from nltk.classify import accuracy as nltk_accuracy
def gender_features(word, num_letters=2):
return {'feature': word[-num_letters:].lower()}
if __name__ == '__main__':
labeled_names = ([(name, 'male') for name in names.words('male.txt')] +
[(name, 'female') for name in names.words('female.txt')])
random.seed(7)
random.shuffle(labeled_names)
input_names = ['Leonardo', 'Amy', 'Sam', 'Rock']
for i in range(1, 5):
print '\n Number of letters :', i
featuresets = [(gender_features(n, i), gender)
for (n, gender) in labeled_names]
train_set, test_set = featuresets[500:], featuresets[:500]
classifier = NaiveBayesClassifier.train(train_set)
print 'Accuracy ==> ', str(
100 * nltk_accuracy(classifier, test_set)) + str('%')
# test the input data
for name in input_names:
print name, '==>', classifier.classify(gender_features(name, i))
#importing library for naivebayes accuracy and names
import random
from nltk import NaiveBayesClassifier
from nltk.classify import accuracy as nltk_accuracy
from nltk.corpus import names
#defining letter N as extract feature
def extract_features(word,N=2):
last_n_letters=word[-N:]
return{'feature':last_n_letters.lower()}
#Create the training data using labeled names alredy available in male file
if __name__=='__main__':
male_list=[(name,'male') for name in names.words('male.txt')]
female_list=[(name,'female') for name in names.words('female.txt')]
data=(male_list+female_list)
random.seed(5)
random.shuffle(data)
#data to be tested on
namesInput=['rajesh','gaurav','swati','shubha']
#declaring train and test data
train_sample=int(0.8*len(data))
for i in range(1,6):
print("\n number of end letters:",i)
features=[(extract_features(n,i),gender)for (n,gender)in data]#feature exraction for n with gender
train_data,test_data=features[:train_sample],features[train_sample:]
classifier=NaiveBayesClassifier.train(train_data)#defining classifier
accuracy_classifier=round(100*nltk_accuracy(classifier,test_data),2)#accuracy of classifier called as this
print('accuracy='+str(accuracy_classifier)+'%')
for name in namesInput:#classified with listing name
print(name,'==>',classifier.classify(extract_features(name,1)))
if __name__ == '__main__':
# 提取标记名称
labeled_names = ([(name, 'male') for name in names.words('male.txt')]) + \
([(name, 'female') for name in names.words('female.txt')])
# 设置随机生成数的种子值，并混合搅乱训练数据
random.seed(7)
random.shuffle(labeled_names)
# 定义一些输入的姓名
input_names = ['Leonardo', 'Amy', 'Sam', 'Werner']
# 搜索参数空间
for i in range(1, 5):
print("取参数为{}".format(i))
featuresets = [(gender_features(n, i), gender)
for (n, gender) in labeled_names]
# 分割数据为训练集和测试集
train_set, test_set = featuresets[500:], featuresets[:500]
# 用朴素贝叶斯分类器做分类
classifier = NaiveBayesClassifier.train(train_set)
# 打印分类器准确性
print(u"准确性：{}%".format(100 * nltk_accuracy(classifier, test_set)))
# 为输入姓名预测结果
for name in input_names:
print("{} ==> {}".format(
name, classifier.classify(gender_features(name, i))))
# 构建模型，训练模型
from nltk import NaiveBayesClassifier
from nltk.classify import accuracy as nltk_accuracy
np.random.shuffle(dataset)
rows=int(len(dataset)*0.8) # 80%为train set
train_set,test_set=dataset[:rows],dataset[rows:]
print('Num of train_set: ',len(train_set),
'/nNum of test_set: ',len(test_set))
clf=NaiveBayesClassifier.train(train_set)
# 查看该模型在test set上的表现
acc=nltk_accuracy(clf,test_set)
#acc=clf.prob_classify(test_set)
print('Accuracy: {:.2f}%'.format(acc*100))
# 用该模型来预测新样本，查看新句子的情感是积极还是消极
new_samples = [
"It is an amazing movie",
"This is a dull movie. I would never recommend it to anyone.",
"The cinematography is pretty great in this movie",
"The direction was terrible and the story was all over the place"
]
from nltk import NaiveBayesClassifier
from nltk.classify import accuracy as nltk_accuracy
from nltk.corpus import names
def extract_features(word, N=2):
last_n_letters = word[-N:]
return {'feature': last_n_letters.lower()}
male_list = [(name, 'male') for name in names.words('male.txt')]
female_list = [(name, 'female') for name in names.words('female.txt')]
data = (male_list + female_list)
num_train = int(0.8 * len(data))
random.seed(5)
random.shuffle(data)
for i in range(1, 6):
print('\nNumber of end letters:', i)
features = [(extract_features(n, i), gender) for (n, gender) in data]
train_data, test_data = features[:num_train], features[num_train:]
classifier = NaiveBayesClassifier.train(train_data)
accuracy = round(100 * nltk_accuracy(classifier, test_data), 2)
print('Accuracy = ' + str(accuracy) + '%')
input_names = ['Alexander', 'Danielle', 'David', 'Cheryl']
for name in input_names:
print(name, '==>', classifier.classify(extract_features(name, i)))
# coding: utf-8
import input_data as datain
datain.out2csv
datain.out2csv()
import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import PlaintextCorpusReader
import random
mesage_corpus = PlaintextCorpusReader('./', ['spam_data.csv', 'ham_data.csv'])
all_message = mesage_corpus.words()
all_message
def massage_feature(word,num_letter=1):
return {'feature':word[-num_letter:]}
labels_name = ([(massage,'垃圾') for massage in message_corpus.words('soam.csv')]+[(massage,'正常') for massage in message_corpus.words('normal.csv')])
random.seed(7)
random.shuffle(labels_name)
message_corpus = PlaintextCorpusReader('./', ['spam_data.csv', 'ham_data.csv'])
labels_name = ([(massage,'垃圾') for massage in message_corpus.words('soam.csv')]+[(massage,'正常') for massage in message_corpus.words('normal.csv')])
random.seed(7)
random.shuffle(labels_name)
labels_name = ([(massage,'垃圾') for massage in message_corpus.words('spam_data.csv')]+[(massage,'正常') for massage in message_corpus.words('ham_data.csv')])
random.seed(7)
random.shuffle(labels_name)
from nltk.classify import accuracy as nltk_accuracy
featuresets = [(massage_feature(n),massage) for (n,massage) in labels_name]
train_set,test_set = featuresets[2000:],featuresets[:2000]
classifier = NaiveBayesClassifier.train(train_set)
rint('结果准确率：',str(100*nltk_accuracy(classifier,test_set))+str('%'))
print('结果准确率：',str(100*nltk_accuracy(classifier,test_set))+str('%'))
get_ipython().run_line_magic('save', 'here 1-31')
if __name__ == "__main__":
# 提取标记名称
labeled_names = ([(name, 'male') for name in names.words('male.txt')]) + \
[(name, 'female') for name in names.words('female.txt')]
# 设置随机生成数的种子值，并混合搅乱训练数据
random.seed(7)
random.shuffle(labeled_names)
input_names = ['Leonardo', 'Amy', 'Sam']
# 搜索参数空间
for i in range(1, 5):
print('Number of letters: ', i)
featuresets = [(gender_features(n, i), gender) for (n, gender) in labeled_names]
# 将数据分为训练数据集和测试数据集
train_set, test_set = featuresets[500:], featuresets[:500]
# 用朴素贝叶斯分类器做分类
classifier = NaiveBayesClassifier.train(train_set)
# 打印分类器的准确性
print('Accuracy==>', str(100 * nltk_accuracy(classifier, test_set)) + str('%'))
# 为新输入预测输出结果
for name in input_names:
print(name , '==>', classifier.classify(gender_features(name, i)))
return {'feature': word[-num_letters:].lower()}
if __name__ == '__main__':
# 提取标记名称
labeled_names = ([(name, 'male') for name in names.words('male.txt')]) + \
([(name, 'female') for name in names.words('female.txt')])
# 设置随机生成数的种子值，并混合搅乱训练数据
random.seed(7)
random.shuffle(labeled_names)
# 定义一些输入的姓名
input_names = ['Leonardo', 'Amy', 'Sam', 'Werner']
# 搜索参数空间
for i in range(1,5):
print("取参数为{}".format(i))
featuresets = [(gender_features(n, i), gender) for (n, gender) in labeled_names]
# 分割数据为训练集和测试集
train_set, test_set = featuresets[500:], featuresets[:500]
# 用朴素贝叶斯分类器做分类
classifier = NaiveBayesClassifier.train(train_set)
# 打印分类器准确性
print(u"准确性：{}%".format(100*nltk_accuracy(classifier, test_set)))
# 为输入姓名预测结果
for name in input_names:
print("{} ==> {}".format(name, classifier.classify(gender_features(name, i))))
dataframe = pd.DataFrame({'normal': normallist}) #将list用DataFrame，以便保存到CSV文件中
dataframe.to_csv('normal.csv', encoding='utf_8_sig', header=False,
index=False) #保存到文件中
message_corpus = PlaintextCorpusReader('./',
['spam.csv', 'normal.csv']) #取出分词文件
all_message = message_corpus.words() #所有分词保存为list
def massage_feature(word, num_letter=1): #分词特征化
return {'feature': word[-num_letter:]}
labels_name = ([(massage, '垃圾')
for massage in message_corpus.words('spam.csv')] +
[(massage, '正常')
for massage in message_corpus.words('normal.csv')]) #给特征分类
random.seed(7)
random.shuffle(labels_name)
featuresets = [(massage_feature(n), massage)
for (n, massage) in labels_name] #调整格式
train_set, test_set = featuresets[
400:], featuresets[:400] #取2000个数据前400个为测试后1600个为训练
classifier = NaiveBayesClassifier.train(
train_set) #调用nltk中的NaiveBayesClassifier函数，传参训练
print('结果准确率：',
str(100 * nltk_accuracy(classifier, test_set)) + str('%')) #传测试集参数并预测准确率
from nltk import NaiveBayesClassifier
from nltk.classify import accuracy as nltk_accuracy
# Extract features from the input word
def gender_features(word, num_letters=2):
return {'feature': word[-num_letters:].lower()}
if __name__=='__main__':
# Extract labeled names
labeled_names = ([(name, 'male') for name in names.words('male.txt')] +
[(name, 'female') for name in names.words('female.txt')])
random.seed(7)
random.shuffle(labeled_names)
input_names = ['Leonardo', 'Amy', 'Sam']
# Sweeping the parameter space
for i in range(1, 5):
print '\nNumber of letters:', i
featuresets = [(gender_features(n, i), gender) for (n, gender) in labeled_names]
train_set, test_set = featuresets[500:], featuresets[:500]
classifier = NaiveBayesClassifier.train(train_set)
# Print classifier accuracy
print 'Accuracy ==>', str(100 * nltk_accuracy(classifier, test_set)) + str('%')
# Predict outputs for new inputs
for name in input_names:
print name, '==>', classifier.classify(gender_features(name, i))
