[machine learning] naive Bayesian classification of text -- Classification of people's names and countries

Naive Bayes

1. Based on a priori probability 、 Conditional probability gets joint probability , Then we get the posterior probability ;
2. Satisfy all characteristic independence assumptions , And equally important ;
3. It's a generative model ;
4. It can be used for multi classification problems of small data sets .

Code

import re

from sklearn.feature_extraction.text import CountVectorizer #  The text means , Until n-gram
from sklearn.model_selection import train_test_split #  Divide the data set 
from sklearn.naive_bayes import MultinomialNB #  Introduce Bayesian formula 


class LanguageDetector():

    def __init__(self, classifier=MultinomialNB()):
        self.classifier = classifier
        # ngram_range=(1,2) N-GRAM by 1,2
        self.vectorizer = CountVectorizer(ngram_range=(1,2), max_features=1000, preprocessor=self._remove_noise)
    
    #  Denoise 
    def _remove_noise(self, document):
        noise_pattern = re.compile("|".join(["http\S+", "\@\w+", "\#\w+"]))
        clean_text = re.sub(noise_pattern, "", document)
        return clean_text
    
    #  feature extraction 
    def features(self, X):
        return self.vectorizer.transform(X)

    #  Training 
    def fit(self, X, y):
        self.vectorizer.fit(X)
        self.classifier.fit(self.features(X), y)
   
    #  forecast 
    def predict(self, x):
        return self.classifier.predict(self.features([x]))
    
    #  Accuracy rate 
    def score(self, X, y):
        return self.classifier.score(self.features(X), y)

if __name__ == "__main__":
    in_f = open('data.csv')
    lines = in_f.readlines()
    in_f.close()
    dataset = [(line.strip()[:-3], line.strip()[-2:]) for line in lines]
    x, y = zip(*dataset)
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1)

    language_detector = LanguageDetector()
    language_detector.fit(x_train, y_train)
    print(language_detector.predict('This is an English sentence')) #  Test statement 
    print(language_detector.score(x_test, y_test))

Running results

['en']
0.9779444199382443

Data display of this article