feat: 增加输出行业数据

src/db/connect.py

@@ -14,6 +14,22 @@ def connect():
         host=env_db_host, user=env_db_user, password=env_db_password, db=env_db_name, charset='utf8')
     return connect
 
+def connect_dict():
+    load_dotenv()
+    env_db_host = os.getenv('db_host')
+    env_db_name = os.getenv('db_name')
+    env_db_user = os.getenv('db_user')
+    env_db_password = os.getenv('db_password')
+    connect = pymysql.connect(
+        host=env_db_host, user=env_db_user, password=env_db_password, db=env_db_name,
+        charset='utf8')
+    connect_dict = {
+        'connect': connect,
+        'cursor': connect.cursor(),
+        'dict_cursor': connect.cursor(pymysql.cursors.DictCursor)
+    }
+    return connect_dict
+
 
 if __name__ == '__main__':
     connect()

src/fund_info/statistic.py

@@ -9,6 +9,7 @@ Copyright (c) 2021 Camel Lu
 '''
 import time
 import datetime
+import re
 import os
 import sys
 from pprint import pprint
@@ -16,6 +17,7 @@ sys.path.append('../')
 sys.path.append(os.getcwd() + '/src')
 from utils.index import get_quarter_index, fisrt_match_condition_from_list
 from sql_model.fund_query import FundQuery
+from sql_model.stock_query import StockQuery
 
 
 class FundStatistic:
@@ -29,6 +31,7 @@ class FundStatistic:
         quarter_index = year + '-Q' + str(index)
         self.quarter_index = quarter_index
         self.each_query = FundQuery()
+        self.stock_query = StockQuery()
 
     def all_stock_fund_count(self, *, quarter_index=None, fund_code_pool=None, filter_count=100):
         """查询某一个季度基金的十大持仓，并对持仓股票进行汇总统计，并根据filter_count进行过滤
@@ -141,7 +144,9 @@ class FundStatistic:
                     }
         #for key, value in code_dict.items(): 
         #    print('key, value', key, value)
-        return sorted(code_dict.items(), key=lambda x: x[1]['count'], reverse=True)
+        print('code_dict.items()', code_dict.items())
+        return list(code_dict.items())
+        #return sorted(code_dict.items(), key=lambda x: x[1]['count'], reverse=True)
     # 分组查询特定股票的每个季度基金持有总数
     def item_stock_fund_count(self, stock_code, fund_code_pool=None):
         return self.each_query.select_special_stock_fund_count(stock_code, fund_code_pool)
@@ -171,3 +176,41 @@ class FundStatistic:
             morning_star_rating_3=morning_star_rating_3,
             **args
         )
+
+    def select_stock_pool_industry(self, fund_code_pool):
+        return self.stock_query.query_stock_industry(fund_code_pool)
+
+    def select_special_fund_info(self, code, quarter_index=None):
+        return self.each_query.select_special_fund_info(code, quarter_index)
+
+    def summary_special_funds_stock_detail(self, fund_code_pool, quarter_index=None):
+        holder_stock_industry_list = []
+        for fund_code in fund_code_pool:
+            fund_info = self.select_special_fund_info(fund_code, quarter_index )
+            fund_code = fund_info[0]
+            fund_name = fund_info[1]
+            fund_cat = fund_info[2]
+            fund_manager = fund_info[3]
+            fund_total_asset = fund_info[4]
+            fund_total_portion = fund_info[5]
+            fund_ten_portion = fund_info[6]
+            for index in range(7, len(fund_info), 3):
+                stock_code = fund_info[index]
+                stock_name = fund_info[index+1]
+                stock_portion = fund_info[index+2]
+                stock_index = int((index - 4) / 3)
+                stock_list_industry = [fund_code, fund_name,fund_cat,fund_manager, fund_total_asset, fund_total_portion, fund_ten_portion, 
+                                    stock_code, stock_name, stock_portion, stock_index]
+                #holder_stock_industry_list.append(stock_list_industry]
+                if bool(re.search("^\d{6}$", stock_code)):
+                    stock_list_industry_list = self.select_stock_pool_industry([stock_code])
+                    stock_list_industry_dict = stock_list_industry_list[0]
+                    industry_name_first = stock_list_industry_dict.get('industry_name_first')
+                    industry_name_second = stock_list_industry_dict.get('industry_name_second')
+                    industry_name_third = stock_list_industry_dict.get('industry_name_third')
+
+                    holder_stock_industry_list.append([*stock_list_industry, industry_name_third,industry_name_second, industry_name_first])
+        return holder_stock_industry_list
+
+    def query_all_stock_industry_info(self):
+        return self.stock_query.query_all_stock()

src/fund_statistic.py

@@ -14,7 +14,7 @@ import re
 from pprint import pprint
 import pandas as pd
 from fund_info.statistic import FundStatistic
-from utils.index import get_last_quarter_str
+from utils.index import get_last_quarter_str, find_from_list_of_dict
 from openpyxl import load_workbook
 import os
 
@@ -44,9 +44,10 @@ def get_fund_code_pool():
     )
     return fund_code_pool
 
-def stocks_compare(stock_list, fund_code_pool=None):
+def stocks_compare(stock_list, *, quarter_index=None, fund_code_pool=None, is_A_stock=None):
     each_statistic = FundStatistic()
-    last_quarter_index = get_last_quarter_str(2)
+    if quarter_index == None:
+        quarter_index = get_last_quarter_str(2)
 
     filter_list = []
     for stock in stock_list:
@@ -60,7 +61,7 @@ def stocks_compare(stock_list, fund_code_pool=None):
 
         last_quarter_holder_detail_dict = each_statistic.select_special_stock_special_quarter_info(
             stock_code,
-            last_quarter_index,
+            quarter_index,
             fund_code_pool
         )
         
@@ -85,8 +86,13 @@ def stocks_compare(stock_list, fund_code_pool=None):
         if diff_holder_asset == 0:
             flag = '='
             
-        item_tuple = (stock_code, stock_name, holder_count, last_holder_count,
-                      diff_holder_count, diff_holder_count_percent, flag_count, holder_asset, last_holder_asset, diff_holder_asset, diff_holder_asset_percent, flag_asset)
+        item_tuple = [stock_code, stock_name, holder_count, last_holder_count,
+                      diff_holder_count, diff_holder_count_percent, flag_count, holder_asset, last_holder_asset, diff_holder_asset, diff_holder_asset_percent, flag_asset]
+        if is_A_stock:
+            industry_name_third = stock_holder_detail.get('industry_name_third')
+            industry_name_second = stock_holder_detail.get('industry_name_second')
+            industry_name_first = stock_holder_detail.get('industry_name_first')
+            item_tuple = [*item_tuple, industry_name_third, industry_name_second,industry_name_first ]
 
         # if diff_percent == "+∞" or not float(diff_percent.rstrip('%')) < -20:
         filter_list.append(item_tuple)
@@ -114,52 +120,50 @@ def t100_stocks_rank(quarter_index=None, *, each_statistic):
 
 # 所有股票排名
 def all_stocks_rank(each_statistic):
-    quarter_index = get_last_quarter_str()
+    quarter_index = get_last_quarter_str(2)
     print("quarter_index", quarter_index)
-    last_quarter_index = get_last_quarter_str(2)
+    last_quarter_index = get_last_quarter_str(3)
     sheet_name = last_quarter_index + '基金重仓股T100'
     columns=['代码',
         '名称', quarter_index + '持有数量（只）', last_quarter_index +'持有数量（只）', '持有数量环比', '持有数量环比百分比', '持有数量升或降',  quarter_index + '持有市值（亿元）', last_quarter_index + '持有市值（亿元）', '持有市值环比', '持有市值环比百分比', '持有市值升或降']
-    output_file = './outcome/数据整理/strategy/'+ quarter_index +'-all_stock_rank.xlsx'
+    output_file = './outcome/数据整理/strategy/all_stock_rank/'+ quarter_index +'.xlsx'
 
 
     stock_top_list = each_statistic.all_stock_fund_count(
         quarter_index=quarter_index,
         filter_count=0)
     #print("stock_top_list", stock_top_list)
+    all_a_stocks_industry_info_list = each_statistic.query_all_stock_industry_info()
     a_stock_list = []
     hk_stock_list = []
     other_stock_list = []
     for stock_name_code in stock_top_list:
         stock_code = stock_name_code[0].split('-', 1)[0]
+
         #path = 'other'
         if bool(re.search("^\d{5}$", stock_code)):
             #path = '港股'
             hk_stock_list.append(stock_name_code)
         elif bool(re.search("^\d{6}$", stock_code)):
-            if bool(re.search("^00(0|1|2|3)\d{3}$", stock_code)):
-                #path = 'A股/深证主板'
-                a_stock_list.append(stock_name_code)
-            elif bool(re.search("^300\d{3}$", stock_code)):
-                #path = 'A股/创业板'
-                a_stock_list.append(stock_name_code)
-            elif bool(re.search("^60(0|1|2|3|5)\d{3}$", stock_code)):
-                #path = 'A股/上证主板'
-                a_stock_list.append(stock_name_code)
-            elif bool(re.search("^68(8|9)\d{3}$", stock_code)):
-                #path = 'A股/科创板'
+            #'A股/深证主板'、'A股/创业板'、'A股/上证主板'、'A股/科创板'
+            a_condition = bool(re.search("^(00(0|1|2|3)\d{3})|(30(0|1)\d{3})|(60(0|1|2|3|5)\d{3})|68(8|9)\d{3}$", stock_code))
+            target_item = find_from_list_of_dict(all_a_stocks_industry_info_list, 'stock_code', stock_code)
+            if a_condition and target_item:
+                print('stock_code',stock_code)
+                stock_name_code[1]['industry_name_first'] = target_item.get('industry_name_first')
+                stock_name_code[1]['industry_name_second'] = target_item.get('industry_name_second')
+                stock_name_code[1]['industry_name_third'] = target_item.get('industry_name_third')
                 a_stock_list.append(stock_name_code)
             else:
                 other_stock_list.append(stock_name_code)
         else:
             other_stock_list.append(stock_name_code)
 
-    a_stock_compare_list = stocks_compare(a_stock_list)
-    hk_stock_compare_list = stocks_compare(hk_stock_list)
-    other_stock_compare_list = stocks_compare(other_stock_list)
-
-    df_a_list = pd.DataFrame(a_stock_compare_list, columns=columns)
-    #print("df_a_list", df_a_list)
+    a_stock_compare_list = stocks_compare(a_stock_list, quarter_index=last_quarter_index, is_A_stock=True)
+    hk_stock_compare_list = stocks_compare(hk_stock_list,quarter_index=last_quarter_index,)
+    other_stock_compare_list = stocks_compare(other_stock_list,quarter_index=last_quarter_index,)
+    a_columns = [*columns, '三级行业', '二级行业', '一级行业']
+    df_a_list = pd.DataFrame(a_stock_compare_list, columns=a_columns)
     df_hk_list = pd.DataFrame(hk_stock_compare_list, columns=columns)
     df_other_list = pd.DataFrame(other_stock_compare_list, columns=columns)
 
@@ -223,7 +227,44 @@ def all_stock_holder_detail(quarter_index, each_statistic, threshold=0):
         else:
             df_list.to_excel(
                 path, sheet_name=quarter_index)
+# 获取某些基金的十大持仓股票信息
+def get_special_fund_code_holder_stock_detail(quarter_index, each_statistic):
+    #基金组合信息
+    fund_portfolio ={
+        '001811': {
+            'name': '中欧明睿新常态混合A',
+            'position' : 0.2
+        },
+        '001705': {
+            'name': '泓德战略转型股票',
+            'position' : 0.2
+        },
+        '163415': {
+            'name': '兴全商业模式优选混合',
+            'position' : 0.2
+        },
+        '001043': {
+            'name': '工银美丽城镇主题股票A',
+            'position' : 0.2
+        },
+        '000547': {
+            'name': '建信健康民生混合',
+            'position' : 0.2
+        },
+         '450001': {
+            'name': '国富中国收益混合',
+            'position' : 0.2
+        },
+    }
+    fund_code_pool = list(fund_portfolio.keys())
+    holder_stock_industry_list = each_statistic.summary_special_funds_stock_detail(fund_code_pool, quarter_index)
+    path = './outcome/数据整理/funds/' + '/' + '高分权益基金组合十大持仓明细' + '.xlsx'
+    columns=['基金代码','基金名称', '基金类型', '基金经理', '基金总资产（亿元）', '基金股票总仓位', '十大股票仓位', '股票代码', '股票名称', '所占仓位', '所处仓位排名',  '三级行业', '二级行业', '一级行业']
+    df_a_list = pd.DataFrame(holder_stock_industry_list, columns=columns)
 
+    writer = pd.ExcelWriter(path, engine='xlsxwriter')
+    df_a_list.to_excel(writer, sheet_name='十大持仓明细--' + quarter_index)
+    writer.save()
 if __name__ == '__main__':
     each_statistic = FundStatistic()
     quarter_index = "2021-Q1"
@@ -231,8 +272,11 @@ if __name__ == '__main__':
     # 所有股票的基金持仓细节
     #all_stock_holder_detail(quarter_index, each_statistic)
 
-    # 获取所有股票排名,分类输出
+    # 获取所有股票排名,按股票市场分类输出
     all_stocks_rank(each_statistic)
 
     # 获取Top100股票排名
     #t100_stocks_rank(each_statistic=each_statistic)
+    
+    # 获取某些基金的十大持仓股票信息
+    #get_special_fund_code_holder_stock_detail(quarter_index, each_statistic)

src/sql_model/fund_query.py

@@ -315,3 +315,23 @@ class FundQuery:
         self.cursor.execute(sql, [quarter_index])    # 执行sql语句
         results = self.cursor.fetchall()    # 获取查询的所有记录
         return results
+
+    # 联表查某一个基金信息
+    def select_special_fund_info(self, code, quarter_index=None):
+        if quarter_index == None:
+            quarter_index = self.quarter_index
+        stock_sql_join = ''
+        for index in range(10):
+            stock_sql_join = stock_sql_join + \
+                "d.top_stock_%s_code, d.top_stock_%s_name, d.top_stock_%s_portion" % (
+                    str(index), str(index), str(index)) + ","
+        stock_sql_join = stock_sql_join[0:-1]
+        
+        sql = "SELECT a.fund_code, a.fund_name, a.fund_cat, c.name, b.total_asset, b.stock_position_total, b.stock_position_ten, " + stock_sql_join + \
+        " FROM fund_morning_base AS a LEFT JOIN fund_morning_quarter AS b ON a.fund_code = b.fund_code \
+        LEFT JOIN fund_morning_manager as c ON c.manager_id = b.manager_id \
+        LEFT JOIN fund_morning_stock_info as d ON b.fund_code = d.fund_code AND b.quarter_index = d.quarter_index \
+        WHERE a.fund_code = %s AND b.quarter_index = %s ;"
+        self.cursor.execute(sql, [code, quarter_index])    # 执行sql语句
+        results = self.cursor.fetchone()    # 获取查询的所有记录
+        return results

src/sql_model/stock_query.py

@@ -0,0 +1,35 @@
+'''
+Desc: 股票查询
+File: /stock_query.py
+Project: sql_model
+File Created: Wednesday, 30th June 2021 3:29:07 pm
+Author: luxuemin2108@gmail.com
+-----
+Copyright (c) 2021 Camel Lu
+'''
+
+from db.connect import connect_dict
+
+class StockQuery:
+    def __init__(self):
+        connect_instance = connect_dict()
+        self.connect = connect_instance.get('connect')
+        self.cursor = connect_instance.get('cursor')
+        self.dict_cursor = connect_instance.get('dict_cursor')
+
+    def query_all_stock(self):
+        query_stock_sql = "SELECT stock_code, industry_name_first, industry_name_second, industry_name_third FROM stock_industry"
+        self.dict_cursor.execute(query_stock_sql)
+        results = self.dict_cursor.fetchall()
+        return results
+    # 查询股票对应行业
+    def query_stock_industry(self, stock_code_pool):
+        if isinstance(stock_code_pool, list):
+            if len(stock_code_pool) == 0:
+                return ()
+            temp = "%s," * len(stock_code_pool)
+            stock_sql_join = temp[0:-1]
+        sql = "SELECT stock_code, stock_name, industry_name_first, industry_name_second, industry_name_third FROM stock_industry WHERE stock_code IN ( " + stock_sql_join + " )"
+        self.dict_cursor.execute(sql, stock_code_pool)
+        results = self.dict_cursor.fetchall()
+        return results

src/utils/index.py

@@ -63,7 +63,7 @@ def get_quarter_index(input_date):
 
 
 def get_last_quarter_str(last_index=1):
-    last_quarter_time = time.localtime(time.time() - last_index * 3 * 30 * 24 * 3600)
+    last_quarter_time = time.localtime(time.time() - last_index * 3 * 30 * 24 * 3600 - 24 * 3600)
     year = time.strftime("%Y", last_quarter_time)
     date = time.strftime("%m-%d", last_quarter_time)
     index = get_quarter_index(date)
@@ -82,3 +82,22 @@ def fisrt_match_condition_from_list(list, code):
     is_exist = code == stock_code
     if is_exist:
       return item
+
+
+def dict_list_to_list_list(dict_list, key_sort_list):
+    tuple_list =[]
+    for item in dict_list:
+        temp_list = []
+        for key in key_sort_list:
+            temp_list.append(item.get(key))
+        tuple_list.append(temp_list)
+    return tuple_list
+
+
+def find_from_list_of_dict(dict_list, match_key, value):
+    res = None
+    for sub in dict_list:
+        if sub[match_key] == value:
+            res = sub
+            break
+    return res