# write hpar before NPI
hpar = pd.concat(
[
hpar,
pd.DataFrame.from_dict(
{
"subpop": modinf.subpop_struct.subpop_names,
"quantity": ["probability"] * len(modinf.subpop_struct.subpop_names),
"outcome": [new_comp] * len(modinf.subpop_struct.subpop_names),
"value": probabilities[0] * np.ones(len(modinf.subpop_struct.subpop_names)),
}
),
pd.DataFrame.from_dict(
{
"subpop": modinf.subpop_struct.subpop_names,
"quantity": ["delay"] * len(modinf.subpop_struct.subpop_names),
"outcome": [new_comp] * len(modinf.subpop_struct.subpop_names),
"value": delays[0] * np.ones(len(modinf.subpop_struct.subpop_names)),
}
# Write hpar before NPI
subpop_names_len = len(modinf.subpop_struct.subpop_names)
hpar = pd.DataFrame(
{
"subpop": 2 * modinf.subpop_struct.subpop_names,
"quantity": (subpop_names_len * ["probability"])
+ (subpop_names_len * ["delay"]),
"outcome": 2 * subpop_names_len * [new_comp],
"value": np.concatenate(
(
probabilities[0] * np.ones(subpop_names_len),
delays[0] * np.ones(subpop_names_len),
)
),
],
axis=0,
}
)
hpar_list.append(hpar)
# Now tackle NPI
if npi is not None:
delays = NPI.reduce_parameter(
parameter=delays,
Expand Down Expand Up @@ -444,22 +439,15 @@ def compute_all_multioutcomes(
) # one draw per subpop
durations = np.repeat(durations[:, np.newaxis], len(dates), axis=1).T # duplicate in time
durations = np.round(durations).astype(int)

hpar = pd.concat(
[
hpar,
pd.DataFrame.from_dict(
{
"subpop": modinf.subpop_struct.subpop_names,
"quantity": ["duration"] * len(modinf.subpop_struct.subpop_names),
"outcome": [new_comp] * len(modinf.subpop_struct.subpop_names),
"value": durations[0] * np.ones(len(modinf.subpop_struct.subpop_names)),
}
),
],
axis=0,
hpar = pd.DataFrame(
data={
TimothyWillard marked this conversation as resolved.
Show resolved Hide resolved
"subpop": modinf.subpop_struct.subpop_names,
"quantity": subpop_names_len * ["duration"],
"outcome": subpop_names_len * [new_comp],
"value": durations[0] * np.ones(subpop_names_len),
}
)

hpar_list.append(hpar)
if npi is not None:
# import matplotlib.pyplot as plt
# plt.imshow(durations)
Expand Down Expand Up @@ -506,7 +494,12 @@ def compute_all_multioutcomes(
all_data[new_comp] = sum_outcome
df_p = dataframe_from_array(sum_outcome, modinf.subpop_struct.subpop_names, dates, new_comp)
outcomes = pd.merge(outcomes, df_p)

# Concat our hpar dataframes
hpar = (
pd.concat(hpar_list)
if hpar_list
else pd.DataFrame(columns=["subpop", "quantity", "outcome", "value"])
)
return outcomes, hpar


Expand Down
Loading