Python实现NLP的完整流程介绍

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

# 示例文本数据
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表示负面情感
}
 
df = pd.DataFrame(data)
print(df)

# 小写化
df['text'] = df['text'].apply(lambda x: x.lower())

nltk.download('punkt')  # 下载 punkt 分词器
 
# 分词
df['tokens'] = df['text'].apply(word_tokenize)
print(df['tokens'])

nltk.download('stopwords')  # 下载停用词库
 
stop_words = set(stopwords.words('english'))
 
# 去除停用词
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()
 
# 词干提取
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()
 
# 将文本数据转换为 TF-IDF 特征矩阵
X = vectorizer.fit_transform(df['text'])
 
# 查看转换后的 TF-IDF 特征矩阵
print(X.toarray())

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, df['label'], test_size=0.2, random_state=42)
 
print(f"训练集大小: {X_train.shape}")
print(f"测试集大小: {X_test.shape}")

# 创建并训练模型
model = MultinomialNB()
model.fit(X_train, y_train)

# 使用测试集进行预测
y_pred = model.predict(X_test)
 
# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"模型准确率: {accuracy:.4f}")
 
# 显示混淆矩阵
conf_matrix = confusion_matrix(y_test, y_pred)
print("混淆矩阵:")
print(conf_matrix)
 
# 可视化混淆矩阵
plt.matshow(conf_matrix, cmap='Blues')
plt.title("Confusion Matrix")
plt.xlabel('Predicted')
plt.ylabel('True')
plt.colorbar()
plt.show()

# 新文本数据
new_text = ["I love learning about AI and machine learning."]
 
# 文本预处理
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)
 
# 预测
prediction = model.predict(new_features)
print(f"预测标签: {prediction[0]}")