File size: 5,081 Bytes
861c542 ac48ca6 2d851fe ac48ca6 8fde30f ac48ca6 2d851fe ac48ca6 2d851fe ac48ca6 2d851fe ac48ca6 2d851fe |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
import gradio as gr
import matplotlib.pyplot as plt
from collections import OrderedDict
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
def compare(number1, number2):
if number1 > number2:
number2 = number1
return number2
def do_train(random_state, n_samples, min_estimators, max_estimators):
RANDOM_STATE = random_state
# Generate a binary classification dataset.
X, y = make_classification(
n_samples=n_samples,
n_features=25,
n_clusters_per_class=1,
n_informative=15,
random_state=RANDOM_STATE,
)
# NOTE: Setting the `warm_start` construction parameter to `True` disables
# support for parallelized ensembles but is necessary for tracking the OOB
# error trajectory during training.
ensemble_clfs = [
(
"RandomForestClassifier, max_features='sqrt'",
RandomForestClassifier(
warm_start=True,
oob_score=True,
max_features="sqrt",
random_state=RANDOM_STATE,
),
),
(
"RandomForestClassifier, max_features='log2'",
RandomForestClassifier(
warm_start=True,
max_features="log2",
oob_score=True,
random_state=RANDOM_STATE,
),
),
(
"RandomForestClassifier, max_features=None",
RandomForestClassifier(
warm_start=True,
max_features=None,
oob_score=True,
random_state=RANDOM_STATE,
),
),
]
# Map a classifier name to a list of (<n_estimators>, <error rate>) pairs.
error_rate = OrderedDict((label, []) for label, _ in ensemble_clfs)
# Range of `n_estimators` values to explore.
min_estimators = 15
max_estimators = 150
for label, clf in ensemble_clfs:
for i in range(min_estimators, max_estimators + 1, 5):
clf.set_params(n_estimators=i)
clf.fit(X, y)
# Record the OOB error for each `n_estimators=i` setting.
oob_error = 1 - clf.oob_score_
error_rate[label].append((i, oob_error))
# Generate the "OOB error rate" vs. "n_estimators" plot.
fig, ax = plt.subplots()
for label, clf_err in error_rate.items():
xs, ys = zip(*clf_err)
ax.plot(xs, ys, label=label)
ax.set_xlim(min_estimators, max_estimators)
ax.set_xlabel("n_estimators")
ax.set_ylabel("OOB error rate")
ax.legend(loc="upper right")
return fig
model_card = f"""
## Description
The ``RandomForestClassifier`` is trained using bootstrap aggregation, where each new tree is fit from a bootstrap sample of the training observations $z_i = (x_i, y_i)$.
The out-of-bag (OOB) error is the average error for each $z_i$ calculated using predictions from the trees that do not contain
$z_i$ in their respective bootstrap sample. This allows the ``RandomForestClassifier`` to be fit and validated whilst being trained.
You can play around with ``number of samples``, ``random seed``, ``min estimators`` and ``max estimators`` controlling the number of trees.
The example demonstrates how the OOB error can be measured at the addition of each new tree during training.
The resulting plot allows a practitioner to approximate a suitable value of ``n_estimators`` at which the error stabilizes.
## Dataset
Simulation data
"""
with gr.Blocks() as demo:
gr.Markdown('''
<div>
<h1 style='text-align: center'>Out-of-Bag(OOB) Errors for Random Forests</h1>
</div>
''')
gr.Markdown(model_card)
gr.Markdown("Author: <a href=\"https://huggingface.co/bharat-raghunathan\">Bharat Raghunathan</a>. Based on the example from <a href=\"https://scikit-learn.org/stable/auto_examples/ensemble/plot_ensemble_oob.html#sphx-glr-auto-examples-ensemble-plot-ensemble-oob-py\">scikit-learn</a>")
n_samples = gr.Slider(minimum=500, maximum=5000, step=500, value=500, label="Number of samples")
random_state = gr.Slider(minimum=0, maximum=2000, step=1, value=0, label="Random seed")
min_estimators = gr.Slider(minimum=5, maximum=300, step=5, value=15, label="Minimum number of trees")
max_estimators = gr.Slider(minimum=5, maximum=300, step=5, value=150, label="Maximum number of trees")
min_estimators.change(compare, [min_estimators, max_estimators], max_estimators)
with gr.Row():
with gr.Column():
plot = gr.Plot()
n_samples.change(fn=do_train, inputs=[n_samples, random_state, min_estimators, max_estimators], outputs=[plot])
random_state.change(fn=do_train, inputs=[n_samples, random_state, min_estimators, max_estimators], outputs=[plot])
min_estimators.change(fn=do_train, inputs=[n_samples, random_state, min_estimators, max_estimators], outputs=[plot])
max_estimators.change(fn=do_train, inputs=[n_samples, random_state, min_estimators, max_estimators], outputs=[plot])
demo.queue().launch()
|