Merge pull request #187 from awslabs/s3-copy

Add s3.copy_objects()

Author: igorborgest

README.md

@@ -84,6 +84,7 @@ df = wr.db.read_sql_query("SELECT * FROM external_schema.my_table", con=engine)
   - [10 - Parquet Crawler](https://github.com/awslabs/aws-data-wrangler/blob/master/tutorials/10%20-%20Parquet%20Crawler.ipynb)
   - [11 - CSV Datasets](https://github.com/awslabs/aws-data-wrangler/blob/master/tutorials/11%20-%20CSV%20Datasets.ipynb)
   - [12 - CSV Crawler](https://github.com/awslabs/aws-data-wrangler/blob/master/tutorials/12%20-%20CSV%20Crawler.ipynb)
+  - [13 - Merging Datasets on S3](https://github.com/awslabs/aws-data-wrangler/blob/master/tutorials/13%20-%20Merging%20Datasets%20on%20S3.ipynb)
 - [**API Reference**](https://aws-data-wrangler.readthedocs.io/en/latest/api.html)
   - [Amazon S3](https://aws-data-wrangler.readthedocs.io/en/latest/api.html#amazon-s3)
   - [AWS Glue Catalog](https://aws-data-wrangler.readthedocs.io/en/latest/api.html#aws-glue-catalog)

awswrangler/_utils.py

@@ -28,6 +28,13 @@ def client(service_name: str, session: Optional[boto3.Session] = None) -> boto3.
     )
 
 
+def resource(service_name: str, session: Optional[boto3.Session] = None) -> boto3.resource:
+    """Create a valid boto3.resource."""
+    return ensure_session(session=session).resource(
+        service_name=service_name, use_ssl=True, config=botocore.config.Config(retries={"max_attempts": 15})
+    )
+
+
 def parse_path(path: str) -> Tuple[str, str]:
     """Split a full S3 path in bucket and key strings.
 
@@ -62,7 +69,7 @@ def ensure_cpu_count(use_threads: bool = True) -> int:
 
     Note
     ----
-    In case of `use_threads=True` the number of process that could be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that could be spawned will be get from os.cpu_count().
 
     Parameters
     ----------

awswrangler/athena.py

@@ -369,7 +369,7 @@ def read_sql_query(  # pylint: disable=too-many-branches,too-many-locals
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------
@@ -605,7 +605,7 @@ def read_sql_table(
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------

awswrangler/db.py

@@ -438,7 +438,7 @@ def copy_to_redshift(  # pylint: disable=too-many-arguments
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------
@@ -576,7 +576,7 @@ def copy_files_to_redshift(  # pylint: disable=too-many-locals,too-many-argument
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------
@@ -798,7 +798,7 @@ def write_redshift_copy_manifest(
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------
@@ -908,7 +908,7 @@ def unload_redshift(
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------
@@ -1024,7 +1024,7 @@ def unload_redshift_to_files(
 
     Note
     ----
-    In case of `use_threads=True` the number of process that will be spawned will be get from os.cpu_count().
+    In case of `use_threads=True` the number of threads that will be spawned will be get from os.cpu_count().
 
     Parameters
     ----------