42 lines
1.4 KiB
Python
42 lines
1.4 KiB
Python
"""
|
|
Use the naive bayes classifier to classify the iris data set.
|
|
|
|
- This is an example of a supervised ML algorithm
|
|
- it has labels on the training data
|
|
- you tell the model: this is class X during training
|
|
"""
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
|
|
from sklearn import datasets
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.naive_bayes import GaussianNB
|
|
|
|
iris = datasets.load_iris()
|
|
print(iris.data.shape)
|
|
|
|
# split into training and test data
|
|
x_train, x_test, y_train, y_test = train_test_split(
|
|
iris.data, iris.target, test_size=0.2, random_state=0
|
|
)
|
|
|
|
# use a gaussian NB classifier
|
|
classifier = GaussianNB()
|
|
# train on the split data
|
|
classifier.fit(x_train, y_train)
|
|
# test the model and print it's accurecy
|
|
score = classifier.score(x_test, y_test)
|
|
print(score)
|
|
|
|
fig, axes = plt.subplots(2, 2, figsize=(12, 10))
|
|
for idx, ax in enumerate(axes.flat):
|
|
x_range = np.linspace(iris.data[:, idx].min() - 1, iris.data[:, idx].max() + 1, 200)
|
|
for class_idx, class_name in enumerate(iris.target_names):
|
|
mean = classifier.theta_[class_idx, idx]
|
|
var = classifier.var_[class_idx, idx]
|
|
gaussian = np.exp(-0.5 * (x_range - mean) ** 2 / var) / np.sqrt(2 * np.pi * var)
|
|
ax.plot(x_range, gaussian, label=class_name)
|
|
ax.set_title(iris.feature_names[idx])
|
|
ax.legend()
|
|
fig.savefig('naivebayes_iris_distributions.png', dpi=150, bbox_inches='tight')
|