mns-scheduler 1.2.3.5__tar.gz → 1.2.3.7__tar.gz

{mns_scheduler-1.2.3.5 → mns_scheduler-1.2.3.7}/PKG-INFO

@@ -1,3 +1,3 @@
 Metadata-Version: 2.1
 Name: mns-scheduler
-Version: 1.2.3.5
+Version: 1.2.3.7

{mns_scheduler-1.2.3.5 → mns_scheduler-1.2.3.7}/mns_scheduler/company_info/clean/company_info_clean_api.py

@@ -13,6 +13,7 @@ import mns_scheduler.company_info.constant.company_constant_data as company_cons
 import mns_common.constant.db_name_constant as db_name_constant
 import mns_scheduler.concept.ths.detaill.ths_concept_detail_api as ths_concept_detail_api
 import mns_scheduler.company_info.base.sync_company_base_info_api as company_info_sync_api
+import mns_common.utils.data_frame_util as data_frame_util
 
 mongodb_util = MongodbUtil('27017')
 import mns_common.component.common_service_fun_api as common_service_fun_api
@@ -20,21 +21,26 @@ import mns_common.component.company.company_common_service_api as company_common
 
 
 # 修改行业信息
-def fix_company_industry(symbol):
+def clean_company_info(symbol):
     if symbol is not None:
         query = {"symbol": symbol}
         company_info = mongodb_util.find_query_data('company_info_base', query)
     else:
         company_info = mongodb_util.find_all_data('company_info_base')
 
-    # company_info = company_info.set_index(['second_sw_industry'], drop=False)
-    # del company_info['industry']
+    company_info = company_constant_data.fix_second_industry(company_info)
+
+    company_info = company_info.set_index(['second_sw_industry'], drop=False)
+
+    # 修改行业名称
+    del company_info['industry']
     # fix industry  name
-    # company_info = company_constant_data.remove_industry_name_special(company_info)
-    # industry_final_fix_df = industry_final_fix_df.set_index(['second_sw_industry'], drop=True)
-    # company_info = pd.merge(company_info, industry_final_fix_df, how='outer',
-    #                         left_index=True, right_index=True)
-    # 将申万第三行业做为行业
+    industry_final_fix_df = company_constant_data.get_fix_industry_name_df()
+    industry_final_fix_df = industry_final_fix_df.set_index(['second_sw_industry'], drop=True)
+    company_info = pd.merge(company_info, industry_final_fix_df, how='outer',
+                            left_index=True, right_index=True)
+
+    # 将申万第三行业做为行业 拆分过大的二级行业 主要有通用设备 和专业设备
     company_info = company_constant_data.fix_industry_use_sw_third(company_info.copy())
     company_info['industry'] = company_info['industry'].fillna('综合')
     company_info = company_constant_data.filed_sort(company_info)
@@ -65,7 +71,7 @@ def fix_company_industry(symbol):
     except BaseException as e:
         logger.error("出现异常:{},{}", symbol, e)
         query = {'concept_code': 885598}
-        ths_stock_concept_detail = mongodb_util.find_query_data('ths_stock_concept_detail', query)
+        ths_stock_concept_detail = mongodb_util.find_query_data(db_name_constant.THS_STOCK_CONCEPT_DETAIL, query)
         sub_stock_symbol_list = list(ths_stock_concept_detail['symbol'])
     company_info.loc[:, 'sub_stock'] = False
     company_info.loc[company_info['symbol'].isin(sub_stock_symbol_list), 'sub_stock'] = True
@@ -73,6 +79,20 @@ def fix_company_industry(symbol):
     try:
         company_info.dropna(subset=['symbol'], axis=0, inplace=True)
         company_info.dropna(subset=['_id'], axis=0, inplace=True)
+        ths_stock_industry_detail_df = mongodb_util.find_all_data(db_name_constant.THS_STOCK_INDUSTRY_DETAIL)
+        if data_frame_util.is_not_empty(ths_stock_industry_detail_df):
+            ths_stock_industry_detail_df = ths_stock_industry_detail_df[
+                ['symbol', 'ths_industry_name', 'ths_industry_code']]
+            ths_stock_industry_detail_df = ths_stock_industry_detail_df.set_index(['symbol'], drop=True)
+            company_info = company_info.set_index(['_id'], drop=False)
+            company_info = pd.merge(company_info, ths_stock_industry_detail_df, how='outer',
+                                    left_index=True, right_index=True)
+            company_info['ths_industry_code'] = company_info['ths_industry_code'].fillna('0')
+            company_info['ths_industry_name'] = company_info['ths_industry_name'].fillna('异常')
+
+        else:
+            company_info['ths_industry_code'] = '0'
+            company_info['ths_industry_name'] = '异常'
         mongodb_util.save_mongo(company_info, db_name_constant.COMPANY_INFO)
         # 保存历史数据
         save_company_info_his(company_info)
@@ -102,7 +122,7 @@ def new_company_info_update():
     for company_one in new_stock.itertuples():
         try:
             company_info_sync_api.sync_company_base_info([company_one.symbol])
-            fix_company_industry(company_one.symbol)
+            clean_company_info(company_one.symbol)
 
         except BaseException as e:
             logger.error("出现异常:{}", e)
@@ -110,4 +130,4 @@ def new_company_info_update():
 
 
 if __name__ == '__main__':
-    fix_company_industry('600230')
+    clean_company_info(None)

{mns_scheduler-1.2.3.5 → mns_scheduler-1.2.3.7}/mns_scheduler/company_info/constant/company_constant_data.py

@@ -46,34 +46,79 @@ def get_fix_symbol_industry():
                          ['830799', '艾融软件', '490101', '证券'],
                          ['300033', '同花顺', '490101', '证券'],
                          ['300399', '天利科技', '490201', '保险'],
-
                          # EDA软件
                          ['301269', '华大九天', '270108', '半导体设备'],
                          ['688206', '概伦电子', '270108', '半导体设备'],
                          ['301095', '广立微', '270108', '半导体设备'],
-
                          ['002131', '利欧股份', '720501', '营销代理'],
 
                          ],
-                        columns=['symbol', 'name', 'new_industry_code', 'new_industry'])
+                        columns=['symbol',
+                                 'name',
+                                 'new_industry_code',  # 三级行业代码
+                                 'new_industry'])
+
+
+# 修改二级行业分类的股票
+def get_fix_second_industry_info():
+    return pd.DataFrame([
+        ['110200', '渔业', "农林牧渔", "110000", '农业综合Ⅱ', '110900'],
+
+        ['110300', '林业', "农林牧渔", "110000", '农业综合Ⅱ', '110900'],
+
+        ['450700', '旅游零售Ⅱ', '社会服务', '460000', '旅游及景区', '461000'],
+
+        ['220700', '化工新材料Ⅱ', '基础化工', '220000', '非金属材料Ⅱ', '220900'],
+
+        ['330700', '其他家电Ⅱ', '家用电器', '330000', '小家电', '330300'],
+
+        ['250100', '建筑材料', '建筑材料', '610000', '装修建材', '610300'],
+
+        ['460600', '体育Ⅱ', '综合', '510000', '综合Ⅱ', '510100'],
+
+        ['770300', '医疗美容', '美容护理', '770000', '化妆品', '770200'],
+
+    ],
+        columns=['original_second_industry_code',
+                 'original_second_industry_name',
+                 'first_sw_industry',
+                 'first_industry_code',
+                 'second_sw_industry',  # 二级级行业代码
+                 'second_industry_code'])
+
+
+def fix_second_industry(company_info):
+    fix_second_industry_df = get_fix_second_industry_info()
+    del fix_second_industry_df['original_second_industry_name']
+    fix_second_company_df = company_info.loc[
+        company_info['second_industry_code'].isin(fix_second_industry_df['original_second_industry_code'])]
+
+    no_fix_second_company_df = company_info.loc[~(
+        company_info['second_industry_code'].isin(fix_second_industry_df['original_second_industry_code']))]
 
+    fix_second_company_df = fix_second_company_df.set_index(['second_industry_code'], drop=True)
+    del fix_second_company_df['second_sw_industry']
+    del fix_second_company_df['first_industry_code']
+    del fix_second_company_df['first_sw_industry']
+    fix_second_industry_df = fix_second_industry_df.set_index(['original_second_industry_code'], drop=True)
 
-# def remove_industry_name_special(industry_df):
-#     industry_df['industry'] = industry_df['industry'].str.replace('Ⅱ', '', regex=False)
-#     return industry_df
+    fix_second_company_df = pd.merge(fix_second_company_df, fix_second_industry_df, how='outer',
+                                     left_index=True, right_index=True)
 
+    return pd.concat([no_fix_second_company_df, fix_second_company_df])
 
-# 修改行业名称
-def get_industry_final_fix_df():
+
+# 修改行业名
+def get_fix_industry_name_df():
     return pd.DataFrame([
 
-        # 交通运输
+        # 交通运输 1
         ['物流', '物流'],
         ['铁路公路', '铁路公路'],
         ['航运港口', '航运港口'],
         ['航空机场', '航空机场'],
 
-        # 传媒
+        # 传媒 2
         ['数字媒体', '数字媒体'],
         ['电视广播Ⅱ', '电视广播'],
         ['游戏Ⅱ', '游戏'],
@@ -81,22 +126,21 @@ def get_industry_final_fix_df():
         ['影视院线', '影视院线'],
         ['广告营销', '广告营销'],
 
-        # 公用事业
+        # 公用事业 3
         ['燃气Ⅱ', '燃气'],
         ['电力', '电力'],
 
-        # 农林牧渔
-        ['养殖业', '养殖业'],  # merge 农林牧渔
-        ['农产品加工', '农产品加工'],  # merge 农林牧渔
-        ['饲料', '饲料'],  # merge  to 农林牧渔
-        ['渔业', '渔业'],  # merge  to 农林牧渔
-        # merge 农林牧渔
+        # 农林牧渔 4
+        ['养殖业', '养殖业'],
+        ['农产品加工', '农产品加工'],
+        ['饲料', '饲料'],
+        ['渔业', '渔业'],  # merge  to 农业综合
         ['动物保健Ⅱ', '动物保健'],
         ['种植业', '种植业'],
-        ['林业Ⅱ', '林业'],  # merge  农林牧渔
-        ['农业综合Ⅱ', '农业综合'],  # merge  农林牧渔
+        # ['林业Ⅱ', '林业'],  # merge  农业综合
+        ['农业综合Ⅱ', '农业综合'],  #
 
-        # 医药生物
+        # 医药生物 5
         ['化学制药', '化学制药'],
         ['生物制品', '生物制品'],
         ['中药Ⅱ', '中药'],
@@ -104,46 +148,85 @@ def get_industry_final_fix_df():
         ['医疗服务', '医疗服务'],
         ['医药商业', '医药商业'],
 
-        # 商贸零售
+        # 商贸零售 6
         ['一般零售', '一般零售'],
         ['互联网电商', '互联网电商'],
         ['贸易Ⅱ', '贸易'],  #
-        ['专业连锁Ⅱ', '专业连锁'],  # 专业连锁 综合Ⅱ
-        ['旅游零售Ⅱ', '旅游零售'],  # m
+        ['专业连锁Ⅱ', '零售专业连锁'],  # 专业连锁 综合Ⅱ
+        # ['旅游零售Ⅱ', '旅游零售'],  # merge旅游及景区
 
-        # 国防
-        ['军工电子Ⅱ', '军工电子'],  # todo merge 国防
-        ['地面兵装Ⅱ', '地面兵装'],  # todo merge 国防
+        # 国防 7
+        ['军工电子Ⅱ', '军工电子'],
+        ['地面兵装Ⅱ', '地面兵装'],
         ['航天装备Ⅱ', '航天装备'],
-        ['航空装备Ⅱ', '航空装备'],  # todo merge 国防
+        ['航空装备Ⅱ', '航空装备'],
         ['航海装备Ⅱ', '航海装备'],
 
-        # 基础化工
+        # 基础化工 8
         ['化学制品', '化学制品'],
         ['化学原料', '化学原料'],
         ['化学纤维', '化学纤维'],
         ['农化制品', '化肥农药'],
         ['塑料', '塑料'],
-        ['橡胶', '橡胶'],  # todo   exclude
+        ['橡胶', '橡胶'],
         ['非金属材料Ⅱ', '非金属材料'],
 
-        # 家用电器
+        # 家用电器 9
         ['白色家电', '白色家电'],  # merge 家用电器
         ['照明设备Ⅱ', '照明设备'],  # merge 家用电器
-        ['其他家电Ⅱ', '其他家电'],  # merge  家用电器
+        # ['其他家电Ⅱ', '其他家电'],  # merge  小家电
         ['家电零部件Ⅱ', '家电零部件'],  # merge 家用电器
         ['小家电', '小家电'],  # merge '家用电器'
         ['黑色家电', '黑色家电'],  # merge 家用电器
         ['厨卫电器', '厨卫电器'],  # merge   家用电器
 
-        # 汽车
+        # 建筑材料  10
+        ['装修建材', '装修建材'],  #
+        ['建筑建材', '装修建材'],  #
+        ['玻璃玻纤', '玻璃玻纤'],
+        ['水泥', '水泥'],
+
+        # 建筑装饰 11
+        ['基础建设', '基础建设'],
+        ['房屋建设Ⅱ', '房屋建设'],
+        ['工程咨询服务Ⅱ', '工程咨询服务'],
+        ['专业工程', '建筑专业工程'],
+        ['装修装饰Ⅱ', '装修装饰'],
+
+        # 房地产 12
+        ['房地产开发', '房地产'],
+        ['房地产服务', '房地产'],
+
+        # 有色金属 13
+        ['能源金属', '能源金属'],
+        ['小金属', '小金属'],
+        ['贵金属', '贵金属'],  #
+        ['金属新材料', '金属新材料'],
+        ['工业金属', '工业金属'],  # 铅锌  铝  铜
+
+        # 机械设备 14
+        ['自动化设备', '自动化设备'],
+        ['轨交设备Ⅱ', '轨交设备'],
+        ['通用设备', '通用设备'],
+        ['专用设备', '专用设备'],
+        ['工程机械', '工程机械'],
+
+        # 汽车 15
         ['汽车零部件', '汽车零部件'],
         ['汽车服务', '汽车服务'],
-        ['乘用车', '汽车整车'],  # = merge 汽车整车
-        ['商用车', '汽车整车'],
+        ['乘用车', '乘用车'],  # = merge 汽车整车
+        ['商用车', '商用车'],
         ['摩托车及其他', '摩托车及其他'],
 
-        # 电力设备
+        # 煤炭 16
+        ['焦炭Ⅱ', '焦炭'],  # merge  to 煤炭
+        ['煤炭开采', '煤炭开采'],  # merge 煤炭
+
+        # 环保 17
+        ['环境治理', '环境治理'],  # merge, 环保
+        ['环保设备Ⅱ', '环保设备'],  # merge '环保'
+
+        # 电力设备 18
         ['电网设备', '电网设备'],
         ['电池', '电池'],
         ['电机Ⅱ', '电机'],  #
@@ -151,20 +234,7 @@ def get_industry_final_fix_df():
         ['风电设备', '风电设备'],
         ['其他电源设备Ⅱ', '其他电源设备'],
 
-        # 房地产
-        ['房地产开发', '房地产'],
-        ['房地产服务', '房地产'],
-
-        # 计算机 联动板块
-        ['计算机设备', '计算机设备'],
-        ['IT服务Ⅱ', 'IT服务'],
-        ['软件开发', '软件开发'],
-
-        # 环保
-        ['环境治理', '环保'],  # merge, 环保
-        ['环保设备Ⅱ', '环保'],  # merge '环保'
-
-        # 电子
+        # 电子 19
         ['半导体', '半导体'],
         ['电子化学品Ⅱ', '电子化学品'],
         ['光学光电子', '光学光电子'],
@@ -172,133 +242,144 @@ def get_industry_final_fix_df():
         ['元件', '元件'],
         ['其他电子Ⅱ', '其他电子'],  #
 
-        # 金融 互联网金融 参股券商
-        ['证券Ⅱ', '证券'],
-        ['国有大型银行Ⅱ', '银行'],  # merge  to 银行
-        ['城商行Ⅱ', '银行'],  #
-        ['农商行Ⅱ', '银行'],  # merge   银行
-        ['股份制银行Ⅱ', '银行'],  # merge  to 银行
-        ['保险Ⅱ', '保险'],
-        ['多元金融', '多元金融'],
-
-        # 通信
-        ['通信服务', '通信服务'],
-        ['通信设备', '通信设备'],
-
-        # 酒 喝死你
-        ['白酒Ⅱ', '酒类'],  # merge '酒类'
-        ['非白酒', '酒类'],  # merge '酒类'
-
-        # 轻工制造
-        ['造纸', '造纸'],
-        ['包装印刷', '包装印刷'],  #
-        ['文娱用品', '文娱用品'],  #
-        ['家居用品', '家居用品'],
-
-        # 纺织服装
-        ['服装家纺', '纺织服装'],  # merge 纺织服装
-        ['纺织制造', '纺织服装'],  # merge 纺织服装
-        ['饰品', '饰品'],  # todo exclude
-
-        # 美容护理
-        ['化妆品', '美容护理'],  # merge  to 美容护理
-        ['医疗美容', '美容护理'],  # merge  美容护理
-        ['个护用品', '个护用品'],
-
-        # 食品饮料
-        ['饮料乳品', '饮料乳品'],  # merge 食品饮料
-        ['食品加工', '食品加工'],  # merge 食品饮料
-        ['调味发酵品Ⅱ', '调味发酵品'],  # merge  to  食品饮料
-        ['休闲食品', '休闲食品'],  # merge '食品饮料'
-
-        # 石油石化
+        # 石油石化 20
         ['炼化及贸易', '石油行业'],  # merge 石油行业
         ['油服工程', '采掘行业'],  # merge '采掘行业'
         ['油气开采Ⅱ', '石油行业'],  # merge  to 石油行业
 
-        #  钢铁
-        ['普钢', '钢铁'],  # merge 钢铁
-        ['特钢Ⅱ', '钢铁'],  # merge '钢铁'
-        ['冶钢原料', '钢铁'],  # merge to 钢铁
+        # 社会服务 21
+        ['专业服务', '社会专业服务'],
+        ['旅游及景区', '旅游及景区'],
+        ['酒店餐饮', '旅游酒店'],
+        ['教育', '教育'],
+        # ['体育Ⅱ', '体育'],
 
-        # 有色金属
-        ['能源金属', '能源金属'],  # merge
-        ['小金属', '小金属'],
-        ['贵金属', '贵金属'],  #
-        ['金属新材料', '金属新材料'],
-        # 铅锌  铝  铜
-        ['工业金属', '工业金属'],
+        # 纺织服装 22
+        ['服装家纺', '纺织服装'],  # merge 纺织服装
+        ['纺织制造', '纺织服装'],  # merge 纺织服装
+        ['饰品', '饰品'],
 
-        # 建筑装饰
-        ['基础建设', '工程建设'],
-        ['房屋建设Ⅱ', '工程建设'],  # merge 工程建设
-        ['工程咨询服务Ⅱ', '工程咨询服务'],
-        ['专业工程', '建筑工程'],
-        ['装修装饰Ⅱ', '装修装饰'],
-        ['工程机械', '工程机械'],
+        # 综合 23
+        ['综合Ⅱ', '综合'],
 
-        # 建筑材料
-        ['装修建材', '装修建材'],  #
-        ['建筑建材', '装修建材'],  #
-        ['玻璃玻纤', '玻璃玻纤'],
-        ['水泥', '水泥'],
+        # 美容护理 24
+        ['化妆品', '化妆美容'],  # merge  to 化妆美容
+        # ['医疗美容', '化妆美容'],  # merge  化妆美容
+        ['个护用品', '个护用品'],
 
-        # 旅游酒店
-        ['酒店餐饮', '旅游酒店'],  # merge  to 旅游酒店
+        # 计算机 25
+        ['计算机设备', '计算机设备'],
+        ['IT服务Ⅱ', 'IT服务'],
+        ['软件开发', '软件开发'],
 
-        ['旅游及景区', '旅游酒店'],  # merge 旅游酒店
+        # 轻工制造 26
+        ['造纸', '造纸'],
+        ['包装印刷', '包装印刷'],  #
+        ['文娱用品', '文娱用品'],  #
+        ['家居用品', '家居用品'],
 
-        # 煤炭
-        ['焦炭Ⅱ', '煤炭'],  # merge  to 煤炭
-        ['煤炭开采', '煤炭'],  # merge 煤炭
+        # 通信 27
+        ['通信服务', '通信服务'],
+        ['通信设备', '通信设备'],
 
-        ['教育', '教育'],
+        #  钢铁 28
+        ['普钢', '普钢'],  #
+        ['特钢Ⅱ', '特钢'],
+        ['冶钢原料', '冶钢原料'],
 
-        ['自动化设备', '自动化设备'],
-        ['轨交设备Ⅱ', '轨交设备'],
+        # 银行 29
+        ['国有大型银行Ⅱ', '银行'],  # merge  to 银行
+        ['城商行Ⅱ', '银行'],  #
+        ['农商行Ⅱ', '银行'],  # merge   银行
+        ['股份制银行Ⅱ', '银行'],  # merge  to 银行
 
-        # 机械设备  仪器仪表 农用机械 制冷空调设备  印刷包装机械 机床工具
-        # 楼宇设备 磨具磨料  纺织服装设备  能源及重型设备 金属制品
-        ['专用设备', '专用设备'],  # todo exclude
-        ['通用设备', '通用设备'],  # todo exclude
-        ['专业服务', '专业服务'],  # todo exclude 无法具体分类
+        # 非银金融  30
+        ['证券Ⅱ', '证券'],
+        ['保险Ⅱ', '保险'],
+        ['多元金融', '多元金融'],
 
-        ['体育Ⅱ', '综合'],  # merge  综合Ⅱ
-        ['综合Ⅱ', '综合']  # todo exclude
+        # 食品饮料 31
+        ['饮料乳品', '饮料乳品'],  # merge 食品饮料
+        ['食品加工', '食品加工'],  # merge 食品饮料
+        ['调味发酵品Ⅱ', '调味发酵品'],  # merge  to  食品饮料
+        ['休闲食品', '休闲食品'],  # merge '食品饮料'
+        ['白酒Ⅱ', '白酒'],
+        ['非白酒', '非白酒']
 
     ], columns=['second_sw_industry', 'industry'])
 
 
-# 第三行业作为筛选行业
+# 第三行业作为行业
 def fix_industry_use_sw_third(company_info_df):
     # 细分工业金属行业
     company_info = company_info_df.copy()
     company_info.loc[company_info.third_industry_code == '240303', 'industry'] = '铅锌'
     company_info.loc[company_info.third_industry_code == '240301', 'industry'] = '铝'
     company_info.loc[company_info.third_industry_code == '240302', 'industry'] = '铜'
+
+    company_info.loc[company_info.third_industry_code == '240303', 'second_sw_industry'] = '铅锌'
+    company_info.loc[company_info.third_industry_code == '240301', 'second_sw_industry'] = '铝'
+    company_info.loc[company_info.third_industry_code == '240302', 'second_sw_industry'] = '铜'
+
+    company_info.loc[company_info.third_industry_code == '240303', 'second_industry_code'] = '240303'
+    company_info.loc[company_info.third_industry_code == '240301', 'second_industry_code'] = '240301'
+    company_info.loc[company_info.third_industry_code == '240302', 'second_industry_code'] = '240302'
+
     # 细分专业设备
     company_info.loc[company_info.third_industry_code == '640203', 'industry'] = '能源及重型设备'
     company_info.loc[company_info.third_industry_code == '640204', 'industry'] = '楼宇设备'
     company_info.loc[company_info.third_industry_code == '640206', 'industry'] = '纺织服装设备'
     company_info.loc[company_info.third_industry_code == '640207', 'industry'] = '农用机械'
     company_info.loc[company_info.third_industry_code == '640208', 'industry'] = '印刷包装机械'
+
+    company_info.loc[company_info.third_industry_code == '640203', 'second_sw_industry'] = '能源及重型设备'
+    company_info.loc[company_info.third_industry_code == '640204', 'second_sw_industry'] = '楼宇设备'
+    company_info.loc[company_info.third_industry_code == '640206', 'second_sw_industry'] = '纺织服装设备'
+    company_info.loc[company_info.third_industry_code == '640207', 'second_sw_industry'] = '农用机械'
+    company_info.loc[company_info.third_industry_code == '640208', 'second_sw_industry'] = '印刷包装机械'
+
+    company_info.loc[company_info.third_industry_code == '640203', 'second_industry_code'] = '640203'
+    company_info.loc[company_info.third_industry_code == '640204', 'second_industry_code'] = '640204'
+    company_info.loc[company_info.third_industry_code == '640206', 'second_industry_code'] = '640206'
+    company_info.loc[company_info.third_industry_code == '640207', 'second_industry_code'] = '640207'
+    company_info.loc[company_info.third_industry_code == '640208', 'second_industry_code'] = '640208'
+
     # todo 细分
     company_info.loc[company_info.third_industry_code == '640209', 'industry'] = '专用设备'
-    company_info.loc[company_info.third_industry_code == '630402', 'industry'] = '专用设备'
+    company_info.loc[company_info.third_industry_code == '640209', 'second_sw_industry'] = '专用设备'
+    company_info.loc[company_info.third_industry_code == '640209', 'second_industry_code'] = '640208'
+
+    company_info.loc[company_info.third_industry_code == '260205', 'industry'] = '专用设备'
+    company_info.loc[company_info.third_industry_code == '260205', 'second_sw_industry'] = '专用设备'
+    company_info.loc[company_info.third_industry_code == '260205', 'second_industry_code'] = '260205'
+
     # 细分通用设备
     company_info.loc[company_info.third_industry_code == '640101', 'industry'] = '机床工具'
     company_info.loc[company_info.third_industry_code == '640103', 'industry'] = '磨具磨料'
     company_info.loc[company_info.third_industry_code == '640105', 'industry'] = '制冷空调设备'
     company_info.loc[company_info.third_industry_code == '640106', 'industry'] = '通用设备'
     company_info.loc[company_info.third_industry_code == '640107', 'industry'] = '仪器仪表'
-    company_info.loc[company_info.third_industry_code == '640301', 'industry'] = '仪器仪表'
-    # todo 细分
     company_info.loc[company_info.third_industry_code == '640108', 'industry'] = '金属制品'
+
+    company_info.loc[company_info.third_industry_code == '640101', 'second_sw_industry'] = '机床工具'
+    company_info.loc[company_info.third_industry_code == '640103', 'second_sw_industry'] = '磨具磨料'
+    company_info.loc[company_info.third_industry_code == '640105', 'second_sw_industry'] = '制冷空调设备'
+    company_info.loc[company_info.third_industry_code == '640106', 'second_sw_industry'] = '通用设备'
+    company_info.loc[company_info.third_industry_code == '640107', 'second_sw_industry'] = '仪器仪表'
+    company_info.loc[company_info.third_industry_code == '640108', 'second_sw_industry'] = '金属制品'
+
+    company_info.loc[company_info.third_industry_code == '640101', 'second_industry_code'] = '640101'
+    company_info.loc[company_info.third_industry_code == '640103', 'second_industry_code'] = '640103'
+    company_info.loc[company_info.third_industry_code == '640105', 'second_industry_code'] = '640105'
+    company_info.loc[company_info.third_industry_code == '640106', 'second_industry_code'] = '640106'
+    company_info.loc[company_info.third_industry_code == '640107', 'second_industry_code'] = '640107'
+    company_info.loc[company_info.third_industry_code == '640108', 'second_industry_code'] = '640108'
+
     return company_info
 
 
-def find_sw_third_industry(industry_id):
-    sw_third_industry = mongodb_util.find_query_data('sw_industry', query={"_id": industry_id})
+def find_sw_third_industry(new_third_industry_code):
+    sw_third_industry = mongodb_util.find_query_data('sw_industry', query={"_id": new_third_industry_code})
     first_sw_industry_name = list(sw_third_industry['first_sw_industry'])[0]
     second_sw_industry_name = list(sw_third_industry['second_sw_industry'])[0]
 
@@ -317,8 +398,9 @@ def find_sw_third_industry(industry_id):
     return sw_third_industry
 
 
-def fix_industry_data(industry_id, company_info):
-    sw_industry = find_sw_third_industry(industry_id)
+# 修改行业信息
+def fix_industry_data(new_third_industry_code, company_info):
+    sw_industry = find_sw_third_industry(new_third_industry_code)
     company_info['first_sw_industry'] = sw_industry.first_sw_industry
     company_info['first_industry_code'] = sw_industry.industry_code
     company_info['second_sw_industry'] = sw_industry.second_sw_industry
@@ -328,24 +410,17 @@ def fix_industry_data(industry_id, company_info):
     return company_info
 
 
+# 手动修改股票行业代码
 def fix_symbol_industry(company_info, symbol):
     fix_symbol_df = get_fix_symbol_industry()
     fix_symbol_df_one = fix_symbol_df.loc[fix_symbol_df['symbol'] == symbol]
     if data_frame_util.is_not_empty(fix_symbol_df_one):
-        new_industry_code = list(fix_symbol_df_one['new_industry_code'])[0]
-        company_info = fix_industry_data(new_industry_code, company_info)
+        new_third_industry_code = list(fix_symbol_df_one['new_industry_code'])[0]
+        company_info = fix_industry_data(new_third_industry_code, company_info)
 
     return company_info
 
 
-def fix_one_symbol():
-    symbol = '300483'
-    company_info = mongodb_util.find_query_data('company_info', query={'_id': symbol})
-    company_info = fix_symbol_industry(company_info, symbol)
-    company_info['industry'] = company_info['second_sw_industry']
-    mongodb_util.save_mongo(company_info, 'company_info')
-
-
 def filed_sort(company_info):
     return company_info[[
         "_id",
@@ -410,6 +485,5 @@ def filed_sort(company_info):
 
 
 if __name__ == '__main__':
-    fix_one_symbol()
-    industry_df_test = get_industry_final_fix_df()
+    industry_df_test = get_fix_industry_name_df()
     print(industry_df_test)

{mns_scheduler-1.2.3.5 → mns_scheduler-1.2.3.7}/mns_scheduler/concept/ths/common/ths_concept_sync_common_api.py

@@ -196,7 +196,7 @@ def update_company_info(new_concept_symbol_df):
     if new_concept_symbol_df.shape[0] > 0:
         symbol_list = list(new_concept_symbol_df['symbol'])
         company_info_sync_api.sync_company_base_info(symbol_list)
-        company_info_clean_api.fix_company_industry(None)
+        company_info_clean_api.clean_company_info(None)
         # 公司缓存信息清除
         company_common_service_api.company_info_industry_cache_clear()