pip install numpy pandas matplotlib scikit-learn nltk spacy

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, confusion_matrix
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import spacy

# 示例文本數(shù)據(jù)
data = {
    'text': [
        "I love programming in Python.",
        "Python is a great language for machine learning.",
        "Natural language processing is fun!",
        "I enjoy solving problems using code.",
        "Deep learning and NLP are interesting fields.",
        "Machine learning and AI are revolutionizing industries."
    ],
    'label': [1, 1, 1, 0, 1, 0]  # 1表示正面情感，0表示負(fù)面情感
}
 
df = pd.DataFrame(data)
print(df)

# 小寫(xiě)化
df['text'] = df['text'].apply(lambda x: x.lower())

nltk.download('punkt')  # 下載 punkt 分詞器
 
# 分詞
df['tokens'] = df['text'].apply(word_tokenize)
print(df['tokens'])

nltk.download('stopwords')  # 下載停用詞庫(kù)
 
stop_words = set(stopwords.words('english'))
 
# 去除停用詞
df['tokens'] = df['tokens'].apply(lambda x: [word for word in x if word not in stop_words])
print(df['tokens'])

from nltk.stem import PorterStemmer
 
stemmer = PorterStemmer()
 
# 詞干提取
df['tokens'] = df['tokens'].apply(lambda x: [stemmer.stem(word) for word in x])
print(df['tokens'])

# 使用 TF-IDF 向量化文本
vectorizer = TfidfVectorizer()
 
# 將文本數(shù)據(jù)轉(zhuǎn)換為 TF-IDF 特征矩陣
X = vectorizer.fit_transform(df['text'])
 
# 查看轉(zhuǎn)換后的 TF-IDF 特征矩陣
print(X.toarray())

# 劃分訓(xùn)練集和測(cè)試集
X_train, X_test, y_train, y_test = train_test_split(X, df['label'], test_size=0.2, random_state=42)
 
print(f"訓(xùn)練集大小: {X_train.shape}")
print(f"測(cè)試集大小: {X_test.shape}")

# 創(chuàng)建并訓(xùn)練模型
model = MultinomialNB()
model.fit(X_train, y_train)

# 使用測(cè)試集進(jìn)行預(yù)測(cè)
y_pred = model.predict(X_test)
 
# 計(jì)算準(zhǔn)確率
accuracy = accuracy_score(y_test, y_pred)
print(f"模型準(zhǔn)確率: {accuracy:.4f}")
 
# 顯示混淆矩陣
conf_matrix = confusion_matrix(y_test, y_pred)
print("混淆矩陣:")
print(conf_matrix)
 
# 可視化混淆矩陣
plt.matshow(conf_matrix, cmap='Blues')
plt.title("Confusion Matrix")
plt.xlabel('Predicted')
plt.ylabel('True')
plt.colorbar()
plt.show()

# 新文本數(shù)據(jù)
new_text = ["I love learning about AI and machine learning."]
 
# 文本預(yù)處理
new_text = [text.lower() for text in new_text]
new_tokens = [word_tokenize(text) for text in new_text]
new_tokens = [[stemmer.stem(word) for word in tokens if word not in stop_words] for tokens in new_tokens]
new_text_clean = [' '.join(tokens) for tokens in new_tokens]
 
# 特征提取
new_features = vectorizer.transform(new_text_clean)
 
# 預(yù)測(cè)
prediction = model.predict(new_features)
print(f"預(yù)測(cè)標(biāo)簽: {prediction[0]}")