数据挖掘——单层感知器的Python实现

Python——scikit-learn实现单层感知器

scikit-learn 提供了感知器功能。和我们用过的其他功能类似，Perceptron类的构造器接受超参数设置。Perceptron类有fit_transform()和predict()方法。Perceptron类还提供了partial_fit()方法，允许分类器训练流式数据（streaming data）并做出预测。

# coding=utf-8
from sklearn.datasets import fetch_20newsgroups
from sklearn.metrics import f1_score, classification_report
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import Perceptron
categories = ['rec.sport.hockey', 'rec.sport.baseball', 'rec.autos']
newsgroups_train = fetch_20newsgroups(subset='train', categories=categories, remove=('headers', 'footers', 'quotes'))
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories, remove=('headers', 'footers', 'quotes'))

vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(newsgroups_train.data)
X_test = vectorizer.trasform(X_train, newsgroups_train.target)

classifier = Perceptron(n_iter=100, eta0=0.1)
classifier.fit_transform(X_train, newsgroups_train.target)
predictions = classifier.predict(X_test)
print classification_report(newsgroups_test.target, predictions)