def trainMaxentropy(trainFeatures, trainLabels):
import shorttext
from shorttext.classifiers import MaxEntClassifier
classifier = MaxEntClassifier()
clf = make_pipeline(DictVectorizer(sparse=True),
MaxentClassifier(encoding=None, weights=0))
scores = cross_val_score(clf, trainFeatures, trainLabels, cv=5)
clf.fit(trainFeatures, trainLabels)
return clf, scores.mean(), scores
# /usr/bin/env python3
# -*- coding:utf-8 -*-
import sys
import math
from collections import defaultdict
from nltk import MaxentClassifier
# play outlook temperature humidity windy
maxent = MaxentClassifier()
class MaxEnt:
def __init__(self):
self._samples = [] # 样本集, 元素是[y,x1,x2,...,xn]的元组
self._Y = set([]) # 标签集合,相当于去重之后的y
self._numXY = defaultdict(int) # Key是(xi,yi)对，Value是count(xi,yi)
self._N = 0 # 样本数量
self._n = 0 # 特征对(xi,yi)总数量
self._xyID = {} # 对(x,y)对做的顺序编号(ID), Key是(xi,yi)对,Value是ID
self._C = 0 # 样本最大的特征数量,用于求参数时的迭代，见IIS原理说明
self._ep_ = [] # 样本分布的特征期望值
self._ep = [] # 模型分布的特征期望值
self._w = [] # 对应n个特征的权值
self._lastw = [] # 上一轮迭代的权值
self._EPS = 0.01 # 判断是否收敛的阈值
def load_data(self, filename):
for line in open(filename, "r"):
sample = line.strip().split("\t")
if len(sample) < 2: # 至少：标签+一个特征
