mdbq 0.0.7__py3-none-any.whl → 0.0.8__py3-none-any.whl

mdbq/aggregation/aggregation.py

@@ -118,11 +118,13 @@ class DataTypes:
         """
         # dtypes = df.dtypes.apply(str).to_dict()  # 将 dataframe 数据类型转为字典形式
         df.replace([np.inf, -np.inf], 0, inplace=True)  # 清理一些非法值
-
-        cols = df.columns.tolist()
         df.replace(to_replace=['\\N', '-', '--', '', 'nan'], value=0, regex=False, inplace=True)  # 替换掉特殊字符
         df.replace(to_replace=[','], value='', regex=True, inplace=True)
+        df.replace(to_replace=['="'], value='', regex=True, inplace=True)  # ="和"不可以放在一起清洗, 因为有: id=86785565
+        df.replace(to_replace=['"'], value='', regex=True, inplace=True)
+        cols = df.columns.tolist()
         for col in cols:
+            # df[col] = df[col].apply(lambda x: re.sub('[="]', '', str(x)) if '="' in str(x) else x)
             # 百分比在某些数据库中不兼容, 转换百分比为小数
             df[col] = df[col].apply(lambda x: float(float((str(x).rstrip("%"))) / 100) if str(x).endswith('%') and '~' not in str(x) else x)
             # 尝试转换合适的数据类型
@@ -976,9 +978,9 @@ def update_dtypte():
 
 def upload():
     """ 上传一个文件夹到数据库 """
-    path = '/Users/xigua/数据中心/原始文件2/生意参谋/客户_客户概况_画像'
-    db_name = '生意参谋数据2'
-    collection_name = '客户_客户概况_画像'
+    path = '/Users/xigua/数据中心/原始文件2/生意经/宝贝指标'
+    db_name = '生意经2'
+    collection_name = '宝贝指标'
 
     username, password, host, port = get_myconf.select_config_values(
         target_service='home_lx',
@@ -1018,10 +1020,7 @@ def upload():
                     df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
                     if len(df) == 0:
                         continue
-                    for col in df.columns.tolist():
-                        df[col] = df[col].apply(lambda x: re.sub('[="]', '', str(x)) if '="' in str(x) else x)
-                    # df.replace(to_replace=['--'], value='', regex=False, inplace=True)
-                    df = dt.convert_df_cols(df=df)
+                    df = dt.convert_df_cols(df=df)  # 清理列名和 df 中的非法字符
                     try:
                         df = df.astype(dtypes)
                     except Exception as e:
@@ -1044,8 +1043,8 @@ def upload():
 
 
 if __name__ == '__main__':
-    username, password, host, port = get_myconf.select_config_values(target_service='aliyun', database='mongodb')
-    print(username, password, host, port)
+    # username, password, host, port = get_myconf.select_config_values(target_service='aliyun', database='mongodb')
+    # print(username, password, host, port)
 
     # main()
-    # upload()
+    upload()

mdbq/aggregation/query_data.py

@@ -102,6 +102,30 @@ class MysqlDatasQuery:
         )
         return df
 
+    def syj(self):
+        start_date, end_date = self.months_data(num=self.months)
+        projection = {
+            '日期': 1,
+            '宝贝id': 1,
+            '商家编码': 1,
+            '行业类目': 1,
+            '销售额': 1,
+            '销售量': 1,
+            '订单数': 1,
+            '退货量': 1,
+            '退款额': 1,
+            '退货量_发货后_': 1,
+        }
+        df = self.download.data_to_df(
+            db_name='生意经2',
+            tabel_name='宝贝指标',
+            start_date=start_date,
+            end_date=end_date,
+            projection=projection,
+        )
+        return df
+
+
     @staticmethod
     def months_data(num=0, end_date=None):
         """ 读取近 num 个月的数据, 0 表示读取当月的数据 """
@@ -127,6 +151,7 @@ class GroupBy:
         """
         self.is_maximize: 是否最大转化数据
         """
+
         if '宝贝主体报表' in tabel_name:
             df.rename(columns={
                 '场景名字': '营销场景',
@@ -169,6 +194,31 @@ class GroupBy:
                 )
             df.insert(loc=1, column='推广渠道', value='万相台无界版')  # df中插入新列
             return df
+        if '宝贝指标' in tabel_name:
+            df.fillna(0, inplace=True)
+            df = df[(df['销售额'] != 0) | (df['退款额'] != 0)]
+            df = df.groupby(['日期', '宝贝id', '商家编码', '行业类目'], as_index=False).agg(
+                **{'销售额': ('销售额', np.min),
+                   '销售量': ('销售量', np.min),
+                   '订单数': ('订单数', np.min),
+                   '退货量': ('退货量', np.max),
+                   '退款额': ('退款额', np.max),
+                   '退货量_发货后_': ('退货量_发货后_', np.max),
+                   }
+            )
+            df['件均价'] = df.apply(lambda x: x['销售额'] / x['销售量'] if x['销售量'] > 0 else 0, axis=1).round(
+                0)  # 两列运算, 避免除以0
+            df['价格带'] = df['件均价'].apply(
+                lambda x: '2000+' if x >= 2000
+                else '1000+' if x >= 1000
+                else '500+' if x >= 500
+                else '300+' if x >= 300
+                else '300以下'
+            )
+            return df
+        else:
+            print(f'<{tabel_name}>: Groupby 类尚未配置，数据为空')
+            return pd.DataFrame({})
     
     def as_csv(self, df, filename, path=None, encoding='utf-8_sig',
                index=False, header=True, st_ascend=None, ascend=None, freq=None):
@@ -255,11 +305,16 @@ class GroupBy:
 def main():
     sdq = MysqlDatasQuery(target_service='home_lx')
     sdq.months = 0
-    df = sdq.tg_wxt()  # 从数据库中获取数据并转为 df
 
-    g = GroupBy()  # 数据聚合
-    df = g.groupby(df=df, tabel_name='推广数据_宝贝主体报表', is_maximize=True)
-    g.as_csv(df=df, filename='test')  # 数据导出
+    # df = sdq.tg_wxt()  # 从数据库中获取数据并转为 df
+    # g = GroupBy()  # 数据聚合
+    # df = g.groupby(df=df, tabel_name='推广数据_宝贝主体报表', is_maximize=True)
+    # g.as_csv(df=df, filename='推广数据_宝贝主体报表')  # 数据导出
+
+    df = sdq.syj()
+    g = GroupBy()
+    df = g.groupby(df=df, tabel_name='宝贝指标', is_maximize=True)
+    g.as_csv(df=df, filename='宝贝指标')
 
 
 if __name__ == '__main__':

{mdbq-0.0.7.dist-info → mdbq-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 0.0.7
+Version: 0.0.8
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-0.0.7.dist-info → mdbq-0.0.8.dist-info}/RECORD

@@ -1,8 +1,8 @@
 mdbq/__init__.py,sha256=Il5Q9ATdX8yXqVxtP_nYqUhExzxPC_qk_WXQ_4h0exg,16
 mdbq/__version__.py,sha256=y9Mp_8x0BCZSHsdLT_q5tX9wZwd5QgqrSIENLrb6vXA,62
 mdbq/aggregation/__init__.py,sha256=EeDqX2Aml6SPx8363J-v1lz0EcZtgwIBYyCJV6CcEDU,40
-mdbq/aggregation/aggregation.py,sha256=RHQa2rs4fimRvJzluujErg6I8fn7s9q1-kwC2bPZohE,59439
-mdbq/aggregation/query_data.py,sha256=Yb-gUPBm8r93oKFDiZ0-DiGhaqeL-jA7eAfZG0__DrA,11235
+mdbq/aggregation/aggregation.py,sha256=7Id0cZ5QR7rPR9srbNRv78lGBwQ7pQre65qYIhu89Ms,59498
+mdbq/aggregation/query_data.py,sha256=9E4dbeQAq7r1srlszP27X3jFiKtMmFc6lP965GHjQms,13368
 mdbq/bdup/__init__.py,sha256=AkhsGk81SkG1c8FqDH5tRq-8MZmFobVbN60DTyukYTY,28
 mdbq/bdup/bdup.py,sha256=LAV0TgnQpc-LB-YuJthxb0U42_VkPidzQzAagan46lU,4234
 mdbq/clean/__init__.py,sha256=A1d6x3L27j4NtLgiFV5TANwEkLuaDfPHDQNrPBbNWtU,41
@@ -28,7 +28,7 @@ mdbq/pbix/__init__.py,sha256=Trtfaynu9RjoTyLLYBN2xdRxTvm_zhCniUkVTAYwcjo,24
 mdbq/pbix/pbix_refresh.py,sha256=JUjKW3bNEyoMVfVfo77UhguvS5AWkixvVhDbw4_MHco,2396
 mdbq/pbix/refresh_all.py,sha256=wulHs4rivf4Mi0Pii2QR5Nk9-TBcvSwnCB_WH9QULKE,5939
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
-mdbq-0.0.7.dist-info/METADATA,sha256=nlphrFIJBQKjQnQvqtyK5NDTCGNTIOXRvxZdDGmiX20,245
-mdbq-0.0.7.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
-mdbq-0.0.7.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-0.0.7.dist-info/RECORD,,
+mdbq-0.0.8.dist-info/METADATA,sha256=dVu6kA6RtVWnfsNTWXnOv_d1TmKhM4Gw6PrypX9MF0E,245
+mdbq-0.0.8.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
+mdbq-0.0.8.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-0.0.8.dist-info/RECORD,,