# -*- coding: utf-8 -*-
import re
import pandas as pd
import json
import ast  # Python 的 ast.literal_eval 可以安全解析 Python 字典字符串

def test_code_001():
    df = pd.read_csv("alpha_list.csv", nrows=5)

    # 方法1：用 ast.literal_eval（推荐，能解析 Python 字面量）
    for i, row in df.iterrows():
        regular_str = row['regular']
        if pd.notna(regular_str):
            try:
                regular_dict = ast.literal_eval(regular_str)
                code = regular_dict.get('code', '')
                print(f"Row {i}: {code[:80]}...")
            except Exception as e:
                print(f"Row {i}: 解析失败 - {e}")

    # 方法2：看看原始字符串前200个字符
    print("\n原始字符串示例:")
    print(df.iloc[0]['regular'][:200])

def test_code_002():
    expression = "last_diff_value(ts_sum(subtract(implied_volatility_call_120, implied_volatility_put_90), 20), 5)"

    # 提取算子
    operators = set()
    for match in re.finditer(r'\b([a-z_][a-z0-9_]*)\s*\(', expression):
        op = match.group(1)
        operators.add(op)
        print(f"匹配到算子: {op}")

    print(f"\n所有算子: {operators}")

    # 提取字段
    candidates = set(re.findall(r'\b([a-z][a-z0-9_]*)\b', expression))
    print(f"\n所有候选词: {candidates}")

    # 过滤掉算子
    fields = [c for c in candidates if c not in operators and not c.isdigit() and len(c) > 2]
    print(f"\n字段: {fields}")

def test_code_003():
    df = pd.read_csv("alpha_list.csv")

    # 检查 id 列的类型
    print(f"id 列类型: {df['id'].dtype}")

    # 检查是否有重复
    duplicates = df[df.duplicated(subset=['id'], keep=False)]
    print(f"\n重复的 id 数量: {len(duplicates)}")

    if len(duplicates) > 0:
        print("\n重复的 id 示例:")
        for aid in duplicates['id'].unique()[:5]:
            rows = df[df['id'] == aid]
            print(f"  {aid}: 出现 {len(rows)} 次")
            # 打印这些行的 fitness 看是否相同
            for _, row in rows.iterrows():
                print(f"    fitness: {row['is'][:100] if isinstance(row['is'], str) else row['is']}...")