Update app.py
Browse files
app.py
CHANGED
|
@@ -72,20 +72,20 @@ def app_fn(
|
|
| 72 |
|
| 73 |
return fig, df_coverage
|
| 74 |
|
| 75 |
-
title = "
|
| 76 |
with gr.Blocks() as demo:
|
| 77 |
gr.Markdown(f"# {title}")
|
| 78 |
gr.Markdown(
|
| 79 |
"""
|
| 80 |
-
|
| 81 |
The app uses the [Quantile Loss](https://en.wikipedia.org/wiki/Quantile_regression#Quantile_loss_function) \
|
| 82 |
to predict the lower and upper quantiles with Gradient Boosting Regression. The data used in this example \
|
| 83 |
is generated through the equation passed in the Formula textbox heteroscedasticity noise is introduced to \
|
| 84 |
make the data more realistic. The app also shows the coverage of the intervals on the train and test data.
|
| 85 |
|
| 86 |
-
|
| 87 |
|
| 88 |
-
[
|
| 89 |
"""
|
| 90 |
)
|
| 91 |
with gr.Row():
|
|
|
|
| 72 |
|
| 73 |
return fig, df_coverage
|
| 74 |
|
| 75 |
+
title = "Prediction Intervals with Gradient Boosting Regression"
|
| 76 |
with gr.Blocks() as demo:
|
| 77 |
gr.Markdown(f"# {title}")
|
| 78 |
gr.Markdown(
|
| 79 |
"""
|
| 80 |
+
This app shows how to use Gradient Boosting Regression to predict intervals. \
|
| 81 |
The app uses the [Quantile Loss](https://en.wikipedia.org/wiki/Quantile_regression#Quantile_loss_function) \
|
| 82 |
to predict the lower and upper quantiles with Gradient Boosting Regression. The data used in this example \
|
| 83 |
is generated through the equation passed in the Formula textbox heteroscedasticity noise is introduced to \
|
| 84 |
make the data more realistic. The app also shows the coverage of the intervals on the train and test data.
|
| 85 |
|
| 86 |
+
Write equations using x as the variable and Python notation. Other supported functions are sin, cos, tan, exp, log, sqrt, and abs.
|
| 87 |
|
| 88 |
+
See original sklearn example [here](https://scikit-learn.org/stable/auto_examples/ensemble/plot_gradient_boosting_quantile.html#sphx-glr-auto-examples-ensemble-plot-gradient-boosting-quantile-py).
|
| 89 |
"""
|
| 90 |
)
|
| 91 |
with gr.Row():
|