feat: djapi 数据源归一化 + bug 修复 + 废弃 getDivData_AK
- 新增 djapi/api/stock/data_source.py 统一数源入口 (Tushare 单例) - 迁移 10 个模块至统一数据源入口 - 废弃 getDivData_AK.py - 修复 getStockDiv2.py / smoothBrush.py 等模块 - indexDatas API 参数 tscode 类型修正 (股票→指数代码) - views.py + urls.py 接口清理 - continuation.md 状态更新 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.7
@@ -1,181 +0,0 @@
|
||||
"""
|
||||
⚠️ 已废弃 — 2026-06-05
|
||||
|
||||
AkShare 股息率数据获取功能已归一化到 data_source.py。
|
||||
如需 AkShare 日线数据，请使用：
|
||||
|
||||
from .data_source import get_daily
|
||||
df = get_daily(ts_code, start, end, source='akshare')
|
||||
|
||||
本文件保留仅用于向后兼容，所有公开函数委托给统一数据源。
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
from .data_source import get_daily
|
||||
|
||||
from .stock_utils import tscodeCheck, date_format_correction
|
||||
from .smoothBrush import smooth_dataframe_brush
|
||||
|
||||
GAP_DAYS = 360 # TTM 计算窗口
|
||||
|
||||
|
||||
def _parse_tscode(tscode: str) -> tuple:
|
||||
"""将 tscode（如 000001.SZ）转为 akshare 格式的 symbol 和 market"""
|
||||
code = tscode.split('.')[0]
|
||||
suffix = tscode.split('.')[1].lower()
|
||||
market_map = {'sz': 'sz', 'sh': 'sh', 'bj': 'bj'}
|
||||
return code, market_map.get(suffix, suffix)
|
||||
|
||||
|
||||
def _fetch_daily_price(symbol: str, start_date: str, end_date: str) -> pd.DataFrame:
|
||||
"""通过 akshare 获取前复权日线行情"""
|
||||
df = ak.stock_zh_a_hist(
|
||||
symbol=symbol,
|
||||
period='daily',
|
||||
start_date=start_date,
|
||||
end_date=end_date,
|
||||
adjust='qfq'
|
||||
)
|
||||
if df.empty:
|
||||
return pd.DataFrame()
|
||||
|
||||
df = df.rename(columns={
|
||||
'日期': 'trade_date',
|
||||
'开盘': 'open',
|
||||
'收盘': 'close',
|
||||
'最高': 'high',
|
||||
'最低': 'low',
|
||||
'成交量': 'vol',
|
||||
'成交额': 'amount',
|
||||
'换手率': 'turnover_rate',
|
||||
})
|
||||
df['trade_date'] = df['trade_date'].astype(str).str.replace('-', '')
|
||||
return df
|
||||
|
||||
|
||||
def _fetch_dividends(symbol: str, market: str) -> pd.DataFrame:
|
||||
"""通过 akshare 获取历史分红记录"""
|
||||
try:
|
||||
df = ak.stock_dividend_cninfo(stock=symbol, symbol=market + symbol)
|
||||
except Exception:
|
||||
return pd.DataFrame()
|
||||
|
||||
if df.empty:
|
||||
return pd.DataFrame()
|
||||
|
||||
# 列名映射（akshare 返回中文列名）
|
||||
col_map = {
|
||||
'除权除息日': 'ex_date',
|
||||
'每股派息': 'cash_div_tax',
|
||||
}
|
||||
df = df.rename(columns={k: v for k, v in col_map.items() if k in df.columns})
|
||||
|
||||
if 'ex_date' not in df.columns or 'cash_div_tax' not in df.columns:
|
||||
return pd.DataFrame()
|
||||
|
||||
df['ex_date'] = df['ex_date'].astype(str).str.replace('-', '').str[:8]
|
||||
df['cash_div_tax'] = pd.to_numeric(df['cash_div_tax'], errors='coerce').fillna(0)
|
||||
return df[['ex_date', 'cash_div_tax']]
|
||||
|
||||
|
||||
def get_akshare_dividend_yield(tscode: str, start_date: str = None, end_date: str = None) -> pd.DataFrame:
|
||||
"""
|
||||
通过 akshare 获取股价和分红数据，计算股息率。
|
||||
|
||||
Args:
|
||||
tscode: 股票代码，如 '000001.SZ'
|
||||
start_date: 起始日期 yyyyMMdd
|
||||
end_date: 结束日期 yyyyMMdd
|
||||
|
||||
Returns:
|
||||
DataFrame: ts_code, trade_date, close, cash_div_tax, cash_div_year, div_yield
|
||||
"""
|
||||
tscode = tscodeCheck(tscode)
|
||||
today = datetime.now().strftime('%Y%m%d')
|
||||
|
||||
if start_date:
|
||||
start_date = date_format_correction(start_date)
|
||||
else:
|
||||
start_date = '20200101'
|
||||
if end_date:
|
||||
end_date = date_format_correction(end_date)
|
||||
else:
|
||||
end_date = today
|
||||
|
||||
if end_date > today:
|
||||
end_date = today
|
||||
|
||||
symbol, market = _parse_tscode(tscode)
|
||||
|
||||
# 1. 获取日线行情（运算时起始日期往前推 GAP_DAYS）
|
||||
calc_start = datetime.strptime(start_date, '%Y%m%d') - timedelta(days=GAP_DAYS)
|
||||
calc_start_str = calc_start.strftime('%Y%m%d')
|
||||
|
||||
df_price = _fetch_daily_price(symbol, calc_start_str, end_date)
|
||||
if df_price.empty:
|
||||
return pd.DataFrame()
|
||||
df_price = df_price.sort_values('trade_date').reset_index(drop=True)
|
||||
|
||||
# 2. 获取分红数据
|
||||
df_div = _fetch_dividends(symbol, market)
|
||||
|
||||
# 3. 计算 TTM 分红序列
|
||||
if df_div.empty:
|
||||
df_price['cash_div_tax'] = 0.0
|
||||
df_price['cash_div_year'] = 0.0
|
||||
else:
|
||||
# 将分红按 ex_date 合并到交易日历
|
||||
df_div['ex_date'] = pd.to_datetime(df_div['ex_date'], format='%Y%m%d')
|
||||
df_price['trade_date_dt'] = pd.to_datetime(df_price['trade_date'], format='%Y%m%d')
|
||||
|
||||
# 按日期合并
|
||||
div_dict = df_div.set_index('ex_date')['cash_div_tax'].to_dict()
|
||||
|
||||
def calc_ttm_div(trade_dt):
|
||||
window_start = trade_dt - timedelta(days=GAP_DAYS)
|
||||
total = 0.0
|
||||
for ex_dt, cash in div_dict.items():
|
||||
if window_start < ex_dt <= trade_dt:
|
||||
total += cash
|
||||
return total
|
||||
|
||||
cash_div_tax_list = []
|
||||
cash_div_year_list = []
|
||||
|
||||
for _, row in df_price.iterrows():
|
||||
td = row['trade_date_dt']
|
||||
cash = div_dict.get(td, 0.0)
|
||||
cash_div_tax_list.append(cash)
|
||||
cash_div_year_list.append(calc_ttm_div(td))
|
||||
|
||||
df_price['cash_div_tax'] = cash_div_tax_list
|
||||
df_price['cash_div_year'] = cash_div_year_list
|
||||
df_price = df_price.drop(columns=['trade_date_dt'])
|
||||
|
||||
# 4. 毛刺平滑
|
||||
df_price = smooth_dataframe_brush(
|
||||
df_price,
|
||||
target_columns=['cash_div_year'],
|
||||
window_size=31,
|
||||
threshold_factor=0.5,
|
||||
max_brush_length=15
|
||||
)
|
||||
|
||||
# 5. 截取请求的时间范围
|
||||
df_result = df_price[
|
||||
(df_price['trade_date'] >= start_date) & (df_price['trade_date'] <= end_date)
|
||||
].copy()
|
||||
|
||||
# 6. 计算股息率
|
||||
df_result['div_yield'] = 0.0
|
||||
mask = (df_result['close'] > 0) & (df_result['cash_div_year'] > 0)
|
||||
df_result.loc[mask, 'div_yield'] = (
|
||||
(df_result.loc[mask, 'cash_div_year'] / df_result.loc[mask, 'close']) * 100
|
||||
).round(4)
|
||||
|
||||
df_result['ts_code'] = tscode
|
||||
final_cols = ['ts_code', 'trade_date', 'close', 'cash_div_tax', 'cash_div_year', 'div_yield']
|
||||
return df_result[final_cols].reset_index(drop=True)
|
||||
@@ -52,7 +52,6 @@ def analyze_stock_dividend_and_price(ts_code, start_date=START_DATE, end_date=EN
|
||||
if start_date > today: start_date = today
|
||||
|
||||
GAP_DAYS = 360 # 定义TTM计算窗口期为360天
|
||||
n = 15 # 定义向前填充的最大非零值个数
|
||||
"""
|
||||
分析个股分红与行情数据。
|
||||
|
||||
@@ -110,23 +109,11 @@ def analyze_stock_dividend_and_price(ts_code, start_date=START_DATE, end_date=EN
|
||||
# 填充空值
|
||||
df_merged_temp['cash_div_tax'] = df_merged_temp['cash_div_tax'].fillna(0.0)
|
||||
|
||||
# 计算 cash_div_year (TTM)
|
||||
# 计算 cash_div_year (TTM) — 向量化 rolling 窗口
|
||||
df_merged_temp = df_merged_temp.sort_values('trade_date').reset_index(drop=True)
|
||||
# 使用滚动窗口计算过去 GAP_DAYS 天的总和
|
||||
# rolling的window参数是基于行数的，所以我们需要先确保日期是连续的交易日
|
||||
# 由于trade_date已经是交易日，我们可以直接使用rolling
|
||||
# 但需要处理时间窗口，确保是360天而不是360行（因为可能有节假日）
|
||||
# 更精确的方法是使用一个自定义函数来累加过去360天内的值
|
||||
|
||||
# 使用更精确的日期差计算
|
||||
def calculate_ttm_div(row_idx):
|
||||
current_date = df_merged_temp.loc[row_idx, 'trade_date']
|
||||
start_window_date = current_date - pd.Timedelta(days=GAP_DAYS)
|
||||
# 筛选出窗口期内的记录
|
||||
mask = (df_merged_temp['trade_date'] > start_window_date) & (df_merged_temp['trade_date'] <= current_date)
|
||||
return df_merged_temp.loc[mask, 'cash_div_tax'].sum()
|
||||
|
||||
df_merged_temp['cash_div_year'] = [calculate_ttm_div(i) for i in range(len(df_merged_temp))]
|
||||
df_temp = df_merged_temp.set_index('trade_date')
|
||||
df_temp['cash_div_year'] = df_temp['cash_div_tax'].rolling(f'{GAP_DAYS}D', min_periods=1).sum()
|
||||
df_merged_temp['cash_div_year'] = df_temp['cash_div_year'].values
|
||||
|
||||
|
||||
# 截取原始请求的起止时间内的数据
|
||||
@@ -155,37 +142,6 @@ def analyze_stock_dividend_and_price(ts_code, start_date=START_DATE, end_date=EN
|
||||
df_result['cash_div_year'] = df_result['cash_div_year'].fillna(0.0)
|
||||
|
||||
|
||||
'''
|
||||
向前填充cash_div_year（最多填充最近n个非零值）
|
||||
如果遇到0值，依次往下查询直到查询到非0数字为止，如果数字个数<=n个，就置last_valid_value, 否则保持不变
|
||||
'''
|
||||
# 确保按trade_date倒序遍历（日期从大到小）
|
||||
df_result = df_result.sort_values('trade_date', ascending=False).reset_index(drop=True)
|
||||
|
||||
last_valid_value = None # 初始化最后一个有效值变量
|
||||
for idx in range(len(df_result)): # 遍历DataFrame的每一行
|
||||
current_value = df_result.loc[idx, 'cash_div_year'] # 获取当前行的TTM分红值
|
||||
if current_value > 0: # 如果当前值大于0
|
||||
last_valid_value = current_value # 更新最后一个有效值
|
||||
else:
|
||||
# 向下查找最多n个位置内的非零值
|
||||
found_value = None # 初始化找到的值
|
||||
search_count = 0 # 初始化搜索计数
|
||||
# 从下一行开始搜索，最多搜索n行
|
||||
for search_idx in range(idx + 1, min(idx + n + 1, len(df_result))):
|
||||
search_value = df_result.loc[search_idx, 'cash_div_year'] # 获取搜索行的值
|
||||
search_count += 1 # 增加搜索计数
|
||||
if search_value > 0: # 如果找到非零值
|
||||
found_value = search_value # 记录找到的值
|
||||
break # 跳出搜索循环
|
||||
|
||||
# 如果找到非零值且在n个位置内
|
||||
if found_value is not None and search_count <= n:
|
||||
df_result.loc[idx, 'cash_div_year'] = found_value
|
||||
last_valid_value = found_value
|
||||
elif last_valid_value is not None:
|
||||
df_result.loc[idx, 'cash_div_year'] = last_valid_value
|
||||
|
||||
# 毛刺平滑处理 cash_div_year 列
|
||||
df_result=smooth_dataframe_brush(df_result, target_columns=['cash_div_year'], window_size=31, threshold_factor=0.5, max_brush_length=15 )
|
||||
# 恢复原始日期顺序
|
||||
|
||||
@@ -90,9 +90,9 @@ def smooth_series_brush(series: pd.Series, window_size: int = 7, threshold_facto
|
||||
|
||||
# 决定使用哪个值填充
|
||||
if prev_valid_val is not None:
|
||||
fill_value = next_valid_val
|
||||
elif next_valid_val is not None:
|
||||
fill_value = prev_valid_val
|
||||
elif next_valid_val is not None:
|
||||
fill_value = next_valid_val
|
||||
else:
|
||||
print(f"警告: 毛刺段 {brush_indices} 无有效邻居，使用全局中位数填充。")
|
||||
fill_value = series.median()
|
||||
|
||||
Reference in New Issue
Block a user