print(len(text1))#文本长度
print(len(set(text1)))#词汇长度
fword=FreqDist(text1)
print(text1.name)#书名
print(fword)
voc=fword.most_common(50)#频率最高的50个字符
fword.plot(50,cumulative=True)#绘出波形图
print(fword.hapaxes())#低频词
分词和分句
from nltk.tokenize import word_tokenize,sent_tokenize
#分词 TreebankWordTokenizer PunktTokenizer
print(word_tokenize(text=“All work and no play makes jack a dull boy, all work and no play”,language=“english”))
#分句
data = “All work and no play makes jack dull boy. All work and no play makes jack a dull boy.”
print(sent_tokenize(data))
from nltk.corpus import stopwords
print(type(stopwords.words(‘english’)))
print([w for w in word_tokenize(text=“All work and no play makes jack a dull boy, all work and no play”,language=“english”) if w not in stopwords.words(‘english’)])#去掉停用词
时态 和 单复数
from nltk.stem import PorterStemmer
data=word_tokenize(text=“All work and no play makes jack a dull boy, all work and no play,playing,played”,language=“english”)
ps=PorterStemmer()
for w in data:
print(w,“:”,ps.stem(word=w))
from nltk.stem import SnowballStemmer
snowball_stemmer = SnowballStemmer(‘english’)
snowball_stemmer.stem(‘presumably’)
#u’presum’
from nltk.stem import WordNetLemmatizer
wordnet_lemmatizer = WordNetLemmatizer()
wordnet_lemmatizer.lemmatize(‘dogs’)
u’dog’
词性标注
sentence = “”“At eight o’clock on Thursday morning… Arthur didn’t feel very good.”“”
tokens = nltk.word_tokenize(sentence)
print(tokens)
#[‘At’, ‘eight’, “o’clock”, ‘on’, ‘Thursday’, ‘morning’,
‘Arthur’, ‘did’, “n’t”, ‘feel’, ‘very’, ‘good’, ‘.’]
nltk.help.upenn_tagset(‘NNP’)#输出NNP的含义
tagged = nltk.pos_tag(tokens)
nltk.batch_pos_tag([[‘this’, ‘is’, ‘batch’, ‘tag’, ‘test’], [‘nltk’, ‘is’, ‘text’, ‘analysis’, ‘tool’]])#批量标注
print(tagged)
[(‘At’, ‘IN’), (‘eight’, ‘CD’), (“o’clock”, ‘JJ’), (‘on’, ‘IN’),
(‘Thursday’, ‘NNP’), (‘morning’, ‘NN’)]
附表:
分类器
下面列出的是NLTK中自带的分类器
from nltk.classify.api import ClassifierI, MultiClassifierI
from nltk.classify.megam import config_megam, call_megam
from nltk.classify.weka import WekaClassifier, config_weka
from nltk.classify.naivebayes import NaiveBayesClassifier
from nltk.classify.positivenaivebayes import PositiveNaiveBayesClassifier
from nltk.classify.decisiontree import DecisionTreeClassifier
from nltk.classify.rte_classify import rte_classifier, rte_features, RTEFeatureExtractor
from nltk.classify.util import accuracy, apply_features, log_likelihood
自我介绍一下,小编13年上海交大毕业,曾经在小公司待过,也去过华为、OPPO等大厂,18年进入阿里一直到现在。
深知大多数Python工程师,想要提升技能,往往是自己摸索成长或者是报班学习,但对于培训机构动则几千的学费,着实压力不小。自己不成体系的自学效果低效又漫长,而且极易碰到天花板技术停滞不前!
因此收集整理了一份《2024年Python开发全套学习资料》,初衷也很简单,就是希望能够帮助到想自学提升又不知道该从何学起的朋友,同时减轻大家的负担。
既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上Python开发知识点,真正体系化!
由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新
如果你觉得这些内容对你有帮助,可以添加V获取:vip1024c (备注Python)
一个人可以走的很快,但一群人才能走的更远。如果你从事以下工作或对以下感兴趣,欢迎戳这里加入程序员的圈子,让我们一起学习成长!
AI人工智能、Android移动开发、AIGC大模型、C C#、Go语言、Java、Linux运维、云计算、MySQL、PMP、网络安全、Python爬虫、UE5、UI设计、Unity3D、Web前端开发、产品经理、车载开发、大数据、鸿蒙、计算机网络、嵌入式物联网、软件测试、数据结构与算法、音视频开发、Flutter、IOS开发、PHP开发、.NET、安卓逆向、云计算
工智能、Android移动开发、AIGC大模型、C C#、Go语言、Java、Linux运维、云计算、MySQL、PMP、网络安全、Python爬虫、UE5、UI设计、Unity3D、Web前端开发、产品经理、车载开发、大数据、鸿蒙、计算机网络、嵌入式物联网、软件测试、数据结构与算法、音视频开发、Flutter、IOS开发、PHP开发、.NET、安卓逆向、云计算**