运行 python程序的时候 就可以有创建了一个简单的升级动画，显示用户的当前等级，并在升级时更新显示_python

import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from flask import Flask, render_template, jsonify
import json

# 初始化nltk
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')

# 初始化分类器和评分模型
classifier = None
scorer = None

# 初始化分类和评分标准
categories = ['工作', '生活']
score_criteria = {
    '工作': {
        '完成任务': 10,
        '解决问题': 5,
        '其他': 1
    },
    '生活': {
        '锻炼': 5,
        '学习': 3,
        '其他': 1
    }
}

# 初始化基础分数和等级
base_score = 0
level = '初级'

# 初始化日志文件和评分记录
daily_log = []
scores = []

# 初始化TF-IDF向量化器
vectorizer = TfidfVectorizer()

# 初始化词形还原器
lemmatizer = WordNetLemmatizer()

# 训练分类器
def train_classifier():
    global classifier
    
    # 读取训练数据
    training_data = []
    training_labels = []
    for category in categories:
        with open(f'{category}_log.txt', 'r') as file:
            activities = file.readlines()
        training_data.extend(activities)
        training_labels.extend([category] * len(activities))
    
    # 数据预处理
    processed_data = preprocess_text(training_data)
    
    # 特征提取
    features = vectorizer.fit_transform(processed_data).toarray()
    
    # 训练分类器
    classifier = MultinomialNB()
    classifier.fit(features, training_labels)

# 训练评分模型
def train_scorer():
    global scorer
    
    # 读取训练数据
    training_data = []
    training_scores = []
    for category in categories:
        with open(f'{category}_log.txt', 'r') as file:
            activities = file.readlines()
        for activity in activities:
            training_data.append(activity)
            training_scores.append(score_activity(activity, category))
    
    # 数据预处理
    processed_data = preprocess_text(training_data)
    
    # 特征提取
    features = vectorizer.fit_transform(processed_data).toarray()
    
    # 训练评分模型
    scorer = MultinomialNB()
    scorer.fit(features, training_scores)

# 预处理文本数据
def preprocess_text(data):
    processed_data = []
    for text in data:
        # 分词
        tokens = word_tokenize(text.lower())
        
        # 去除停用词和标点符号
        stop_words = set(stopwords.words('english'))
        filtered_tokens = [token for token in tokens if token.isalnum() and token not in stop_words]
        
        # 词形还原
        lemmatized_tokens = [lemmatizer.lemmatize(token) for token in filtered_tokens]
        
        # 重新组合为文本
        processed_text = ' '.join(lemmatized_tokens)
        processed_data.append(processed_text)
    
    return processed_data

# 智能分类工作日常
def classify_activity(activity):
    processed_activity = preprocess_text([activity])
    features = vectorizer.transform(processed_activity).toarray()
    category = classifier.predict(features)[0]
    return category

# 根据分类和评分标准计算活动得分
def score_activity(activity, category):
    score = 0
    for word, points in score_criteria[category].items():
        if word in activity:
            score += points
    return score

# 记录每天的工作日常
def log_daily_activity(activity):
    global base_score, level
    
    # 智能分类
    category = classify_activity(activity)
    
    # 计算得分
    score = score_activity(activity, category)
    
    # 更新基础分数和等级
    base_score += score
    if base_score >= 100:
        level = '高级'
    elif base_score >= 50:
        level = '中级'
    
    # 记录日志
    daily_log.append((activity, category, score))
    
    # 更新评分记录
    scores.append(score)

# 创建Flask应用
app = Flask(__name__)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/simulate')
def simulate():
    global base_score, level
    # 模拟每天的活动记录
    activities = [
        '完成工作任务',
        '锻炼身体',
        '解决问题',
        '学习新知识',
        '其他活动'
    ]
    
    for activity in activities:
        log_daily_activity(activity)
    
    # 返回当前分数和等级
    return jsonify({'base_score': base_score, 'level': level})

if __name__ == '__main__':
    # 训练分类器和评分模型
    train_classifier()
    train_scorer()
    
    # 启动Flask应用
    app.run(debug=True)