import string
import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer, WordNetLemmatizer

# 下載NLTK數(shù)據(jù)
nltk.download('stopwords')
nltk.download('wordnet')

# 示例文本
text = "Hello, world! This is a sample text with some punctuation and stop words."

# 去除標(biāo)點(diǎn)符號
text = text.translate(str.maketrans('', '', string.punctuation))

# 轉(zhuǎn)換為小寫
text = text.lower()

# 去除停用詞
stop_words = set(stopwords.words('english'))
words = text.split()
filtered_text = ' '.join([word for word in words if word not in stop_words])

# 詞干提取
stemmer = PorterStemmer()
stemmed_text = ' '.join([stemmer.stem(word) for word in filtered_text.split()])

# 詞形還原
lemmatizer = WordNetLemmatizer()
lemmatized_text = ' '.join([lemmatizer.lemmatize(word) for word in filtered_text.split()])

print("原始文本:", text)
print("去除標(biāo)點(diǎn)后的文本:", text)
print("去除停用詞后的文本:", filtered_text)
print("詞干提取后的文本:", stemmed_text)
print("詞形還原后的文本:", lemmatized_text)

from collections import Counter
import matplotlib.pyplot as plt
from wordcloud import WordCloud

# 示例文本
text = "This is a sample text. This text is used to demonstrate word frequency analysis."

# 詞頻統(tǒng)計(jì)
word_counts = Counter(text.split())

# 繪制詞云
wordcloud = WordCloud(width=800, height=400, background_color='white').generate_from_frequencies(word_counts)

plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()

from textblob import TextBlob

# 示例文本
text = "I love this product! It's amazing and very useful."

# 使用TextBlob進(jìn)行情感分析
blob = TextBlob(text)
sentiment = blob.sentiment

print(f"情感極性: {sentiment.polarity}")
print(f"主觀性: {sentiment.subjectivity}")

if sentiment.polarity > 0:
    print("情感傾向: 正面")
elif sentiment.polarity < 0:
    print("情感傾向: 負(fù)面")
else:
    print("情感傾向: 中立")

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score

# 示例數(shù)據(jù)
texts = ["I love this product", "This is a great movie", "I hate this book", "This is a terrible experience"]
labels = [1, 1, 0, 0]  # 1表示正面，0表示負(fù)面

# 特征提取
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)

# 劃分訓(xùn)練集和測試集
X_train, X_test, y_train, y_test = train_test_split(X, labels, test_size=0.2, random_state=42)

# 訓(xùn)練模型
model = MultinomialNB()
model.fit(X_train, y_train)

# 預(yù)測
y_pred = model.predict(X_test)

# 評估
accuracy = accuracy_score(y_test, y_pred)
print(f"準(zhǔn)確率: {accuracy}")

from gensim import corpora, models
import pyLDAvis.gensim_models as gensimvis
import pyLDAvis

# 示例數(shù)據(jù)
texts = [["this", "is", "a", "sample", "text"],
         ["another", "example", "of", "text", "data"],
         ["more", "text", "to", "demonstrate", "topic", "modeling"]]

# 創(chuàng)建詞典和語料庫
dictionary = corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]

# 訓(xùn)練LDA模型
lda_model = models.LdaModel(corpus, num_topics=2, id2word=dictionary, passes=10)

# 可視化
vis = gensimvis.prepare(lda_model, corpus, dictionary)
pyLDAvis.display(vis)