智能文本处理 双十二优惠活动

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB

# 假设我们有一个用户数据集和他们的购买历史
user_data = pd.DataFrame({
    'user_id': [1, 2, 3],
    'purchase_history': ['手机 电脑', '书籍 音乐', '服装 鞋子']
})

# 假设我们有一些促销活动的描述
promotions = pd.DataFrame({
    'promotion_id': [1, 2, 3],
    'description': ['手机优惠20%', '书籍买一送一', '服装全场五折']
})

# 使用TF-IDF向量化文本数据
vectorizer = TfidfVectorizer()
user_features = vectorizer.fit_transform(user_data['purchase_history'])
promotion_features = vectorizer.transform(promotions['description'])

# 训练一个简单的分类器来匹配用户和促销活动
model = MultinomialNB()
model.fit(user_features, user_data['user_id'])

# 预测最适合用户的促销活动
predictions = model.predict(promotion_features)

# 输出个性化的优惠信息
for user_id, promotion_id in zip(user_data['user_id'], predictions):
    print(f"User {user_id} is recommended promotion {promotion_id}: {promotions.loc[promotion_id, 'description']}")

from textblob import TextBlob

# 假设我们有一些用户评论
comments = [
    "这次双十二的优惠真的很给力！",
    "商品质量一般，不太满意。",
    "客服服务很好，解决问题迅速。"
]

# 进行情感分析
for comment in comments:
    blob = TextBlob(comment)
    sentiment = blob.sentiment.polarity
    if sentiment > 0:
        print(f"正面评论: {comment}")
    elif sentiment < 0:
        print(f"负面评论: {comment}")
    else:
        print(f"中性评论: {comment}")