修改self.portfolio

app/service/portfolio_diagnose.py

+# -*- coding: UTF-8 -*-
+"""
+@author: Zongxi.Li
+@file:portfolio_diagnose.py
+@time:2020/12/07
+"""
 from app.utils.fund_rank import *
 from app.utils.risk_parity import *
 from app.pypfopt import risk_models
@@ -52,23 +58,6 @@ def replace_fund(manager, substrategy, fund_rank):
     return df['fund_id'].values[0]
 
 
-def get_tamp_fund():
-    """获取探普产品池净值表
-
-    Returns:
-
-    """
-    with TAMP_SQL(tamp_fund_engine) as tamp_fund:
-        tamp_fund_session = tamp_fund.session
-        sql = "SELECT id FROM tamp_fund_info WHERE id LIKE 'HF%'"
-        cur = tamp_fund_session.execute(sql)
-        data = cur.fetchall()
-        # df = pd.read_sql(sql, con)
-        df = pd.DataFrame(list(data), columns=['fund_id'])
-        # df.rename({'id': 'fund_id'}, axis=1, inplace=True)
-    return df
-
-
 def search_rank(fund_rank, fund, metric):
     """查找基金在基金排名表中的指标
 
@@ -157,13 +146,17 @@ def choose_bad_evaluation(evaluation):
 
 
 def get_fund_rank():
-    with TAMP_SQL(tamp_fund_engine) as tamp_product:
-        tamp_product_session = tamp_product.session
+    """获取基金指标排名
+
+    :return: 基金指标排名表
+    """
+    with TAMP_SQL(tamp_fund_engine) as tamp_fund:
+        tamp_fund_session = tamp_fund.session
         sql = "SELECT * FROM fund_rank"
 
         # df = pd.read_sql(sql, con)
         # df = pd.read_csv('fund_rank.csv', encoding='gbk')
-        cur = tamp_product_session.execute(sql)
+        cur = tamp_fund_session.execute(sql)
         data = cur.fetchall()
         df = pd.DataFrame(list(data), columns=['index', 'fund_id', 'range_return', 'annual_return', 'max_drawdown',
                                                'sharp_ratio', 'volatility', 'sortino_ratio', 'downside_risk',
@@ -173,18 +166,20 @@ def get_fund_rank():
         return df
 
 
-def get_index_daily(index_id):
-    """获取指数数据
+def get_index_daily(index_id, start_date):
+    """获取指数日更数据
 
     Args:
         index_id: 指数ID
+        start_date: 数据开始时间
 
     Returns:与组合净值形式相同的表
 
     """
     with TAMP_SQL(tamp_fund_engine) as tamp_product:
         tamp_product_session = tamp_product.session
-        sql = "SELECT ts_code, trade_date, close FROM index_daily WHERE ts_code='{}'".format(index_id)
+        sql = "SELECT ts_code, trade_date, close FROM index_daily " \
+              "WHERE ts_code='{}' AND trade_date>'{}'".format(index_id, start_date)
         # df = pd.read_sql(sql, con).dropna(how='any')
         cur = tamp_product_session.execute(sql)
         data = cur.fetchall()
@@ -198,6 +193,49 @@ def get_index_daily(index_id):
     return df
 
 
+def get_index_monthly(index_id, start_date):
+    """获取指数月度数据
+
+    Args:
+        index_id: 指数ID
+        start_date: 数据开始时间
+
+    Returns:与组合净值形式相同的表
+
+    """
+    with TAMP_SQL(tamp_fund_engine) as tamp_fund:
+        tamp_fund_session = tamp_fund.session
+        sql = "SELECT ts_code, trade_date, pct_chg FROM index_monthly " \
+              "WHERE ts_code='{}' AND trade_date>'{}'".format(index_id, start_date)
+        # df = pd.read_sql(sql, con).dropna(how='any')
+        cur = tamp_fund_session.execute(sql)
+        data = cur.fetchall()
+
+        df = pd.DataFrame(list(data), columns=['fund_id', 'end_date', 'pct_chg'])
+        df['end_date'] = pd.to_datetime(df['end_date'])
+        df.set_index('end_date', drop=True, inplace=True)
+        df.sort_index(inplace=True, ascending=True)
+        df = rename_col(df, index_id)
+        return df
+
+
+def get_tamp_fund():
+    """获取探普产品池净值表
+
+    Returns:
+
+    """
+    with TAMP_SQL(tamp_fund_engine) as tamp_fund:
+        tamp_fund_session = tamp_fund.session
+        sql = "SELECT id FROM tamp_fund_info WHERE id LIKE 'HF%'"
+        cur = tamp_fund_session.execute(sql)
+        data = cur.fetchall()
+        # df = pd.read_sql(sql, con)
+        df = pd.DataFrame(list(data), columns=['fund_id'])
+        # df.rename({'id': 'fund_id'}, axis=1, inplace=True)
+    return df
+
+
 def get_tamp_nav(fund, start_date, rollback=False, invest_type='public'):
     """获取基金ID为fund, 起始日期为start_date, 终止日期为当前日期的基金净值表
 
@@ -277,11 +315,11 @@ def get_radar_data(fund):
 
 
 def get_fund_name(fund):
-    with TAMP_SQL(tamp_fund_engine) as tamp_product:
-        tamp_product_session = tamp_product.session
+    with TAMP_SQL(tamp_fund_engine) as tamp_fund:
+        tamp_fund_session = tamp_fund.session
         sql = "SELECT fund_short_name FROM fund_info WHERE id='{}'".format(fund)
         # df = pd.read_sql(sql, con)
-        cur = tamp_product_session.execute(sql)
+        cur = tamp_fund_session.execute(sql)
         data = cur.fetchall()
         df = pd.DataFrame(list(data), columns=['fund_short_name'])
         return df
@@ -294,14 +332,17 @@ tamp_fund = get_tamp_fund()
 
 
 class PortfolioDiagnose(object):
-    def __init__(self, client_type, portfolio, invest_amount, expect_return=None,
-                 expect_drawdown=None, index_id='000905.SH', invest_type='private', start_date=None, end_date=None):
+    def __init__(self, client_type, portfolio, invest_amount, expect_return=0.2,
+                 expect_drawdown=0.1, index_id='000905.SH', invest_type='private', start_date=None, end_date=None):
         """基金诊断
 
         Args:
             client_type: 客户类型：1:保守型, 2:稳健型, 3:平衡型, 4:成长型, 5：进取型
             portfolio: 投资组合：[基金1, 基金2, 基金3...]
             invest_amount: 投资金额：10000000元
+            expect_return: 期望收益
+            expect_drawdown: 期望回撤
+            index_id： 指数ID
             invest_type: 投资类型：public, private, ...
             start_date: 诊断所需净值的开始日期
             end_date: 诊断所需净值的结束日期
@@ -348,51 +389,52 @@ class PortfolioDiagnose(object):
 
         while prod is None:
             # 获取的净值表为空时首先考虑基金净值数据不足半年，查找同一基金经理下的相同二级策略的基金ID作替换
-            result = fund_info[fund_info['fund_id'] == portfolio[0]]
+            result = fund_info[fund_info['fund_id'] == self.portfolio[0]]
             manager = str(result['manager'].values)
             strategy = result['substrategy'].values
+
             replaced_fund = replace_fund(manager, strategy, fund_rank)
 
-            if replaced_fund is not None:
+            if replaced_fund:
                 # 替换基金数据非空则记录替换的基金对
                 prod = get_nav(replaced_fund, self.start_date, invest_type=self.invest_type)
-                self.replace_pair[portfolio[0]] = replaced_fund
+                self.replace_pair[self.portfolio[0]] = replaced_fund
             else:
                 # 替换基金数据为空则记录当前基金为找不到数据的基金， 继续尝试获取下一个基金ID的净值表
-                self.no_data_fund.append(portfolio[0])
+                self.no_data_fund.append(self.portfolio[0])
                 self.portfolio.pop(0)
                 prod = get_tamp_nav(self.portfolio[0], self.start_date, invest_type=self.invest_type)
 
         # 记录基金的公布频率
         self.freq_list.append(get_frequency(prod))
-        prod = rename_col(prod, portfolio[0])
+        prod = rename_col(prod, self.portfolio[0])
 
         # 循环拼接基金净值表构建组合
-        for idx in range(len(portfolio) - 1):
-            prod1 = get_tamp_nav(portfolio[idx + 1], self.start_date, invest_type=self.invest_type)
+        for idx in range(len(self.portfolio) - 1):
+            prod1 = get_tamp_nav(self.portfolio[idx + 1], self.start_date, invest_type=self.invest_type)
 
             if prod1 is None or prod1.index[-1] - prod1.index[0] < 0.6 * (self.end_date - self.start_date):
-                result = fund_info[fund_info['fund_id'] == portfolio[idx + 1]]
+                result = fund_info[fund_info['fund_id'] == self.portfolio[idx + 1]]
 
                 if result['fund_manager_id'].count() != 0:
                     manager = str(result['fund_manager_id'].values)
                     substrategy = result['substrategy'].values[0]
                     replaced_fund = replace_fund(manager, substrategy, fund_rank)
                 else:
-                    self.no_data_fund.append(portfolio[idx + 1])
+                    self.no_data_fund.append(self.portfolio[idx + 1])
                     continue
 
-                if replaced_fund is not None:
+                if replaced_fund:
                     prod1 = get_nav(replaced_fund, self.start_date, invest_type=self.invest_type)
-                    self.replace_pair[portfolio[idx + 1]] = replaced_fund
+                    self.replace_pair[self.portfolio[idx + 1]] = replaced_fund
                     self.freq_list.append(get_frequency(prod1))
                     prod1 = rename_col(prod1, replaced_fund)
                 else:
-                    self.no_data_fund.append(portfolio[idx + 1])
+                    self.no_data_fund.append(self.portfolio[idx + 1])
                     continue
             else:
                 self.freq_list.append(get_frequency(prod1))
-                prod1 = rename_col(prod1, portfolio[idx + 1])
+                prod1 = rename_col(prod1, self.portfolio[idx + 1])
 
             # 取prod表和prod1表的并集
             prod = pd.merge(prod, prod1, on=['end_date'], how='outer')
@@ -476,6 +518,7 @@ class PortfolioDiagnose(object):
                 prod = pd.merge(prod, proposal_nav, how='outer', on='end_date').astype(float)
                 prod.sort_index(inplace=True)
                 prod.ffill(inplace=True)
+                prod.bfill(inplace=True)
                 prod = resample(prod, get_trade_cal(), min(self.freq_list))
 
                 self.new_correlation = cal_correlation(prod)
@@ -529,14 +572,31 @@ class PortfolioDiagnose(object):
         for fund in self.propose_portfolio.columns:
             propose_risk_mapper[fund] = str(get_risk_level(search_rank(fund_rank, fund, metric='substrategy')))
 
-        # risk_upper = {"H": 0.0}
-        # risk_lower = {"L": 0.6, "M": 0.4}
-
-        w_low = 1e6 / self.invest_amount
-        ef = EfficientFrontier(mu, S, expected_drawdown=dd)
-        # ef.add_sector_constraints(propose_risk_mapper, risk_lower, risk_upper)
-        # weights = ef.nonconvex_objective(deviation_risk_parity, ef.cov_matrix)
-        ef.efficient_return(0.3)
+        if self.client_type == 1:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+        elif self.client_type == 2:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+        elif self.client_type == 3:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+        elif self.client_type == 4:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+        elif self.client_type == 5:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+        else:
+            risk_upper = {"H": 1.0}
+            risk_lower = {"L": 0.0}
+            raise ValueError
+
+        w_low = 1000000 / self.invest_amount
+        # ef = EfficientFrontier(mu, S, weight_bounds=[w_low, 1], expected_drawdown=dd)
+        ef = EfficientFrontier(mu, S, weight_bounds=[0, 1], expected_drawdown=dd)
+        ef.add_sector_constraints(propose_risk_mapper, risk_lower, risk_upper)
+        ef.efficient_return(target_return=self.expect_return)
         clean_weights = ef.clean_weights()
         # ef.portfolio_performance(verbose=True)
         self.new_weights = np.array(list(clean_weights.values()))
@@ -564,7 +624,7 @@ class PortfolioDiagnose(object):
         # self.proposal_weights = calcu_w(w_origin, S, risk_target)
 
     def return_compare(self):
-        index_data = get_index_daily(self.index_id)
+        index_data = get_index_daily(self.index_id, self.start_date)
         index_data = pd.merge(index_data, self.propose_portfolio, how='inner', left_index=True, right_index=True)
         index_return = index_data.iloc[:, :] / index_data.iloc[0, :] - 1
         # origin_fund_return = origin_portfolio.iloc[:, :] / origin_portfolio.iloc[0, :] - 1
@@ -610,7 +670,7 @@ class PortfolioDiagnose(object):
 
         # 正收益基金数量
         group_hold_data = pd.DataFrame(group_result[group_name]["group_hoding_info"])
-        profit_positive_num = group_hold_data[group_hold_data["profit"]>0]["profit"].count()
+        profit_positive_num = group_hold_data[group_hold_data["profit"] > 0]["profit"].count()
         if profit_positive_num > 0:
             profit_positive_evaluate = str(profit_positive_num) + "只基金取的正收益，"
         else:
@@ -863,6 +923,16 @@ class PortfolioDiagnose(object):
                                  70 <= z_score < 80,
                                  z_score < 70], [0, 1, 2]).item()
 
+        index_return_monthly = get_index_monthly(self.index_id, self.start_date)
+        fund_nav = get_tamp_nav(fund_id, self.start_date, invest_type=self.invest_type)
+        fund_nav_monthly = fund_nav.groupby([fund_nav.index.year, fund_nav.index.month]).tail(1)
+        fund_nav_monthly = rename_col(fund_nav_monthly, fund_id)
+        fund_return_monthly = simple_return(fund_nav_monthly[fund_id].astype(float))
+        index_return_monthly.index = index_return_monthly.index.strftime('%Y-%m')
+        fund_return_monthly.index = fund_return_monthly.index.strftime('%Y-%m')
+        compare = pd.merge(index_return_monthly, fund_return_monthly, how='inner', left_index=True, right_index=True)
+        fund_win_rate = ((compare[fund_id] - compare['pct_chg']) > 0).sum()
+
         return_rank = search_rank(fund_rank, fund_id, metric='annual_return_rank')
         return_level = np.select([return_rank >= 0.8,
                                   0.7 <= return_rank < 0.8,
@@ -886,7 +956,7 @@ class PortfolioDiagnose(object):
                                  sharp_rank < 0.6], [0, 1, 2]).item()
 
         data = {1: [total_level, return_level, drawdown_level, sharp_level],
-                2: [return_triple, "12", return_bool],
+                2: [return_triple, str(fund_win_rate), return_bool],
                 3: [drawdown_triple, drawdown_triple, format(drawdown_value, '.2%'), drawdown_triple],
                 4: [return_bool, drawdown_bool, drawdown_bool, return_bool, drawdown_bool]}
 
@@ -923,7 +993,7 @@ class PortfolioDiagnose(object):
 
         sentence = {
             1: "该基金整体表现%s，收益能力%s，回撤控制能力%s，风险收益比例%s；\n",
-            2: "在收益方面，该基金年化收益能力%s同类基金平均水平，有%s区间跑赢指数，绝对收益能力%s；\n",
+            2: "在收益方面，该基金年化收益能力%s同类基金平均水平，有%s个区间跑赢指数，绝对收益能力%s；\n",
             3: "在风险方面，该基金抵御风险能力%s，在同类基金中处于%s等水平，最大回撤为%s，%s同类基金平均水平；\n",
             4: "该基金收益%s的同时回撤%s，也就是说，该基金在用%s风险换取%s收益，存在%s风险；\n",
             5: "基金经理，投资年限%s年，经验丰富；投资能力较强，生涯中共管理过%s只基金，历任的%s只基金平均业绩在同类中处于上游水平，其中%s只排名在前%s；生涯年化回报率%s，同期大盘只有%s；"}
@@ -945,6 +1015,14 @@ class PortfolioDiagnose(object):
             ret.append(single_sentence)
             i += 1
         fund_name = get_fund_name(fund_id).values[0][0]
+
+        if not ret:
+            try:
+                default_evaluation = pd.read_csv("evaluation.csv", encoding='utf-8', names=['fund_id', 'eval'])
+                ret.append('1、' + default_evaluation[default_evaluation['fund_id'] == fund_id]['eval'].values[0])
+            except Exception:
+                pass
+
         evaluation_dict = {'name': fund_name, 'data': ret}
         if fund_id in self.abandon_fund_score + self.abandon_fund_corr:
             evaluation_dict['status'] = "换仓"
@@ -983,14 +1061,14 @@ class PortfolioDiagnose(object):
         return radar_data
 
 
-portfolio = ['HF00002JJ2', 'HF00005DBQ', 'HF0000681Q', 'HF00006693', 'HF00006AZF', 'HF00006BGS']
-portfolio_diagnose = PortfolioDiagnose(client_type=1, portfolio=portfolio, invest_amount=10000000)
-portfolio_diagnose.optimize()
-if __name__ == '__main__':
-    print(portfolio_diagnose.single_fund_radar())
-    print(portfolio_diagnose.propose_fund_radar())
-    print(portfolio_diagnose.old_portfolio_evaluation())
-    print('旧组合相关性：', portfolio_diagnose.old_correlation)
-    print('新组合相关性：', portfolio_diagnose.new_correlation)
-    print('旧组合个基评价：', portfolio_diagnose.old_portfolio_evaluation())
-    print('新组合个基评价：', portfolio_diagnose.propose_fund_evaluation())
+# portfolio = ['HF00002JJ2', 'HF00005DBQ', 'HF0000681Q', 'HF00006693', 'HF00006AZF', 'HF00006BGS']
+# portfolio_diagnose = PortfolioDiagnose(client_type=1, portfolio=portfolio, invest_amount=10000000)
+# portfolio_diagnose.optimize()
+# if __name__ == '__main__':
+#     print(portfolio_diagnose.single_fund_radar())
+#     print(portfolio_diagnose.propose_fund_radar())
+#     print(portfolio_diagnose.old_portfolio_evaluation())
+#     print('旧组合相关性：', portfolio_diagnose.old_correlation)
+#     print('新组合相关性：', portfolio_diagnose.new_correlation)
+#     print('旧组合个基评价：', portfolio_diagnose.old_portfolio_evaluation())
+#     print('新组合个基评价：', portfolio_diagnose.propose_fund_evaluation())
\ No newline at end of file