Naive Bayes algorithm example in Python

The Naive Bayes algorithm is one of the classic machine learning algorithms. It is widely used, especially in fields such as text classification and spam filtering, and has high accuracy and efficiency. This article will introduce the implementation of the Naive Bayes algorithm in Python and illustrate its application with examples.

1. Introduction to Naive Bayes Algorithm
The Naive Bayes algorithm is a classification algorithm based on Bayes theorem and the assumption of feature independence. The basic idea is to infer the classification of new data through the conditional probability of known category data. Specifically, before classification, the model needs to be trained, that is, the conditional probability of each feature under each category is calculated. Then when classifying, the probability that the new data belongs to each category is calculated according to Bayes' theorem, and the category corresponding to the maximum probability is selected as the prediction result. Since the features are assumed to be independent, the algorithm is named "Naive Bayes".

2. Implementation of Naive Bayes in Python
There are multiple libraries or modules in Python that can be used to implement the Naive Bayes algorithm, such as scikit-learn, nltk, gensim, etc. This article will introduce how to implement the naive Bayes algorithm using the scikit-learn library.

1. Prepare the data set
First you need to prepare a data set to train and test the classifier. In this example, we select the "Spambase Data Set" on UCI Machine Learning Repository. This data set contains 4601 emails, of which 1813 are spam emails and 2788 are normal emails. This data set can be downloaded and stored in CSV format.

2. Import the data and divide the training set and test set
Use the read_csv function of the pandas library to read the CSV file into DataFrame format and divide it into a training set and a test set. The code is as follows:

import pandas as pd
from sklearn.model_selection import train_test_split

Import data

df = pd.read_csv('spambase.csv')

Divide the training set and test set

X = df.iloc[:, :-1]
y = df.iloc[:, -1]
X_train, X_test, y_train, y_test = train_test_split (X, y, test_size=0.3, random_state=42)

3. Training model
Use the MultinomialNB class of the sklearn library to initialize a naive Bayes classification model and use the training data for model training, code As follows:

from sklearn.naive_bayes import MultinomialNB

Training model

clf = MultinomialNB()
clf.fit(X_train, y_train)

4. Test model
Use the test set to test the classifier and calculate the classification accuracy. The code is as follows:

from sklearn.metrics import accuracy_score

Test model

y_pred = clf.predict(X_test)
acc = accuracy_score(y_test, y_pred)
print('Accuracy: {:.2f}%'.format(acc*100))

5. Apply model
Use the trained model to classify new data and output the prediction results. The code is as follows:

Apply model

new_data = [[0.05, 0.08, 0.00, 0.00, 0.04, 0.00, 0.00, 0.14, 0.03, 0.10, 0.05, 0.00, 0.02, 0.04, 0.00, 0.10, 0.05, 0.01, 0.04, 0.67, 2.16, 10.00, 136.00, 0.00, 0.96, 0.00, 0.00, 0.00, 0.32, 0.01]]
prediction = clf.predict(new_data)
print('Prediction:', prediction)

3. Example analysis
This example uses a classification problem, and the characteristics are Frequency of words in emails, with the goal of classifying emails into spam and normal emails. After training, the naive Bayes algorithm was used for classification and an accuracy of 90.78% was obtained. It can be seen from the results that in certain application situations, Naive Bayes has excellent classification results.

4. Conclusion
The Naive Bayes algorithm is a simple and effective classification method, which is widely used in fields such as text classification and spam filtering. The scikit-learn library in Python provides a convenient implementation of the naive Bayes classifier, which can well support the training, testing and application of the model.

The above is the detailed content of Naive Bayes algorithm example in Python. For more information, please follow other related articles on the PHP Chinese website!