Skip to content

Add weekday-aware YTA prediction #166

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

Merged
zmek merged 2 commits into from
Apr 20, 2026
Merged

Add weekday-aware YTA prediction #166

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a61c27a
Add weekday-aware YTA prediction
zmek Apr 20, 2026
33e8865
refresh notebooks
zmek Apr 20, 2026
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
251 changes: 176 additions & 75 deletions docs/notebooks/3e_Predict_demand_from_patients_yet_to_arrive.md
View file
Open in desktop

Large diffs are not rendered by default.

Binary file added ...ents_yet_to_arrive_files/3e_Predict_demand_from_patients_yet_to_arrive_56_0.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
56 changes: 20 additions & 36 deletions docs/notebooks/3f_Evaluate_demand_predictions_for_patients_yet_to_arrive.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,20 +40,12 @@ params = prediction_inputs['config']

Processing: (6, 0)



Processing: (9, 30)



Processing: (12, 0)



Processing: (15, 30)



Processing: (22, 0)

Below I use the training, validation and test set dates set in `config.yaml` to retrieve the portions of the data needed for evaluation.
Expand Down Expand Up @@ -177,6 +169,7 @@ train_visits, valid_visits, test_visits = create_temporal_splits(
start_test_set_fake,
end_test_set_fake,
col_name="arrival_datetime",
verbose=False
)

# Train the EmpiricalIncomingAdmissionPredictor
Expand All @@ -187,40 +180,21 @@ train_visits_copy = train_visits.copy(deep=True)
if 'arrival_datetime' in train_visits_copy.columns:
train_visits_copy.set_index('arrival_datetime', inplace=True)

yta_model_empirical = EmpiricalIncomingAdmissionPredictor(verbose=True)
yta_model_empirical = EmpiricalIncomingAdmissionPredictor(verbose=False)
yta_model_empirical.fit(
train_visits_copy,
yta_time_interval=timedelta(minutes=15),
num_days=num_days,
start_time_col='arrival_datetime',
end_time_col='admitted_to_ward_datetime'
end_time_col='admitted_to_ward_datetime',
stratify_by_weekday=True
)
```

Split sizes: [2214, 710, 1584]
Calculating time-varying arrival rates for data provided, which spans 45 unique dates


EmpiricalIncomingAdmissionPredictor trained for these times: [(6, 0), (9, 30), (12, 0), (15, 30), (22, 0)]


using prediction window of 8:00:00 after the time of prediction


and time interval of 0:15:00 within the prediction window.


The error value for prediction will be 1e-07


To see the weights saved by this model, used the get_weights() method


EmpiricalIncomingAdmissionPredictor has been fitted with survival curve containing 881 time points

<style>#sk-container-id-1 {
/* Definition of color scheme common for light and dark mode */
--sklearn-color-text: black;
--sklearn-color-text: #000;
--sklearn-color-text-muted: #666;
--sklearn-color-line: gray;
/* Definition of color scheme for unfitted estimators */
--sklearn-color-unfitted-level-0: #fff5e6;
Expand Down Expand Up @@ -365,12 +339,21 @@ clickable and can be expanded/collapsed.
/* Toggleable label */
#sk-container-id-1 label.sk-toggleable__label {
cursor: pointer;
display: block;
display: flex;
width: 100%;
margin-bottom: 0;
padding: 0.5em;
box-sizing: border-box;
text-align: center;
align-items: start;
justify-content: space-between;
gap: 0.5em;
}

#sk-container-id-1 label.sk-toggleable__label .caption {
font-size: 0.6rem;
font-weight: lighter;
color: var(--sklearn-color-text-muted);
}

#sk-container-id-1 label.sk-toggleable__label-arrow:before {
Expand Down Expand Up @@ -523,7 +506,8 @@ a:visited.sk-estimator-doc-link {
height: 1em;
width: 1em;
text-decoration: none !important;
margin-left: 1ex;
margin-left: 0.5em;
text-align: center;
/* unfitted */
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
color: var(--sklearn-color-unfitted-level-1);
Expand Down Expand Up @@ -622,7 +606,7 @@ div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
}
</style><div id="sk-container-id-1" class="sk-top-container"><div class="sk-text-repr-fallback"><pre>EmpiricalIncomingAdmissionPredictor(filters={}, verbose=True)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class="sk-container" hidden><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-1" type="checkbox" checked><label for="sk-estimator-id-1" class="sk-toggleable__label sk-toggleable__label-arrow ">&nbsp;EmpiricalIncomingAdmissionPredictor<span class="sk-estimator-doc-link ">i<span>Not fitted</span></span></label><div class="sk-toggleable__content "><pre>EmpiricalIncomingAdmissionPredictor(filters={}, verbose=True)</pre></div> </div></div></div></div>
</style><div id="sk-container-id-1" class="sk-top-container"><div class="sk-text-repr-fallback"><pre>EmpiricalIncomingAdmissionPredictor(filters={})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class="sk-container" hidden><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-1" type="checkbox" checked><label for="sk-estimator-id-1" class="sk-toggleable__label sk-toggleable__label-arrow"><div><div>EmpiricalIncomingAdmissionPredictor</div></div><div><span class="sk-estimator-doc-link ">i<span>Not fitted</span></span></div></label><div class="sk-toggleable__content "><pre>EmpiricalIncomingAdmissionPredictor(filters={})</pre></div> </div></div></div></div>

### Compare survival curves across train, validation and test sets

Expand Down Expand Up @@ -677,7 +661,7 @@ for prediction_time in prediction_times:
)
```

The result can be plotted using EPUDD plots. The model appears as a series of vertical lines because the `EmpiricalIncomingAdmissionPredictor` is trained only on time of day, so there is minimal variation in the predicted distributions. This is included as a placeholder, to show how modelling of yet-to-arrive patients using past data on time to admission could be evaluated. You could modify the function to include a weekday/weekend variable, or replace it with a different approach based on moving averages (such as ARIMA).
The result can be plotted using EPUDD plots to allow for the evaluation of the model. (But note that this is showing the results of using fake data.)

```python
from patientflow.viz.epudd import plot_epudd
Expand Down
Binary file modified ...arrive_files/3f_Evaluate_demand_predictions_for_patients_yet_to_arrive_17_0.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
26 changes: 8 additions & 18 deletions docs/notebooks/4a_Organise_predictions_for_a_production_pipeline.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,8 +111,7 @@ yta_model.fit(

<style>#sk-container-id-1 {
/* Definition of color scheme common for light and dark mode */
--sklearn-color-text: #000;
--sklearn-color-text-muted: #666;
--sklearn-color-text: black;
--sklearn-color-line: gray;
/* Definition of color scheme for unfitted estimators */
--sklearn-color-unfitted-level-0: #fff5e6;
Expand Down Expand Up @@ -257,21 +256,12 @@ clickable and can be expanded/collapsed.
/* Toggleable label */
#sk-container-id-1 label.sk-toggleable__label {
cursor: pointer;
display: flex;
display: block;
width: 100%;
margin-bottom: 0;
padding: 0.5em;
box-sizing: border-box;
text-align: center;
align-items: start;
justify-content: space-between;
gap: 0.5em;
}

#sk-container-id-1 label.sk-toggleable__label .caption {
font-size: 0.6rem;
font-weight: lighter;
color: var(--sklearn-color-text-muted);
}

#sk-container-id-1 label.sk-toggleable__label-arrow:before {
Expand Down Expand Up @@ -424,8 +414,7 @@ a:visited.sk-estimator-doc-link {
height: 1em;
width: 1em;
text-decoration: none !important;
margin-left: 0.5em;
text-align: center;
margin-left: 1ex;
/* unfitted */
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
color: var(--sklearn-color-unfitted-level-1);
Expand Down Expand Up @@ -524,7 +513,7 @@ div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
}
</style><div id="sk-container-id-1" class="sk-top-container"><div class="sk-text-repr-fallback"><pre>ParametricIncomingAdmissionPredictor(filters={})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class="sk-container" hidden><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-1" type="checkbox" checked><label for="sk-estimator-id-1" class="sk-toggleable__label sk-toggleable__label-arrow"><div><div>ParametricIncomingAdmissionPredictor</div></div><div><span class="sk-estimator-doc-link ">i<span>Not fitted</span></span></div></label><div class="sk-toggleable__content "><pre>ParametricIncomingAdmissionPredictor(filters={})</pre></div> </div></div></div></div>
</style><div id="sk-container-id-1" class="sk-top-container"><div class="sk-text-repr-fallback"><pre>ParametricIncomingAdmissionPredictor(filters={})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class="sk-container" hidden><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-1" type="checkbox" checked><label for="sk-estimator-id-1" class="sk-toggleable__label sk-toggleable__label-arrow ">&nbsp;ParametricIncomingAdmissionPredictor<span class="sk-estimator-doc-link ">i<span>Not fitted</span></span></label><div class="sk-toggleable__content "><pre>ParametricIncomingAdmissionPredictor(filters={})</pre></div> </div></div></div></div>

We also need the aspirational curve parameters for the parametric model. These are loaded from the config file in the repository:

Expand Down Expand Up @@ -646,10 +635,10 @@ In notebook 3e, we used Poisson distributions to model yet-to-arrive patients. T
Let's call `predict()` on the model we just trained to see the result.

```python
prediction_context = {'unfiltered': {'prediction_time': prediction_time}}

# predict() returns a full probability distribution
yta_prediction = yta_model.predict(prediction_context,
yta_prediction = yta_model.predict(
prediction_time=prediction_time,
prediction_window=timedelta(hours=8),
x1=x1, y1=y1, x2=x2, y2=y2, max_value=50)
yta_distribution = yta_prediction['unfiltered']
Expand Down Expand Up @@ -746,7 +735,8 @@ Because this distribution is based on a Poisson model, the `DemandPredictor` can

```python
# predict_mean() returns just the Poisson rate (a single float)
yta_lambda = yta_model.predict_mean(prediction_context,
yta_lambda = yta_model.predict_mean(
prediction_time=prediction_time,
prediction_window=timedelta(hours=8),
x1=x1, y1=y1, x2=x2, y2=y2)

Expand Down
Loading
Loading