1.新增分布分析分组显示数据

api/api_v1/endpoints/event_mana.py

@@ -30,11 +30,11 @@ async def event_list(
     #获取事件名
     try:
         event_list = await ckdb.distinct(game, 'event', '#event_name')
+        # 获取事件量
+        event_count = await ckdb.yesterday_event_count(game)
+        event_meta = await crud.event_mana.find_many(db, {'game': game}) or {}
     except Exception as e:
         return schemas.Msg(code=-9, msg='查无数据', data='')
-    #获取事件量
-    event_count = await ckdb.yesterday_event_count(game)
-    event_meta = await crud.event_mana.find_many(db, {'game':game}) or {}
     if event_meta:
         event_meta = pd.DataFrame(event_meta).set_index('event_name').fillna('').T.to_dict()
 

api/api_v1/endpoints/query.py

@@ -990,14 +990,14 @@ async def scatter_model(
     #转换数据类型为int
     df['values'] = df['values'].astype(int)
     interval_type = res['interval_type']
-    analysis = res['analysis']
+    analysi = res['analysis']
     groupby = res['groupby']
     quota_interval_arr = res['quota_interval_arr']
     # 兼容合计的
     if res['time_particle'] == 'total':
         df['date'] = '合计'
 
-    if analysis != 'number_of_days' and interval_type != 'discrete':
+    if analysi != 'number_of_days' and interval_type != 'discrete':
         max_v = int(df['values'].max())
         min_v = int(df['values'].min())
         interval = (max_v - min_v) // 10 or 1
@@ -1035,19 +1035,19 @@ async def scatter_model(
                                                                 'p': round(bins_s * 100 / total, 2).to_list(),
                                                                 'title': '总体'}
         # 分组的
-        if groupby:
+        # if groupby:
-            for key, tmp_df in df.groupby(['date', *groupby]):
+        #     for key, tmp_df in df.groupby(['date', *groupby]):
-                bins_s = pd.cut(tmp_df['values'], bins=bins,
+        #         bins_s = pd.cut(tmp_df['values'], bins=bins,
-                                right=False).value_counts()
+        #                         right=False).value_counts()
-                bins_s.sort_index(inplace=True)
+        #         bins_s.sort_index(inplace=True)
-                total = int(bins_s.sum())
+        #         total = int(bins_s.sum())
-                title = '.'.join(key[1:])
+        #         title = '.'.join(key[1:])
-                date = key[0]
+        #         date = key[0]
-                resp['list'][date.strftime('%Y-%m-%d')][title] = {'n': bins_s.to_list(), 'total': total,
+        #         resp['list'][date.strftime('%Y-%m-%d')][title] = {'n': bins_s.to_list(), 'total': total,
-                                                                  'p': round((bins_s * 100 / total).fillna(0),
+        #                                                           'p': round((bins_s * 100 / total).fillna(0),
-                                                                             2).to_list(),
+        #                                                                      2).to_list(),
-                                                                  'title': title
+        #                                                           'title': title
-                                                                  }
+        #                                                           }
         return schemas.Msg(code=0, msg='ok', data=resp)
 
     # elif analysis == 'number_of_days':
@@ -1122,7 +1122,91 @@ async def scatter_model(
         # resp['list'][key.strftime('%Y-%m-%d')]['总体'] = {'n': bins_s.to_list(), 'total': total,
         #                                                 'p': round(bins_s * 100 / total, 2).to_list(),
         #                                                 'title': '总体'}
+@router.post("/scatter_model_details")
+async def scatter_model(
+        request: Request,
+        game: str,
+        ckdb: CKDrive = Depends(get_ck_db),
+        db: AsyncIOMotorDatabase = Depends(get_database),
+        analysis: BehaviorAnalysis = Depends(BehaviorAnalysis),
+        current_user: schemas.UserDB = Depends(deps.get_current_user)
+) -> schemas.Msg:
+    await analysis.init(data_where=current_user.data_where)
+    try:
+        res = await analysis.scatter_model_sql()
+    except Exception as e:
+        return schemas.Msg(code=-9, msg='报表配置参数异常')
+    sql=res['sql']
+    if analysis.event_view['groupBy'] != []:
+        columnName=analysis.event_view['groupBy'][-1]['columnName']
+        sql=sql.replace(f'toDate(addHours({game}.event."#event_time", 8)) AS date', f'max(`{columnName}`) as va', 1)
+        sql=sql.replace(f'toDate(addHours({game}.event."#event_time", 8)),','',1)
+        df = await ckdb.query_dataframe(sql)
+        if df.empty:
+            return schemas.Msg(code=-9, msg='无数据', data=None)
+        df.fillna(0, inplace=True)
+        # 转换数据类型为int
+        df['values'] = df['values'].astype(int)
+        interval_type = res['interval_type']
+        analysi = res['analysis']
+        groupby = res['groupby']
+        quota_interval_arr = res['quota_interval_arr']
+        # 兼容合计的
+        if res['time_particle'] == 'total':
+            df['date'] = '合计'
 
+        if analysi != 'number_of_days' and interval_type != 'discrete':
+            max_v = int(df['values'].max())
+            min_v = int(df['values'].min())
+            interval = (max_v - min_v) // 10 or 1
+            resp = {'list': dict(),
+                    'start_date': res['start_date'],
+                    'end_date': res['end_date'],
+                    'time_particle': res['time_particle'],
+                    'biaotou':columnName
+                    }
+
+            if not quota_interval_arr:
+                resp['label'] = [f'[{i},{i + interval})' for i in range(min_v, max_v, interval)]
+                bins = [i for i in range(min_v, max_v + interval, interval)]
+            else:
+                quota_interval_arr = [-float('inf')] + quota_interval_arr + [float('inf')]
+                resp['label'] = []
+                bins = [quota_interval_arr[0]]
+                for i, v in enumerate(quota_interval_arr[1:]):
+                    resp['label'].append(f'[{quota_interval_arr[i]},{v})')
+                    bins.append(v)
+
+            # 这是分组的
+            for key, tmp_df in df.groupby('va'):
+                bins_s = pd.cut(tmp_df['values'], bins=bins,
+                                right=False).value_counts()
+                bins_s.sort_index(inplace=True)
+                total = int(bins_s.sum())
+                if res['time_particle'] == 'total':
+                    resp['list']['合计'] = dict()
+                    resp['list']['合计']['总体'] = {'n': bins_s.to_list(), 'total': total,
+                                                'p': round(bins_s * 100 / total, 2).to_list(),
+                                                'title': '总体'}
+                else:
+                    p=round(bins_s * 100 / total, 2).to_list()
+                    for i in range(len(p)):
+                        if str(p[i]) == 'nan':
+                            p[i] = 0
+                    if 'time' not in columnName:
+                        resp['list'][key] = dict()
+                        resp['list'][key] = {'n': bins_s.to_list(), 'total': total,
+                                                    'p': p,
+                                                    'title': '总体'}
+                    else:
+                        resp['list'][key.strftime('%Y-%m-%d %H:%M:%S')] = dict()
+                        resp['list'][key.strftime('%Y-%m-%d %H:%M:%S')] = {'n': bins_s.to_list(), 'total': total,
+                                                                        'p': p,
+                                                                        'title': '总体'}
+
+            return schemas.Msg(code=0, msg='ok', data=resp)
+    else:
+        return schemas.Msg(code=-9, msg='没有添加分组项', data='')
 
 @router.post("/trace_model_sql")
 async def trace_model_sql(

models/behavior_analysis.py

@@ -651,10 +651,14 @@ ORDER BY level
                     .where(and_(*where)) \
                     .group_by(*self.groupby, e_account_id_col)
             else:
+                # qry = sa.select(event_date_col, e_account_id_col,
+                #                 settings.CK_FUNC[analysis](event_attr_col).label('values')) \
+                #     .where(and_(*where)) \
+                #     .group_by(event_date_col, *self.groupby, e_account_id_col)
                 qry = sa.select(event_date_col, e_account_id_col,
                                 settings.CK_FUNC[analysis](event_attr_col).label('values')) \
                     .where(and_(*where)) \
-                    .group_by(event_date_col, *self.groupby, e_account_id_col)
+                    .group_by(event_date_col,e_account_id_col)
             sql = str(qry.compile(compile_kwargs={"literal_binds": True}))
             print(sql)
             return {