def __init__(self, code, namecode, name, chrome_driver):
self.quarter_index = get_last_quarter_str()
self.update_date = None # 数据更新时间，默认取资产配置更新时间
self.fund_code = code # 基金代码，需要初始化赋值
self.fund_name = name # 基金名称，需要初始化赋值
self.morning_star_code = namecode # 基金编码，晨星网特有，需要建立索引表
self._morning_cookies = chrome_driver.get_cookies() or None
self._chrome_driver = chrome_driver or None
self._is_trigger_catch = False
self._catch_detail = None
# 基本信息
self.fund_cat = None # 基金分类
self.found_date = None # 成立时间
self.company = None # 基金公司
# 季度变动信息
self.total_asset = None # 总资产
self.investname_style = None # 投资风格
self.manager = dict() # 基金经理,name,id,管理时间
self.three_month_retracement = 0.0 # 最差六个月回报
self.june_month_retracement = 0.0 # 最差六个月回报
self.bond_position = dict({'total': '0.00'}) # 债券总仓位、前五大持仓
self.stock_position = dict({'total': '0.00'}) # 股票总仓位、前十大持仓
self.risk_assessment = dict() # 三年风险评估 -- 标准差 风险系数 夏普比
self.risk_statistics = dict() # 阿尔法 贝塔 R平方值
self.risk_rating = dict() # 风险评价 -- 二年、三年、五年、十年
self.morning_star_rating = dict() # 晨星评级--三年，五年，十年
# 十大持仓信息
self.ten_top_stock_list = [] # 股票十大持仓股信息
def select_condition_stocks_rank(each_statistic=None, *, quarter_index=None):
if each_statistic == None:
each_statistic = FundStatistic()
if quarter_index == None:
quarter_index = get_last_quarter_str(1)
columns = ['代码', '名称', '持有数量（只）', '持有市值（亿元）']
company = '广发基金管理有限公司'
company_condition = {'value': company, 'operator': '='}
output_file = './outcome/数据整理/stocks/condition/' + company + '.xlsx'
condition_dict = {
# 'morning_star_rating_5': morning_star_rating_5_condition,
# 'morning_star_rating_3': morning_star_rating_3_condition,
'company': company_condition
}
fund_pool = get_fund_code_pool(condition_dict)
stock_top_list = each_statistic.all_stock_fund_count(
quarter_index=quarter_index, fund_code_pool=fund_pool, filter_count=0)
stock_rank_list = []
for stock_name_code in stock_top_list:
stock_code = stock_name_code[0].split('-', 1)[0]
stock_name = stock_name_code[0].split('-', 1)[1]
stock_count = stock_name_code[1]['count']
stock_holder_asset = stock_name_code[1]['holder_asset']
stock_rank_item = [
stock_code, stock_name, stock_count, stock_holder_asset
]
stock_rank_list.append(stock_rank_item)
df_stock_top_list = pd.DataFrame(stock_rank_list, columns=columns)
print(df_stock_top_list)
update_xlsx_file(output_file, df_stock_top_list, quarter_index)
def output_high_score_funds(each_query=None, quarter_index=None):
"""
输出高分基金
"""
if each_query == None:
each_query = FundQuery()
if quarter_index == None:
quarter_index = get_last_quarter_str()
print("quarter_index", quarter_index)
high_score_funds = each_query.select_high_score_funds(
quarter_index=quarter_index)
columns_bk = [
'代码', '名称', '季度', '总资产', '现任基金经理管理起始时间', '投资风格', '三月最大回撤', '六月最大回撤',
'夏普比率', '阿尔法系数', '贝塔系数', 'R平方', '标准差', '风险系数', '两年风险评级', '三年风险评级',
'五年风险评级', '五年晨星评级', '三年晨星评级', '股票仓位', '十大持股仓位'
]
columns = [
'代码', '名称', '投资风格', '基金经理', '现任经理管理起始时间', '成立时间', '三年晨星评级', '五年晨星评级',
'夏普比率', '股票仓位', '十大持股仓位', '两年风险评级', '三年风险评级', '五年风险评级', '阿尔法系数',
'贝塔系数', '标准差', '总资产', '数据更新时间'
]
df_high_score_funds = pd.DataFrame(high_score_funds, columns=columns)
# pprint(df_high_score_funds)
path = './outcome/数据整理/funds/high-score-funds.xlsx'
update_xlsx_file(path, df_high_score_funds, quarter_index)
def t100_stocks_rank(each_statistic=None, *, quarter_index=None):
# T100权重股排名
if each_statistic == None:
each_statistic = FundStatistic()
if quarter_index == None:
quarter_index = get_last_quarter_str(1)
last_quarter_index = get_last_quarter_str(2)
output_file = './outcome/数据整理/strategy/top100_rank.xlsx'
sheet_name = 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'
]
stock_top_list = each_statistic.all_stock_fund_count(
quarter_index=quarter_index, filter_count=80)
stock_top_list = stock_top_list[:100] # 获取top100权重股
filter_list = stocks_compare(stock_top_list)
df_filter_list = pd.DataFrame(filter_list, columns=columns)
update_xlsx_file(output_file, df_filter_list, sheet_name)
def all_stock_holder_detail(each_statistic=None,
*,
quarter_index=None,
threshold=0):
""" 所有股票的基金持仓细节
Args:
each_statistic (class): 统计类
quarter_index (str, optional): 季度字符串. Defaults to None.
threshold (int, optional): 输出门槛. Defaults to 0.
"""
if each_statistic == None:
each_statistic = FundStatistic()
if quarter_index == None:
quarter_index = get_last_quarter_str()
stock_list = each_statistic.all_stock_fund_count_and_details(
quarter_index=quarter_index, filter_count=threshold)
for i in range(0, len(stock_list)):
stock = stock_list[i]
stock_name_code = stock[0]
stock_code = stock_name_code.split('-', 1)[0]
path = '其他'
if bool(re.search("^\d{5}$", stock_code)):
path = '港股'
elif bool(re.search("^\d{6}$", stock_code)):
if bool(re.search("^00(0|1|2|3)\d{3}$", stock_code)):
path = 'A股/深证主板'
elif bool(re.search("^300\d{3}$", stock_code)):
path = 'A股/创业板'
elif bool(re.search("^60(0|1|2|3|5)\d{3}$", stock_code)):
path = 'A股/上证主板'
elif bool(re.search("^68(8|9)\d{3}$", stock_code)):
path = 'A股/科创板'
else:
print('stock_name_code', stock_name_code)
hold_fund_list = sorted(stock[1]['fund_list'],
key=lambda x: x['持有市值(亿元)'],
reverse=True)
df_list = pd.DataFrame(hold_fund_list)
stock_name_code = stock_name_code.replace('-*', '-').replace('/', '-')
path = './outcome/数据整理/stocks/' + path + '/' + stock_name_code + '.xlsx'
path = path.replace('\/', '-')
update_xlsx_file(path, df_list, quarter_index)
def __init__(self):
self.quarter_index = get_last_quarter_str()
self.quarter_date = get_quarter_date(self.quarter_index)
connect_instance = connect()
self.connect_instance = connect_instance
self.cursor = connect_instance.cursor()
def __init__(self, code=None): self.fund_code = code # 动态计算季度信息 self.quarter_index = get_last_quarter_str()
def stocks_compare(stock_list,
*,
market=None,
quarter_index=None,
is_A_stock=None):
"""与某个季度数据进行比较
"""
if quarter_index == None:
quarter_index = get_last_quarter_str(2)
print("比较-->quarter_index", quarter_index)
last_quarter_input_file = './outcome/数据整理/strategy/all_stock_rank/' + \
quarter_index + '.xlsx'
data_last_quarter = pd.read_excel(io=last_quarter_input_file,
engine="openpyxl",
dtype={"代码": np.str},
sheet_name=None)
if market:
df_data_target_market = data_last_quarter.get(market)
df_data_target_market[quarter_index +
'持有数量（只）'] = df_data_target_market[
quarter_index + '持有数量（只）'].astype(int)
filter_list = []
for stock in stock_list:
stock_code = stock[0].split('-', 1)[0]
if not stock_code:
continue
stock_name = stock[0].split('-', 1)[1]
stock_holder_detail = stock[1]
holder_count = stock_holder_detail.get('count')
holder_asset = stock_holder_detail.get('holder_asset')
if not market:
target_market = get_stock_market(stock_code)
df_data_target_market = data_last_quarter.get(target_market)
target_loc = df_data_target_market[df_data_target_market['代码'] ==
stock_code]
last_holder_count = 0
last_holder_asset = 0
if len(target_loc) == 1:
col_target = quarter_index + '持有数量（只）'
last_holder_count = target_loc[col_target].iloc[0]
col_target = quarter_index + '持有市值（亿元）'
last_holder_asset = round(
decimal.Decimal(target_loc[col_target].iloc[0]), 4)
diff_holder_count = holder_count - last_holder_count
diff_holder_asset = holder_asset - last_holder_asset
diff_holder_count_percent = '{:.2%}'.format(
diff_holder_count /
last_holder_count) if last_holder_count != 0 else "+∞"
diff_holder_asset_percent = '{:.2%}'.format(
diff_holder_asset /
last_holder_asset) if last_holder_asset != 0 else "+∞"
# flag = '📈' if diff_holder_count > 0 else '📉'
# if diff_holder_count == 0:
# flag = '⏸'
flag_count = 'up' if diff_holder_count > 0 else 'down'
flag_asset = 'up' if diff_holder_asset > 0 else 'down'
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)
# print(item_tuple)
return filter_list
def get_special_fund_code_holder_stock_detail(each_statistic=None,
quarter_index=None):
"""获取某些基金的十大持仓股票信息
"""
if each_statistic == None:
each_statistic = FundStatistic()
if quarter_index == None:
quarter_index = get_last_quarter_str(2)
print("quarter_index", quarter_index)
holder_history_list = [
{
'001811': {
'name': '中欧明睿新常态混合A',
'radio': 0.2
},
'001705': {
'name': '泓德战略转型股票',
'radio': 0.2
},
'163415': {
'name': '兴全商业模式优选混合',
'radio': 0.2
},
'001043': {
'name': '工银美丽城镇主题股票A',
'radio': 0.1
},
'000547': {
'name': '建信健康民生混合',
'radio': 0.1
},
'450001': {
'name': '国富中国收益混合',
'radio': 0.2
},
},
# """
# 根据二季度高分基金池数据，以及近期组合表现，剔除一些不在高性价比基金池中基金，以及结合近期市场风格进行调仓以及调整成分基金比例。
# 保留：中欧明睿新常态混合A(001811),建信健康民生混合(000547),
# 调出：泓德战略转型股票(001705),兴全商业模式优选混合(163415),工银美丽城镇主题股票A(001043),国富中国收益混合(450001)
# 调入：工银新金融股票（001054），工银瑞信战略转型主题股票A（000991），汇丰晋信动态策略混合A（540003）兴全绿色投资混合（163409）
# 结合以上基金的近期表现，以及风控，以及维持整个组合均衡配置（目前组合偏科技板块）做出如上调整，欢迎大家跟调。
# """
{
'001811': {
'name': '中欧明睿新常态混合A',
'radio': 0.2
},
'001054': {
'name': '工银新金融股票',
'radio': 0.2
},
'000991': {
'name': '工银瑞信战略转型主题股票A',
'radio': 0.1
},
'540003': {
'name': '汇丰晋信动态策略混合A',
'radio': 0.2
},
'000547': {
'name': '建信健康民生混合',
'radio': 0.1
},
'163409': {
'name': '兴全绿色投资混合(LOF)',
'radio': 0.2
},
},
[
{
'code': '519002',
'name': '华安安信消费混合',
'radio': 0.2
},
{
'code': '001718',
'name': '工银瑞信物流产业股票',
'radio': 0.2
},
{
'code': '000991',
'name': '工银瑞信战略转型主题股票A',
'radio': 0.1
},
{
'code': '540003',
'name': '汇丰晋信动态策略混合A',
'radio': 0.1
},
{
'code': '450001',
'name': '国富中国收益混合',
'radio': 0.1
},
{
'code': '000547',
'name': '建信健康民生混合',
'radio': 0.1
},
{
'code': '163409',
'name': '兴全绿色投资混合(LOF)',
'radio': 0.2
},
]
]
# 基金组合信息
fund_portfolio = holder_history_list[2]
fund_code_pool = [] #list(fund_portfolio.keys())
for item in fund_portfolio:
fund_code_pool.append(item.get('code'))
print("fund_code_pool", fund_code_pool)
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-加工.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)
# print("df_a_list", df_a_list)
update_xlsx_file(path, df_a_list, sheet_name='十大持仓明细--' + '2022-01')
def all_stocks_rank(each_statistic=None):
if each_statistic == None:
each_statistic = FundStatistic()
"""所有股票排名
"""
quarter_index = get_last_quarter_str(1)
print("该quarter_index为", quarter_index)
last_quarter_index = get_last_quarter_str(2)
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/all_stock_rank/' + quarter_index + '.xlsx'
stock_top_list = each_statistic.all_stock_fund_count(
quarter_index=quarter_index, filter_count=0)
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)):
# '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:
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_market = 'A股'
hk_market = '港股'
other_market = '其他'
a_stock_compare_list = stocks_compare(a_stock_list,
market=a_market,
quarter_index=last_quarter_index,
is_A_stock=True)
hk_stock_compare_list = stocks_compare(
hk_stock_list,
market=hk_market,
quarter_index=last_quarter_index,
)
other_stock_compare_list = stocks_compare(
other_stock_list,
market=other_market,
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)
writer = pd.ExcelWriter(output_file, engine='xlsxwriter')
df_a_list.to_excel(writer, sheet_name=a_market)
df_hk_list.to_excel(writer, sheet_name=hk_market)
df_other_list.to_excel(writer, sheet_name=other_market)
writer.save()