mirror of
https://github.com/TheAlgorithms/Python.git
synced 2026-09-28 21:45:27 +08:00
priya-sundaram-dev
35b7074d2d
Re-enable the four scikit-learn machine-learning examples and the
neural-network perceptron that had been disabled (renamed to
.broken.txt / .DISABLED), and modernize them so they import and run
cleanly on current scikit-learn and pass the doctest CI:
machine_learning/gaussian_naive_bayes.py
machine_learning/random_forest_classifier.py
- Replace the removed sklearn.metrics.plot_confusion_matrix with
ConfusionMatrixDisplay.from_estimator (removed in scikit-learn 1.2).
- Drop the artificial time.sleep() calls.
machine_learning/gradient_boosting_regressor.py
machine_learning/random_forest_regressor.py
- Replace the removed load_boston dataset (removed in scikit-learn
1.2 for ethical reasons) with the bundled load_diabetes dataset so
the examples run offline.
- Avoid an unused-variable lint (RUF059).
neural_network/perceptron.py
- Use a dedicated seeded random.Random instance instead of the global
random state, so training is reproducible and thread-safe under the
parallel test runner.
- Cap training at epoch_number epochs so it always terminates even on
non-linearly-separable data (previously an unbounded while True).
- Have training() and sort() return their results instead of printing,
per the contribution guidelines, and update the doctests accordingly.
Requested by @cclauss in #8029; perceptron follow-up to #15206.
44 lines
1.1 KiB
Python
44 lines
1.1 KiB
Python
# Random Forest Classifier Example
|
|
|
|
from matplotlib import pyplot as plt
|
|
from sklearn.datasets import load_iris
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
from sklearn.metrics import ConfusionMatrixDisplay
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
|
|
def main():
|
|
"""
|
|
Random Forest Classifier Example using sklearn function.
|
|
Iris type dataset is used to demonstrate algorithm.
|
|
"""
|
|
# Load Iris dataset
|
|
iris = load_iris()
|
|
|
|
# Split dataset into train and test data
|
|
x = iris["data"] # features
|
|
y = iris["target"]
|
|
x_train, x_test, y_train, y_test = train_test_split(
|
|
x, y, test_size=0.3, random_state=1
|
|
)
|
|
|
|
# Random Forest Classifier
|
|
rand_for = RandomForestClassifier(random_state=42, n_estimators=100)
|
|
rand_for.fit(x_train, y_train)
|
|
|
|
# Display Confusion Matrix of Classifier
|
|
ConfusionMatrixDisplay.from_estimator(
|
|
rand_for,
|
|
x_test,
|
|
y_test,
|
|
display_labels=iris["target_names"],
|
|
cmap="Blues",
|
|
normalize="true",
|
|
)
|
|
plt.title("Normalized Confusion Matrix - IRIS Dataset")
|
|
plt.show()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|