jack/Chan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add A share to display

Browse Source
This commit is contained in:
Porter
2025-05-25 14:37:47 +08:00
parent b4aef0b728
commit 3f16a5e6ce
16 changed files with 1718 additions and 215 deletions
Download Patch File Download Diff File Expand all files Collapse all files
web/cn_stock_data.py
+749
View File
@@ -0,0 +1,749 @@
import akshare as ak
import pandas as pd
from datetime import datetime, timedelta, time
import time as time_module
import traceback
from pytz import timezone
import warnings
warnings.filterwarnings('ignore')
class ChinaStockData:
"""A股数据获取类"""
def __init__(self):
self.tz = timezone('Asia/Shanghai')
# A股交易时间配置
self.trading_hours = {
'morning': {'start': '09:30', 'end': '11:30'},
'afternoon': {'start': '13:00', 'end': '15:00'}
}
def get_stock_list(self):
"""获取A股股票列表"""
try:
# 获取沪深A股实时行情
stock_info = ak.stock_zh_a_spot_em()
# 增加到前2000只股票，提供更多选择
stock_list = []
for index, row in stock_info.head(2000).iterrows():
# 过滤掉ST股票和停牌股票
stock_name = str(row['名称'])
if 'ST' not in stock_name and '*' not in stock_name:
stock_list.append({
'symbol': row['代码'],
'name': row['名称'],
'price': float(row['最新价']) if pd.notna(row['最新价']) else 0.0,
'change_pct': float(row['涨跌幅']) if pd.notna(row['涨跌幅']) else 0.0,
'volume': float(row['成交量']) if pd.notna(row['成交量']) else 0.0,
'amount': float(row['成交额']) if pd.notna(row['成交额']) else 0.0
})
# 按成交金额排序，优先显示活跃股票
stock_list.sort(key=lambda x: x['amount'], reverse=True)
return stock_list
except Exception as e:
print(f"获取股票列表失败: {e}")
return []
def get_popular_stocks(self):
"""获取热门A股股票代码列表 - 扩展版本，按行业分类"""
return [
# 银行股
{'symbol': '600036', 'name': '招商银行', 'sector': '银行'},
{'symbol': '000001', 'name': '平安银行', 'sector': '银行'},
{'symbol': '600000', 'name': '浦发银行', 'sector': '银行'},
{'symbol': '002142', 'name': '宁波银行', 'sector': '银行'},
{'symbol': '600016', 'name': '民生银行', 'sector': '银行'},
{'symbol': '601288', 'name': '农业银行', 'sector': '银行'},
{'symbol': '601398', 'name': '工商银行', 'sector': '银行'},
{'symbol': '601328', 'name': '交通银行', 'sector': '银行'},
# 白酒股
{'symbol': '600519', 'name': '贵州茅台', 'sector': '白酒'},
{'symbol': '000858', 'name': '五粮液', 'sector': '白酒'},
{'symbol': '002304', 'name': '洋河股份', 'sector': '白酒'},
{'symbol': '000596', 'name': '古井贡酒', 'sector': '白酒'},
{'symbol': '603369', 'name': '今世缘', 'sector': '白酒'},
{'symbol': '000799', 'name': '酒鬼酒', 'sector': '白酒'},
{'symbol': '600809', 'name': '山西汾酒', 'sector': '白酒'},
# 科技股
{'symbol': '002415', 'name': '海康威视', 'sector': '科技'},
{'symbol': '000063', 'name': '中兴通讯', 'sector': '科技'},
{'symbol': '002475', 'name': '立讯精密', 'sector': '科技'},
{'symbol': '300059', 'name': '东方财富', 'sector': '科技'},
{'symbol': '000725', 'name': '京东方A', 'sector': '科技'},
{'symbol': '002230', 'name': '科大讯飞', 'sector': '科技'},
{'symbol': '300433', 'name': '蓝思科技', 'sector': '科技'},
{'symbol': '002236', 'name': '大华股份', 'sector': '科技'},
# 新能源
{'symbol': '300750', 'name': '宁德时代', 'sector': '新能源'},
{'symbol': '002594', 'name': '比亚迪', 'sector': '新能源'},
{'symbol': '300274', 'name': '阳光电源', 'sector': '新能源'},
{'symbol': '002460', 'name': '赣锋锂业', 'sector': '新能源'},
{'symbol': '300014', 'name': '亿纬锂能', 'sector': '新能源'},
{'symbol': '600884', 'name': '杉杉股份', 'sector': '新能源'},
{'symbol': '002812', 'name': '恩捷股份', 'sector': '新能源'},
# 房地产
{'symbol': '000002', 'name': '万科A', 'sector': '房地产'},
{'symbol': '000858', 'name': '五粮液', 'sector': '房地产'},
{'symbol': '600048', 'name': '保利发展', 'sector': '房地产'},
{'symbol': '001979', 'name': '招商蛇口', 'sector': '房地产'},
{'symbol': '600606', 'name': '绿地控股', 'sector': '房地产'},
# 消费股
{'symbol': '600887', 'name': '伊利股份', 'sector': '消费'},
{'symbol': '000568', 'name': '泸州老窖', 'sector': '消费'},
{'symbol': '600600', 'name': '青岛啤酒', 'sector': '消费'},
{'symbol': '000895', 'name': '双汇发展', 'sector': '消费'},
{'symbol': '002304', 'name': '洋河股份', 'sector': '消费'},
{'symbol': '600779', 'name': '水井坊', 'sector': '消费'},
# 医药股
{'symbol': '600196', 'name': '复星医药', 'sector': '医药'},
{'symbol': '000661', 'name': '长春高新', 'sector': '医药'},
{'symbol': '300015', 'name': '爱尔眼科', 'sector': '医药'},
{'symbol': '002821', 'name': '凯莱英', 'sector': '医药'},
{'symbol': '300760', 'name': '迈瑞医疗', 'sector': '医药'},
{'symbol': '600276', 'name': '恒瑞医药', 'sector': '医药'},
# 证券股
{'symbol': '000776', 'name': '广发证券', 'sector': '证券'},
{'symbol': '600030', 'name': '中信证券', 'sector': '证券'},
{'symbol': '000166', 'name': '申万宏源', 'sector': '证券'},
{'symbol': '601688', 'name': '华泰证券', 'sector': '证券'},
{'symbol': '600837', 'name': '海通证券', 'sector': '证券'},
# 化工股
{'symbol': '600309', 'name': '万华化学', 'sector': '化工'},
{'symbol': '002352', 'name': '顺丰控股', 'sector': '化工'},
{'symbol': '600346', 'name': '恒力石化', 'sector': '化工'},
{'symbol': '000792', 'name': '盐湖股份', 'sector': '化工'},
# 汽车股
{'symbol': '600104', 'name': '上汽集团', 'sector': '汽车'},
{'symbol': '000625', 'name': '长安汽车', 'sector': '汽车'},
{'symbol': '601633', 'name': '长城汽车', 'sector': '汽车'},
{'symbol': '002049', 'name': '紫光国微', 'sector': '汽车'},
# 军工股
{'symbol': '002179', 'name': '中航光电', 'sector': '军工'},
{'symbol': '600893', 'name': '航发动力', 'sector': '军工'},
{'symbol': '000768', 'name': '中航飞机', 'sector': '军工'},
# 基建股
{'symbol': '601186', 'name': '中国铁建', 'sector': '基建'},
{'symbol': '601390', 'name': '中国中铁', 'sector': '基建'},
{'symbol': '000001', 'name': '平安银行', 'sector': '基建'},
# 煤炭股
{'symbol': '601225', 'name': '陕西煤业', 'sector': '煤炭'},
{'symbol': '600188', 'name': '兖矿能源', 'sector': '煤炭'},
{'symbol': '601898', 'name': '中煤能源', 'sector': '煤炭'},
# 钢铁股
{'symbol': '000717', 'name': '韶钢松山', 'sector': '钢铁'},
{'symbol': '600019', 'name': '宝钢股份', 'sector': '钢铁'},
{'symbol': '000708', 'name': '中信特钢', 'sector': '钢铁'},
]
def timeframe_to_period(self, timeframe):
"""将时间周期转换为akshare的period参数"""
mapping = {
'1m': '1', # 1分钟
'5m': '5', # 5分钟
'15m': '15', # 15分钟
'30m': '30', # 30分钟
'1h': '60', # 60分钟
'1d': 'daily', # 日线
'1w': 'weekly',# 周线
'1M': 'monthly'# 月线
}
return mapping.get(timeframe, 'daily')
def get_kl_data(self, symbol, timeframe='1d', start_date=None, end_date=None, limit=1000):
"""
获取A股K线数据 - 支持分批次获取突破单次限制
:param symbol: 股票代码，如 '000001'
:param timeframe: 时间周期，如 '1d', '1h', '5m'
:param start_date: 开始日期，格式 'YYYY-MM-DD'
:param end_date: 结束日期，格式 'YYYY-MM-DD'
:param limit: 数据条数限制
:return: DataFrame
"""
try:
period = self.timeframe_to_period(timeframe)
# 处理时间参数
if start_date is None:
# 默认获取最近一年的数据
start_date = (datetime.now() - timedelta(days=365)).strftime('%Y%m%d')
else:
# 将 YYYY-MM-DD 格式转换为 YYYYMMDD
if '-' in start_date:
start_date = start_date.replace('-', '')
if end_date is None:
end_date = datetime.now().strftime('%Y%m%d')
else:
if '-' in end_date:
end_date = end_date.replace('-', '')
print(f"获取A股数据: {symbol}, 周期: {timeframe}, 开始: {start_date}, 结束: {end_date}")
# 分批次获取数据以突破单次限制
all_data = []
current_start = start_date
# 计算时间间隔（根据时间周期调整批次大小）
if period in ['1', '5', '15', '30']:
# 分钟级数据，每次获取7天
batch_days = 7
elif period == '60':
# 小时级数据，每次获取30天
batch_days = 30
else:
# 日线及以上，每次获取365天
batch_days = 365
max_iterations = 20 # 最大迭代次数，防止无限循环
iteration_count = 0
while current_start <= end_date and iteration_count < max_iterations:
iteration_count += 1
# 计算当前批次的结束时间
current_start_dt = datetime.strptime(current_start, '%Y%m%d')
current_end_dt = current_start_dt + timedelta(days=batch_days)
current_end = min(current_end_dt.strftime('%Y%m%d'), end_date)
print(f"批次 {iteration_count}: 获取 {current_start} 到 {current_end} 的数据")
try:
# 根据时间周期选择不同的API
df_batch = None
if period in ['1', '5', '15', '30', '60']:
# 分钟级数据
df_batch = ak.stock_zh_a_hist_min_em(symbol=symbol, period=period,
start_date=current_start, end_date=current_end)
if df_batch is not None and len(df_batch) > 0:
# 重命名列
df_batch = df_batch.rename(columns={
'时间': 'date',
'开盘': 'open',
'收盘': 'close',
'最高': 'high',
'最低': 'low',
'成交量': 'volume'
})
else:
# 日线、周线、月线数据
df_batch = ak.stock_zh_a_hist(symbol=symbol, period=period,
start_date=current_start, end_date=current_end)
if df_batch is not None and len(df_batch) > 0:
# 重命名列
df_batch = df_batch.rename(columns={
'日期': 'date',
'开盘': 'open',
'收盘': 'close',
'最高': 'high',
'最低': 'low',
'成交量': 'volume'
})
if df_batch is not None and len(df_batch) > 0:
# 转换时间格式
df_batch['date'] = pd.to_datetime(df_batch['date'])
# 根据A股交易时间调整时间戳
df_batch = self.adjust_timestamp_for_trading_hours(df_batch, timeframe)
all_data.append(df_batch)
print(f"批次 {iteration_count}: 获取到 {len(df_batch)} 条记录")
else:
print(f"批次 {iteration_count}: 未获取到数据")
except Exception as e:
print(f"批次 {iteration_count} 获取失败: {e}")
# 继续下一个批次
# 更新下一批次的开始时间
current_start = (current_end_dt + timedelta(days=1)).strftime('%Y%m%d')
# 防止API请求过于频繁
time_module.sleep(0.5)
# 合并所有批次的数据
if not all_data:
print(f"未获取到任何数据: {symbol}")
return None
# 合并DataFrame
df = pd.concat(all_data, ignore_index=True)
# 数据清洗和格式化
df = df.dropna() # 删除空值
df = df.drop_duplicates(subset=['date']) # 删除重复数据
df = df.sort_values('date').reset_index(drop=True) # 按时间排序
# A股特有的数据清理和时间处理
df = self.clean_a_stock_data(df, timeframe)
# 限制数据条数 - 只有在没有指定明确时间范围时才应用
# 如果用户指定了start_date和end_date，应该返回该时间范围内的所有数据
if limit is not None and len(df) > limit:
# 检查是否指定了明确的时间范围
if start_date and end_date:
# 如果指定了时间范围，优先返回完整的时间范围数据
print(f"用户指定了时间范围 {start_date} 到 {end_date}，返回完整数据 {len(df)} 条记录")
if len(df) > 10000: # 防止数据量过大，设置一个合理的上限
print(f"警告：数据量过大({len(df)}条)，为保证性能将限制为最新的10000条记录")
df = df.tail(10000).reset_index(drop=True)
else:
# 如果没有指定时间范围，使用默认的limit限制
print(f"未指定明确时间范围，应用默认限制，返回最新的 {limit} 条记录")
df = df.tail(limit).reset_index(drop=True)
elif limit is None and len(df) > 10000:
# 即使没有limit限制，也要防止数据量过大影响性能
print(f"无limit限制但数据量过大({len(df)}条)，为保证性能将限制为最新的10000条记录")
df = df.tail(10000).reset_index(drop=True)
# 添加技术指标
df = self.add_indicators(df)
# 最终数据验证 - 确保没有NaN值
import numpy as np
# 检查并处理任何剩余的NaN值
if df.isnull().any().any():
print("警告：发现NaN值，正在清理...")
# 对于数值列，用0填充NaN
numeric_cols = df.select_dtypes(include=[np.number]).columns
for col in numeric_cols:
if col in ['volume_ratio']:
df[col] = df[col].fillna(1.0)
else:
df[col] = df[col].fillna(0)
# 删除仍然包含NaN的行
df = df.dropna()
# 确保所有数值都是有限的
for col in df.select_dtypes(include=[np.number]).columns:
df[col] = df[col].replace([np.inf, -np.inf], 0 if col != 'volume_ratio' else 1.0)
print(f"成功获取A股数据: {len(df)} 条记录 (共 {len(all_data)} 个批次)")
return df
except Exception as e:
print(f"获取A股数据失败: {e}")
traceback.print_exc()
return None
def add_indicators(self, df):
"""添加技术指标"""
try:
import talib.abstract as ta
import numpy as np
# MACD指标
fast = 8
slow = 16
period = 6
macd = ta.MACD(df, fastperiod=fast, slowperiod=slow, signalperiod=period)
df['macd'] = macd['macd'].fillna(0)
df['macdsignal'] = macd['macdsignal'].fillna(0)
df['macdhist'] = macd['macdhist'].fillna(0)
# 移动平均线
df['ma5'] = ta.MA(df, timeperiod=5).fillna(0)
df['ma10'] = ta.MA(df, timeperiod=10).fillna(0)
df['ma30'] = ta.EMA(df, timeperiod=30).fillna(0)
df['ma250'] = ta.MA(df, timeperiod=250).fillna(0)
# RSI指标
df['rsi'] = ta.RSI(df, timeperiod=14).fillna(0)
# 成交量指标
df['avg_volume'] = df['volume'].rolling(10).mean().fillna(0)
df['volume_ratio'] = (df['volume'] / df['avg_volume']).fillna(1.0)
# 处理Infinity和-Infinity值
df['volume_ratio'] = df['volume_ratio'].replace([float('inf'), float('-inf')], 1.0)
# 确保所有指标列都不包含NaN或无限值
indicator_columns = ['macd', 'macdsignal', 'macdhist', 'ma5', 'ma10', 'ma30', 'ma250', 'rsi', 'avg_volume', 'volume_ratio']
for col in indicator_columns:
if col in df.columns:
# 替换NaN、inf、-inf为合理的默认值
df[col] = df[col].replace([np.nan, np.inf, -np.inf], 0 if col != 'volume_ratio' else 1.0)
return df
except Exception as e:
print(f"添加指标失败: {e}")
return df
def search_stock(self, keyword):
"""搜索股票 - 支持代码和名称模糊搜索"""
try:
if not keyword or len(keyword.strip()) == 0:
return []
keyword = keyword.strip().upper()
results = []
# 从热门股票中搜索
popular_stocks = self.get_popular_stocks()
for stock in popular_stocks:
if (keyword in stock['symbol'] or
keyword.lower() in stock['name'].lower() or
stock['symbol'].startswith(keyword)):
results.append({
'symbol': stock['symbol'],
'name': stock['name'],
'sector': stock.get('sector', ''),
'source': '热门股票'
})
# 如果热门股票中找到的结果少于10个，从完整股票列表中搜索
if len(results) < 10:
try:
# 获取完整股票列表进行搜索
stock_info = ak.stock_zh_a_spot_em()
# 搜索前1000只活跃股票
for index, row in stock_info.head(1000).iterrows():
stock_code = str(row['代码'])
stock_name = str(row['名称'])
# 过滤ST股票
if 'ST' in stock_name or '*' in stock_name:
continue
# 检查是否已经在结果中
if any(r['symbol'] == stock_code for r in results):
continue
# 搜索匹配
if (keyword in stock_code or
keyword.lower() in stock_name.lower() or
stock_code.startswith(keyword)):
results.append({
'symbol': stock_code,
'name': stock_name,
'price': float(row['最新价']) if pd.notna(row['最新价']) else 0.0,
'change_pct': float(row['涨跌幅']) if pd.notna(row['涨跌幅']) else 0.0,
'source': '全市场搜索'
})
# 限制结果数量
if len(results) >= 30:
break
except Exception as e:
print(f"全市场搜索失败: {e}")
# 排序：优先显示代码匹配的结果
def sort_key(item):
if item['symbol'].startswith(keyword):
return (0, item['symbol']) # 代码开头匹配优先级最高
elif keyword in item['symbol']:
return (1, item['symbol']) # 代码包含匹配次之
else:
return (2, item['symbol']) # 名称匹配最后
results.sort(key=sort_key)
# 限制返回结果数量
return results[:20]
except Exception as e:
print(f"搜索股票失败: {e}")
return []
def get_stock_by_sector(self, sector=None):
"""根据行业获取股票列表"""
try:
popular_stocks = self.get_popular_stocks()
if sector:
return [stock for stock in popular_stocks if stock.get('sector', '') == sector]
else:
# 按行业分组
sectors = {}
for stock in popular_stocks:
sector_name = stock.get('sector', '其他')
if sector_name not in sectors:
sectors[sector_name] = []
sectors[sector_name].append(stock)
return sectors
except Exception as e:
print(f"获取行业股票失败: {e}")
return {} if sector is None else []
def get_all_sectors(self):
"""获取所有行业分类"""
try:
popular_stocks = self.get_popular_stocks()
sectors = set()
for stock in popular_stocks:
sector = stock.get('sector', '其他')
sectors.add(sector)
return sorted(list(sectors))
except Exception as e:
print(f"获取行业分类失败: {e}")
return []
def is_trading_day(self, date):
"""判断是否为交易日（排除周末和节假日）"""
try:
# 将日期转换为datetime对象
if isinstance(date, str):
date = datetime.strptime(date.split()[0], '%Y-%m-%d')
elif isinstance(date, pd.Timestamp):
date = date.to_pydatetime()
# 周末不是交易日
if date.weekday() >= 5: # 5=周六, 6=周日
return False
# 这里可以进一步添加节假日判断
# 目前暂时只过滤周末
return True
except Exception as e:
print(f"判断交易日失败: {e}")
return True # 默认返回True，避免过度过滤
def is_trading_time(self, dt):
"""判断是否为交易时间"""
try:
if isinstance(dt, str):
dt = pd.to_datetime(dt)
time_str = dt.strftime('%H:%M')
# 上午交易时间：09:30-11:30
morning_start = self.trading_hours['morning']['start']
morning_end = self.trading_hours['morning']['end']
# 下午交易时间：13:00-15:00
afternoon_start = self.trading_hours['afternoon']['start']
afternoon_end = self.trading_hours['afternoon']['end']
return ((morning_start <= time_str <= morning_end) or
(afternoon_start <= time_str <= afternoon_end))
except Exception as e:
print(f"判断交易时间失败: {e}")
return True # 默认返回True，避免过度过滤
def adjust_timestamp_for_trading_hours(self, df, timeframe):
"""根据A股交易时间调整时间戳"""
try:
if df is None or len(df) == 0:
return df
# 确保date列是datetime类型
if 'date' in df.columns:
df['date'] = pd.to_datetime(df['date'])
# 对于日线数据，设置为收盘时间（15:00）
if timeframe == '1d':
df['date'] = df['date'].dt.normalize() + pd.Timedelta(hours=15)
# 对于分钟级数据，过滤非交易时间的数据
elif timeframe in ['1m', '5m', '15m', '30m', '1h']:
# 过滤交易日
df = df[df['date'].apply(self.is_trading_day)]
# 过滤交易时间（只在有足够数据时进行）
if len(df) > 10: # 避免过度过滤导致数据不足
df = df[df['date'].apply(self.is_trading_time)]
# 重新计算时间戳
if 'date' in df.columns:
# 将时间转换为上海时区
df['date'] = df['date'].dt.tz_localize('Asia/Shanghai', ambiguous='infer', nonexistent='shift_forward')
# 转换为毫秒时间戳
df['timestamp'] = df['date'].astype('int64') // 10**6
return df.reset_index(drop=True)
except Exception as e:
print(f"调整A股时间戳失败: {e}")
traceback.print_exc()
return df
def get_trading_calendar(self, start_date, end_date):
"""获取交易日历（简化版本）"""
try:
# 使用akshare获取交易日历
trading_calendar = ak.tool_trade_date_hist_sina()
# 过滤指定日期范围
start_dt = pd.to_datetime(start_date)
end_dt = pd.to_datetime(end_date)
trading_days = []
for _, row in trading_calendar.iterrows():
trade_date = pd.to_datetime(row['trade_date'])
if start_dt <= trade_date <= end_dt:
trading_days.append(trade_date.strftime('%Y-%m-%d'))
return trading_days
except Exception as e:
print(f"获取交易日历失败: {e}")
# 如果获取失败，生成简单的工作日列表（排除周末）
trading_days = []
current = pd.to_datetime(start_date)
end = pd.to_datetime(end_date)
while current <= end:
if current.weekday() < 5: # 周一到周五
trading_days.append(current.strftime('%Y-%m-%d'))
current += timedelta(days=1)
return trading_days
def fill_trading_gaps(self, df, timeframe):
"""填补A股交易时间间隙，确保图表连续性"""
try:
if df is None or len(df) == 0:
return df
# 对于日线数据，不需要填补间隙，因为本来就是每日一个数据点
if timeframe == '1d':
return df
# 对于分钟级数据，创建完整的交易时间序列
if timeframe in ['1m', '5m', '15m', '30m', '1h']:
# 获取数据的开始和结束时间
start_date = df['date'].min().date()
end_date = df['date'].max().date()
# 创建完整的交易时间序列
complete_times = []
current_date = start_date
# 获取时间间隔（分钟）
freq_map = {'1m': 1, '5m': 5, '15m': 15, '30m': 30, '1h': 60}
freq_minutes = freq_map.get(timeframe, 5)
while current_date <= end_date:
# 只处理交易日
if self.is_trading_day(current_date):
# 上午交易时间 - 使用datetime.time而不是pd.Time
morning_start = pd.Timestamp.combine(current_date, time(9, 30))
morning_end = pd.Timestamp.combine(current_date, time(11, 30))
# 下午交易时间
afternoon_start = pd.Timestamp.combine(current_date, time(13, 0))
afternoon_end = pd.Timestamp.combine(current_date, time(15, 0))
# 生成上午时间序列
current_time = morning_start
while current_time <= morning_end:
complete_times.append(current_time)
current_time += pd.Timedelta(minutes=freq_minutes)
# 生成下午时间序列
current_time = afternoon_start
while current_time <= afternoon_end:
complete_times.append(current_time)
current_time += pd.Timedelta(minutes=freq_minutes)
current_date += timedelta(days=1)
# 创建完整时间序列的DataFrame
if complete_times:
complete_df = pd.DataFrame({'date': complete_times})
complete_df['date'] = complete_df['date'].dt.tz_localize('Asia/Shanghai')
complete_df['timestamp'] = complete_df['date'].astype('int64') // 10**6
# 将原始数据合并到完整时间序列
# 使用时间戳进行合并，避免时区问题
df_merged = pd.merge(complete_df, df, on='timestamp', how='left', suffixes=('', '_orig'))
# 保持原有date列
df_merged['date'] = df_merged['date']
# 对于缺失的OHLCV数据，使用前向填充
price_cols = ['open', 'high', 'low', 'close']
for col in price_cols:
if col in df_merged.columns:
df_merged[col] = df_merged[col].ffill()
# 成交量缺失时设为0
if 'volume' in df_merged.columns:
df_merged['volume'] = df_merged['volume'].fillna(0)
# 删除辅助列
cols_to_drop = [col for col in df_merged.columns if col.endswith('_orig')]
df_merged = df_merged.drop(columns=cols_to_drop)
return df_merged
return df
except Exception as e:
print(f"填补交易时间间隙失败: {e}")
traceback.print_exc()
return df
def clean_a_stock_data(self, df, timeframe):
"""清理A股数据，处理异常值和时间问题"""
try:
if df is None or len(df) == 0:
return df
import numpy as np
# 首先删除所有包含NaN的行
df = df.dropna()
# 删除价格异常的数据
price_cols = ['open', 'high', 'low', 'close']
for col in price_cols:
if col in df.columns:
# 删除价格为0、负数、NaN、inf的记录
df = df[df[col] > 0]
df = df[np.isfinite(df[col])]
# 检查OHLC逻辑合理性
if all(col in df.columns for col in price_cols):
# high应该是最高价
df = df[df['high'] >= df['open']]
df = df[df['high'] >= df['close']]
# low应该是最低价
df = df[df['low'] <= df['open']]
df = df[df['low'] <= df['close']]
# high应该大于等于low
df = df[df['high'] >= df['low']]
# 删除成交量异常的数据
if 'volume' in df.columns:
# 删除成交量为负数、NaN、inf的记录
df = df[df['volume'] >= 0]
df = df[np.isfinite(df['volume'])]
# 确保所有数值列都不包含NaN或无限值
numeric_cols = df.select_dtypes(include=[np.number]).columns
for col in numeric_cols:
# 替换NaN、inf、-inf为0（除了价格列，价格列的异常值已经被过滤掉了）
if col not in price_cols:
df[col] = df[col].replace([np.nan, np.inf, -np.inf], 0)
# 确保时间序列连续性（仅对分钟级数据）
if timeframe in ['1m', '5m', '15m', '30m', '1h']:
df = self.fill_trading_gaps(df, timeframe)
# 最后再次检查并清理任何剩余的NaN值
df = df.dropna()
return df.reset_index(drop=True)
except Exception as e:
print(f"清理A股数据失败: {e}")
return df