import random
import os
import json
import numpy as np
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import zero_one_loss
from sklearn.naive_bayes import MultinomialNB
import Bayes as bayes
base_dir = os.path.dirname(__file__)
n_estimators = 500
learning_rate = 1.
vocabList = bayes.build_key_word(os.path.join(base_dir, "train.txt"))
line_cut, label = bayes.loadDataSet(os.path.join(base_dir, "train.txt"))
train_mood_array = bayes.setOfWordsListToVecTor(vocabList, line_cut)
test_word_array = []
test_word_arrayLabel = []
testCount = 100 # 从中随机选取100条用来测试，并删除原来的位置
for i in range(testCount):
try:
randomIndex = int(random.uniform(0, len(train_mood_array)))
test_word_arrayLabel.append(label[randomIndex])
test_word_array.append(train_mood_array[randomIndex])
del (train_mood_array[randomIndex])
del (label[randomIndex])
except Exception as e:
print(e)
multi = MultinomialNB()
from pylab import mpl
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import label_binarize
if __name__ == '__main__':
mpl.rcParams['font.sans-serif'] = ['SimHei']
fig = plt.figure()
ax = fig.add_subplot(111)
n_estimators = 500
learning_rate = 1.
vocabList = bayes.build_key_word("../train/train.txt")
line_cut, label = bayes.loadDataSet("../train/train.txt")
train_mood_array = bayes.setOfWordsListToVecTor(vocabList, line_cut)
test_word_array = []
test_word_arrayLabel = []
testCount = 100 # 从中随机选取100条用来测试，并删除原来的位置
for i in range(testCount):
try:
randomIndex = int(random.uniform(0, len(train_mood_array)))
test_word_arrayLabel.append(label[randomIndex])
test_word_array.append(train_mood_array[randomIndex])
del (train_mood_array[randomIndex])
del (label[randomIndex])
except Exception as e:
print(e)
multi = MultinomialNB()