Skip to content

A
alpha-mind
Commit ebd16b85 authored by Dr.李's avatar Dr.李
Browse files
Options

added more industry styles

parent 4944d755
Hide whitespace changes
Inline Side-by-side
Showing with 102 additions and 20 deletions
alphamind/data/engines/industries.py 0 → 100644
View file @ ebd16b85
# -*- coding: utf-8 -*-
"""
Created on 2018-1-24
@author: cheng.li
"""
INDUSTRY_MAPPING = {
'sw': {
1: ["采掘", "传媒", "电气设备", "电子", "房地产", "纺织服装", "非银金融", "钢铁", "公用事业", "国防军工", "化工", "机械设备", "计算机", "家用电器", "建筑材料",
"建筑装饰", "交通运输", "农林牧渔", "汽车", "轻工制造", "商业贸易", "食品饮料", "通信", "休闲服务", "医药生物", "银行", "有色金属", "综合"],
2: ["白色家电", "半导体", "包装印刷", "保险", "玻璃制造", "采掘服务", "餐饮", "畜禽养殖", "船舶制造", "地面兵装", "电机", "电力", "电气自动化设备", "电源设备",
"电子制造", "动物保健", "多元金融", "房地产开发", "房屋建设", "纺织制造", "服装家纺", "钢铁", "港口", "高低压设备", "高速公路", "工业金属", "公交", "光学光电子",
"航空运输", "航空装备", "航天装备", "航运", "互联网传媒", "化学纤维", "化学原料", "化学制品", "化学制药", "环保工程及服务", "黄金", "机场", "基础建设",
"计算机设备", "计算机应用", "家用轻工", "金属非金属新材料", "金属制品", "景点", "酒店", "林业", "旅游综合", "贸易", "煤炭开采", "农产品加工", "农业综合",
"其他采掘", "其他电子", "其他建材", "其他交运设备", "其他轻工制造", "其他休闲服务", "汽车服务", "汽车零部件", "汽车整车", "燃气", "商业物业经营", "生物制品",
"石油化工", "石油开采", "食品加工", "视听器材", "水泥制造", "水务", "饲料", "塑料", "铁路运输", "通信设备", "通信运营", "通用机械", "文化传媒", "物流",
"稀有金属", "橡胶", "一般零售", "医疗服务", "医疗器械", "医药商业", "仪器仪表", "银行", "饮料制造", "营销传播", "渔业", "元件", "园林工程", "园区开发",
"运输设备", "造纸", "证券", "中药", "种植业", "专业工程", "专业零售", "专用设备", "装修装饰", "综合"],
3: ["IT服务", "LED", "氨纶", "白酒", "百货", "半导体材料", "包装印刷", "保险", "被动元件", "冰箱", "玻璃制造", "玻纤", "彩电", "餐饮", "超市",
"城轨建设", "乘用车", "储能设备", "畜禽养殖", "船舶制造", "纯碱", "磁性材料", "氮肥", "低压设备", "涤纶", "地面兵装", "电机", "电网自动化", "电子零部件制造",
"电子系统组装", "动物保健", "多业态零售", "多元金融", "房地产开发", "房屋建设", "纺织服装设备", "纺织化学用品", "非金属新材料", "分立器件", "风电设备", "氟化工及制冷剂",
"辅料", "复合肥", "改性塑料", "钢结构", "港口", "高速公路", "高压设备", "工程机械", "工控自动化", "公交", "管材", "光伏设备", "光学元件", "国际工程承包",
"果蔬加工", "海洋捕捞", "航空运输", "航空装备", "航天装备", "航运", "合成革", "互联网信息服务", "化学工程", "化学原料药", "化学制剂", "环保工程及服务", "环保设备",
"黄金", "黄酒", "火电", "火电设备", "机场", "机床工具", "机械基础件", "集成电路", "计量仪表", "计算机设备", "家电零部件", "家纺", "家具", "钾肥", "焦炭加工",
"金属新材料", "金属制品", "酒店", "聚氨酯", "空调", "锂", "粮食种植", "粮油加工", "林业", "磷肥", "磷化工及磷酸盐", "楼宇设备", "路桥施工", "轮胎",
"旅游综合", "铝", "氯碱", "毛纺", "贸易", "煤炭开采", "棉纺", "民爆用品", "磨具磨料", "耐火材料", "男装", "内燃机", "农药", "农业综合", "农用机械",
"女装", "啤酒", "平面媒体", "葡萄酒", "普钢", "其他采掘", "其他采掘服务", "其他电子", "其他纺织", "其他服装", "其他互联网服务", "其他化学原料", "其他化学制品",
"其他基础建设", "其他家用轻工", "其他建材", "其他交运设备", "其他酒类", "其他农产品加工", "其他轻工制造", "其他塑料制品", "其他文化传媒", "其他稀有小金属", "其他纤维",
"其他橡胶制品", "其他休闲服务", "其他种植业", "其他专业工程", "其它电源设备", "其它视听器材", "其它通用机械", "其它专用机械", "汽车服务", "汽车零部件", "铅锌",
"燃机发电", "燃气", "热电", "人工景点", "日用化学产品", "肉制品", "乳品", "软件开发", "软饮料", "商用载货车", "商用载客车", "生物制品", "石油加工", "石油开采",
"石油贸易", "食品综合", "水产养殖", "水电", "水利工程", "水泥制造", "水务", "丝绸", "饲料", "炭黑", "特钢", "调味发酵品", "铁路建设", "铁路设备", "铁路运输",
"通信传输设备", "通信配套服务", "通信运营", "铜", "涂料油漆油墨制造", "维纶", "文娱用品", "钨", "无机盐", "物流", "稀土", "洗衣机", "显示器件", "线缆部件及其他",
"小家电", "鞋帽", "新能源发电", "休闲服装", "冶金矿采化工设备", "一般物业经营", "医疗服务", "医疗器械", "医药商业", "仪器仪表", "移动互联网服务", "银行", "印染",
"印刷包装机械", "印制电路板", "营销服务", "影视动漫", "油气钻采服务", "有线电视网络", "园林工程", "园区开发", "造纸", "粘胶", "证券", "制冷空调设备", "中压设备",
"中药", "终端设备", "种子生产", "重型机械", "珠宝首饰", "专业连锁", "专业市场", "装修装饰", "自然景点", "综合", "综合电力设备商"]
},
'zz': {
1: ["电信业务", "工业", "公用事业", "金融地产", "可选消费", "能源", "信息技术", "医药卫生", "原材料", "主要消费"],
2: ["半导体", "保险", "传媒", "电信服务", "房地产", "公用事业", "计算机及电子设备", "计算机运用", "家庭与个人用品", "交通运输", "零售业", "耐用消费品与服装", "能源",
"其他金融", "汽车与汽车零部件", "商业服务与用品", "食品、饮料与烟草", "食品与主要用品零售", "通信设备", "消费者服务", "医疗器械与服务", "医药生物", "银行", "原材料",
"资本品", "资本市场"],
3: ["半导体", "包装食品与肉类", "保险", "传媒", "道路运输", "电力", "电脑与外围设备", "电气设备", "电网", "电信运营服务", "电信增值服务", "电子设备", "多元化零售",
"房地产管理与服务", "房地产开发与园区", "纺织服装", "非金属采矿及制品", "钢铁", "个人用品", "工业集团企业", "供热或其他公用事业", "航空公司", "航空航天与国防",
"航空货运与物流", "航运", "互联网服务", "互联网零售", "化学原料", "化学制品", "环保设备、工程与服务", "机械制造", "家常用品", "家庭耐用消费品", "建筑材料", "建筑产品",
"建筑与工程", "交通基本设施", "酒店、餐馆与休闲", "煤炭", "能源开采设备与服务", "农牧渔产品", "其他金融服务", "其他零售", "汽车零配件与轮胎", "汽车与摩托车", "燃气",
"日用品经销商", "容器与包装", "软件开发", "商业服务与用品", "商业银行", "生物科技", "石油与天然气", "食品与主要用品零售", "水务", "通信设备", "消费信贷", "信息技术服务",
"休闲设备与用品", "医疗器械", "医疗用品与服务提供商", "饮料", "有色金属", "纸类与林业产品", "制药", "制药与生物科技服务", "珠宝与奢侈品", "资本市场", "综合消费者服务"]
},
'zjh': {
1: ["采矿业", "电力、热力、燃气及水生产和供应业", "房地产业", "建筑业", "交通运输、仓储和邮政业", "教育", "金融业", "居民服务、修理和其他服务业", "科学研究和技术服务业",
"农、林、牧、渔业", "批发和零售业", "水利、环境和公共设施管理业", "卫生和社会工作", "文化、体育和娱乐业", "信息传输、软件和信息技术服务业", "制造业", "住宿和餐饮业", "综合",
"租赁和商务服务业"],
2: ["保险业", "餐饮业", "仓储业", "畜牧业", "道路运输业", "电力、热力生产和供应业", "电气机械和器材制造业", "电信、广播电视和卫星传输服务", "房地产业", "房屋建筑业",
"纺织服装、服饰业", "纺织业", "非金属矿采选业", "非金属矿物制品业", "废弃资源综合利用业", "公共设施管理业", "广播、电视、电影和影视录音制作业", "航空运输业", "黑色金属矿采选业",
"黑色金属冶炼和压延加工业", "互联网和相关服务", "化学纤维制造业", "化学原料和化学制品制造业", "货币金融服务", "机动车、电子产品和日用产品修理业", "计算机、通信和其他电子设备制造业",
"家具制造业", "建筑安装业", "建筑装饰和其他建筑业", "教育", "金属制品业", "酒、饮料和精制茶制造业", "开采辅助活动", "林业", "零售业", "煤炭开采和洗选业",
"木材加工和木、竹、藤、棕、草制品业", "农、林、牧、渔服务业", "农副食品加工业", "农业", "批发业", "皮革、毛皮、羽毛及其制品和制鞋业", "其他金融业", "其他制造业", "汽车制造业",
"燃气生产和供应业", "软件和信息技术服务业", "商务服务业", "生态保护和环境治理业", "石油和天然气开采业", "石油加工、炼焦和核燃料加工业", "食品制造业", "水的生产和供应业",
"水利管理业", "水上运输业", "体育", "铁路、船舶、航空航天和其它运输设备制造业", "铁路运输业", "通用设备制造业", "土木工程建筑业", "卫生", "文化艺术业",
"文教、工美、体育和娱乐用品制造业", "橡胶和塑料制品业", "新闻和出版业", "研究和试验发展", "医药制造业", "仪器仪表制造业", "印刷和记录媒介复制业", "邮政业", "有色金属矿采选业",
"有色金属冶炼和压延加工业", "渔业", "造纸和纸制品业", "住宿业", "专业技术服务业", "专用设备制造业", "装卸搬运和运输代理业", "资本市场服务", "综合", "租赁业"],
},
'dx': {
1: ["Cyclical", "Defensive", "Sensitive"],
2: ["ConsumerDiscretionary", "ConsumerStaples", "Financials", "HealthCare", "Industrials", "IT", "Materials", "RealEstate", "Utilities"]
}
}
alphamind/data/engines/sqlengine.py
View file @ ebd16b85
......@@ -207,12 +207,12 @@ class SqlEngine(object):
cond = universe._query_statements(start_date, end_date, None)
big_table = join(Market, UniverseTable,
and_(
Market.trade_date == UniverseTable.trade_date,
Market.code == UniverseTable.code,
cond
)
)
and_(
Market.trade_date == UniverseTable.trade_date,
Market.code == UniverseTable.code,
cond
)
)
query = select([Market.trade_date, Market.code, stats]) \
.select_from(big_table)
......@@ -379,7 +379,7 @@ class SqlEngine(object):
FullFactor.code == UniverseTable.code,
cond
)
)
)
query = select(
[FullFactor.trade_date, FullFactor.code, FullFactor.isOpen] + list(factor_cols.keys())) \
......@@ -498,7 +498,7 @@ class SqlEngine(object):
FullFactor.code == UniverseTable.code,
cond
)
)
)
query = select(
[FullFactor.trade_date, FullFactor.code, special_risk_col] + risk_exposure_cols).select_from(big_table) \
......@@ -508,7 +508,8 @@ class SqlEngine(object):
if universe.is_filtered:
codes = universe.query(self, start_date, end_date, dates)
risk_exp = pd.merge(risk_exp, codes, how='inner', on=['trade_date', 'code']).sort_values(['trade_date', 'code'])
risk_exp = pd.merge(risk_exp, codes, how='inner', on=['trade_date', 'code']).sort_values(
['trade_date', 'code'])
return risk_cov, risk_exp
......@@ -536,7 +537,8 @@ class SqlEngine(object):
start_date: str = None,
end_date: str = None,
dates: Iterable[str] = None,
category: str = 'sw'):
category: str = 'sw',
level: int = 1):
industry_category_name = _map_industry_category(category)
cond = universe._query_statements(start_date, end_date, dates)
......@@ -548,12 +550,15 @@ class SqlEngine(object):
Industry.industry == industry_category_name,
cond
)
)
)
code_name = 'industryID' + str(level)
category_name = 'industryName' + str(level)
query = select([Industry.trade_date,
Industry.code,
Industry.industryID1.label('industry_code'),
Industry.industryName1.label('industry')]).select_from(big_table).distinct()
getattr(Industry, code_name).label('industry_code'),
getattr(Industry, category_name).label('industry')]).select_from(big_table).distinct()
df = pd.read_sql(query, self.engine)
if universe.is_filtered:
......@@ -802,10 +807,10 @@ class SqlEngine(object):
else:
id_filter = 'in_'
t = select([table.trade_id]).\
t = select([table.trade_id]). \
where(and_(table.trade_date <= ref_date,
table.operation == 'withdraw')).alias('t')
query = select([table]).\
query = select([table]). \
where(and_(getattr(table.trade_id, id_filter)(t),
table.trade_date <= ref_date,
table.operation == 'lend'))
......@@ -823,7 +828,7 @@ class SqlEngine(object):
rule = x['price_rule'].split('@')
if rule[0] in ['closePrice', 'openPrice']:
query = select([getattr(Market, rule[0])]).\
query = select([getattr(Market, rule[0])]). \
where(and_(Market.code == code, Market.trade_date == rule[1]))
data = pd.read_sql(query, self.engine)
if not data.empty:
......@@ -835,6 +840,7 @@ class SqlEngine(object):
else:
raise KeyError('do not have rule for %s' % x['price_rule'])
return price
df['price'] = df.apply(lambda x: parse_price_rule(x), axis=1)
df.drop(['remark', 'price_rule', 'operation'], axis=1, inplace=True)
......@@ -848,12 +854,10 @@ class SqlEngine(object):
if __name__ == '__main__':
universe = Universe('ss', ['hs300'])
engine = SqlEngine()
df = engine.fetch_outright_status('2017-12-28')
df = engine.fetch_industry_range(universe, '2017-12-28', '2017-12-31', category='dx', level=3)
print(df)
alphamind/data/engines/utilities.py
View file @ ebd16b85
......@@ -43,5 +43,15 @@ def _map_factors(factors: Iterable[str], used_factor_tables) -> Dict:
def _map_industry_category(category: str) -> str:
if category == 'sw':
return '申万行业分类'
elif category == 'zz':
return '中证行业分类'
elif category == 'dx':
return '中证行业分类'
elif category == 'zjh':
return '证监会行业V2012'
else:
raise ValueError("No other industry is supported at the current time")
\ No newline at end of file
raise ValueError("No other industry is supported at the current time")
def industry_list(catrgory, level=1):
pass
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment