[GitHub] [airflow] jj-ookla commented on a change in pull request #6670: [AIRFLOW-4816]MySqlToS3Operator

[GitBox <gi...@apache.org>]

jj-ookla commented on a change in pull request #6670: [AIRFLOW-4816]MySqlToS3Operator
URL: https://github.com/apache/airflow/pull/6670#discussion_r374202523
 
 

 ##########
 File path: airflow/operators/mysql_to_s3_operator.py
 ##########
 @@ -0,0 +1,122 @@
+# -*- coding: utf-8 -*-
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+"""
+Transfer data from MySQL into a S3 bucket
+"""
+import os
+import pickle
+import tempfile
+from typing import Optional, Union
+
+import numpy as np
+import pandas as pd
+
+from airflow.models import BaseOperator
+from airflow.providers.amazon.aws.hooks.s3 import S3Hook
+from airflow.providers.mysql.hooks.mysql import MySqlHook
+from airflow.utils.decorators import apply_defaults
+
+
+class MySQLToS3Operator(BaseOperator):
+    """
+    Saves data from an specific MySQL query into a file in S3.
+
+    :param query: the sql query to be executed.
+    :type query: str
+    :param s3_bucket: bucket where the data will be stored
+    :type s3_bucket: str
+    :param s3_key: desired key for the file. It includes the name of the file
+    :type s3_key: str
+    :param mysql_conn_id: reference to a specific mysql database
+    :type mysql_conn_id: str
+     :param aws_conn_id: reference to a specific S3 connection
+    :type aws_conn_id: str
+    :param verify: Whether or not to verify SSL certificates for S3 connection.
+        By default SSL certificates are verified.
+        You can provide the following values:
+
+        - False: do not validate SSL certificates. SSL will still be used
+                 (unless use_ssl is False), but SSL certificates will not be
+                 verified.
+        - path/to/cert/bundle.pem: A filename of the CA cert bundle to uses.
+                 You can specify this argument if you want to use a different
+                 CA cert bundle than the one used by botocore.
+    :type verify: bool or str
+    :param header: whether to include header or not into the S3 file
+    :type header: bool
+    :param index: whether to include index or not into the S3 file
+    :type index: bool
+    """
+
+    @apply_defaults
+    def __init__(
+            self,
+            query: str,
+            s3_bucket: str,
+            s3_key: str,
+            mysql_conn_id: str = 'mysql_default',
+            aws_conn_id: str = 'aws_default',
+            verify: Optional[Union[bool, str]] = None,
+            header: Optional[bool] = False,
+            index: Optional[bool] = False,
+            *args, **kwargs) -> None:
+        super().__init__(*args, **kwargs)
+        self.query = query
+        self.s3_bucket = s3_bucket
+        self.s3_key = s3_key
+        self.mysql_conn_id = mysql_conn_id
+        self.aws_conn_id = aws_conn_id
+        self.verify = verify
+        self.header = header
+        self.index = index
+
+    def fill_na_with_none(self, series):
+        """
+        Replace NaN values with None
+         """
+        return np.where(series.isnull(), None, series)
+
+    def fix_int_dtypes(self, df):
+        """
+        Mutate DataFrame to set dtypes for int columns containing NaN values."
+        """
+        for col in df:
+            if "float" in df[col].dtype.name and df[col].hasnans:
+                # inspect values to determine if dtype of non-null values is int or float
+                notna_series = df[col].dropna().values
+                if np.isclose(notna_series, notna_series.astype(int)).all():
+                    # set to dtype that retains integers and supports NaNs
+                    df[col] = self.fill_na_with_none(df[col]).astype(pd.Int64Dtype)
 
 Review comment:
   @feluelle @JavierLopezT 
   
   Using pandas 0.25.3, this will cause an error. My initial [suggestion](https://github.com/apache/airflow/pull/6670#discussion_r351426086) provides information on why this approach is necessary.
   
   ```Python
   In [2]: import pandas as pd    
   
   In [3]: df = pd.DataFrame({"a": [0, 1, 2, None, 3]})                                      
   
   In [4]: df                                                                                
   Out[4]: 
        a
   0  0.0
   1  1.0
   2  2.0
   3  NaN
   4  3.0
   
   In [5]: df["a"].fillna(None)                                                              
   ---------------------------------------------------------------------------
   ValueError                                Traceback (most recent call last)
   <ipython-input-5-565a6a1eb2b3> in <module>
   ----> 1 df["a"].fillna(None)
   ...
   ValueError: Must specify a fill 'value' or 'method'.
   ```
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services