Spaces:
Runtime error
Runtime error
File size: 3,647 Bytes
471733b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
import gradio as gr
import numpy as np
import plotly.graph_objects as go
from sklearn.tree import DecisionTreeRegressor
rng = np.random.default_rng(0)
X = np.sort(5 * rng.random((80, 1)), axis=0)
y = np.sin(X).ravel()
y[::5] += 3 * (0.5 - rng.random(16))
md_description = """
# A 1D regression with decision tree.
The [decision trees](https://scikit-learn.org/stable/modules/tree.html#tree) is used to fit a sine curve with addition noisy observation. As a result, it learns local linear regressions approximating the sine curve.
We can see that if the maximum depth of the tree (controlled by the max_depth parameter) is set too high, the decision trees learn too fine details of the training data and learn from the noise, i.e. they overfit.
"""
def make_regression(model_1_depth, model_2_depth):
regr_1 = DecisionTreeRegressor(max_depth=model_1_depth, random_state=0)
regr_2 = DecisionTreeRegressor(max_depth=model_2_depth, random_state=0)
regr_1.fit(X, y)
regr_2.fit(X, y)
# Predict
X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
y_1 = regr_1.predict(X_test)
y_2 = regr_2.predict(X_test)
fig = go.Figure()
fig.add_trace(go.Scatter(x=X[:, 0], y=y, mode="markers", name="data"))
fig.add_trace(
go.Scatter(x=X_test[:, 0], y=y_1, mode="lines", name=f"max_depth={model_1_depth}")
)
fig.add_trace(
go.Scatter(x=X_test[:, 0], y=y_2, mode="lines", name=f"max_depth={model_2_depth}")
)
fig.update_layout(title="Decision Tree Regression")
fig.update_xaxes(title_text="data")
fig.update_yaxes(title_text="target")
return fig, make_example(model_1_depth, model_2_depth)
def make_example(model_1_depth, model_2_depth):
return f"""
With the following code you can reproduce this example with the current values of the sliders and the same data in a notebook:
```python
import numpy as np
import plotly.graph_objects as go
from sklearn.tree import DecisionTreeRegressor
rng = np.random.default_rng(0)
X = np.sort(5 * rng.random((80, 1)), axis=0)
y = np.sin(X).ravel()
y[::5] += 3 * (0.5 - rng.random(16))
regr_1 = DecisionTreeRegressor(max_depth={model_1_depth}, random_state=0)
regr_2 = DecisionTreeRegressor(max_depth={model_2_depth}, random_state=0)
regr_1.fit(X, y)
regr_2.fit(X, y)
# Predict
X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
y_1 = regr_1.predict(X_test)
y_2 = regr_2.predict(X_test)
fig = go.Figure()
fig.add_trace(go.Scatter(x=X[:,0], y=y, mode='markers', name='data'))
fig.add_trace(go.Scatter(x=X_test[:,0], y=y_1, mode='lines', name=f"Model 1 max_depth={model_1_depth}"))
fig.add_trace(go.Scatter(x=X_test[:,0], y=y_2, mode='lines', name=f"Model 2 max_depth={model_2_depth}"))
fig.update_layout(title='Decision Tree Regression')
fig.update_xaxes(title_text='data')
fig.update_yaxes(title_text='target')
fig.show()
```
"""
with gr.Blocks() as demo:
with gr.Row():
gr.Markdown(md_description)
with gr.Row():
with gr.Column():
slider_1 = gr.Slider(minimum=1, maximum=10, label="Model 1 max_depth", step=1)
slider_2 = gr.Slider(minimum=1, maximum=10, label="Model 2 max_depth", step=1)
with gr.Column():
plot = gr.Plot(label="Output")
with gr.Row():
example = gr.Markdown(make_example(slider_1.value, slider_2.value))
slider_1.change(fn=make_regression, inputs=[slider_1, slider_2], outputs=[plot, example])
slider_2.change(fn=make_regression, inputs=[slider_1, slider_2], outputs=[plot, example])
demo.launch()
|