Preparing for release 0.3.2

Author: igorborgest

awswrangler/pandas.py

@@ -935,7 +935,9 @@ def _data_to_s3_object_writer(dataframe: pd.DataFrame,
         if file_format == "parquet":
             outfile: str = f"{guid}{compression_extension}.parquet"
         elif file_format == "csv":
-            filename: Optional[str] = extra_args.get("filename")
+            filename: Optional[str] = None
+            if extra_args is not None:
+                filename = extra_args.get("filename")
             if filename is None:
                 outfile = f"{guid}{compression_extension}.csv"
             else:
@@ -989,8 +991,11 @@ def _write_csv_dataframe(dataframe, path, preserve_index, compression, fs, extra
                 csv_extra_args["quoting"] = csv.QUOTE_NONE
                 csv_extra_args["escapechar"] = "\\"
         csv_buffer: bytes = bytes(
-            dataframe.to_csv(None, header=extra_args.get("header"), index=preserve_index, compression=compression, **csv_extra_args),
-            "utf-8")
+            dataframe.to_csv(None,
+                             header=extra_args.get("header"),
+                             index=preserve_index,
+                             compression=compression,
+                             **csv_extra_args), "utf-8")
         Pandas._write_csv_to_s3_retrying(fs=fs, path=path, buffer=csv_buffer)
 
     @staticmethod

awswrangler/s3.py

@@ -325,7 +325,7 @@ def list_objects(self, path: str) -> List[str]:
                     after=tenacity.after_log(logger, INFO))
     def head_object_with_retry(client_s3: client, bucket: str, key: str) -> Dict[str, Any]:
         """
-        Executes the Boto3 head_object() function with an extra layer of random exponential back-off.
+        Execute the Boto3 head_object() function with an extra layer of random exponential back-off.
 
         https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/s3.html#S3.Client.head_object
 

docs/source/_templates/globaltoc.html

@@ -12,9 +12,9 @@
    :maxdepth: 4
 
    install
-   examples
    tutorials
+   examples
    divingdeep
-   contributing
    api/awswrangler
+   contributing
    license

docs/source/index.rst

@@ -2519,20 +2519,8 @@ def test_sequential_overwrite(bucket):
     path = f"s3://{bucket}/test_sequential_overwrite/"
     df = pd.DataFrame({"col": [1]})
     df2 = pd.DataFrame({"col": [2]})
-    wr.pandas.to_parquet(
-        dataframe=df,
-        path=path,
-        preserve_index=False,
-        mode="overwrite",
-        procs_cpu_bound=1
-    )
-    wr.pandas.to_parquet(
-        dataframe=df2,
-        path=path,
-        preserve_index=False,
-        mode="overwrite",
-        procs_cpu_bound=1
-    )
+    wr.pandas.to_parquet(dataframe=df, path=path, preserve_index=False, mode="overwrite", procs_cpu_bound=1)
+    wr.pandas.to_parquet(dataframe=df2, path=path, preserve_index=False, mode="overwrite", procs_cpu_bound=1)
     df3 = wr.pandas.read_parquet(path=path)
     assert len(df3.index) == 1
     assert df3.col[0] == 2
@@ -2541,13 +2529,7 @@ def test_sequential_overwrite(bucket):
 def test_read_parquet_int_na(bucket):
     path = f"s3://{bucket}/test_read_parquet_int_na/"
     df = pd.DataFrame({"col": [1] + [pd.NA for _ in range(10_000)]}, dtype="Int64")
-    wr.pandas.to_parquet(
-        dataframe=df,
-        path=path,
-        preserve_index=False,
-        mode="overwrite",
-        procs_cpu_bound=4
-    )
+    wr.pandas.to_parquet(dataframe=df, path=path, preserve_index=False, mode="overwrite", procs_cpu_bound=4)
     df2 = wr.pandas.read_parquet(path=path)
     assert len(df2.index) == 10_001
     assert len(df2.columns) == 1
@@ -2557,13 +2539,7 @@ def test_read_parquet_int_na(bucket):
 def test_to_csv_header_filename(bucket):
     path = f"s3://{bucket}/test_to_csv_header_filename/"
     df = pd.DataFrame({"col1": [1, 2], "col2": ["foo", "boo"]})
-    paths = wr.pandas.to_csv(
-        dataframe=df,
-        path=path,
-        filename="file.csv",
-        header=True,
-        preserve_index=False
-    )
+    paths = wr.pandas.to_csv(dataframe=df, path=path, filename="file.csv", header=True, preserve_index=False)
     assert len(paths) == 1
     assert paths[0].endswith("/test_to_csv_header_filename/file.csv")
     df2 = wr.pandas.read_csv(path=paths[0])

testing/test_awswrangler/test_pandas.py

@@ -933,9 +933,7 @@ def test_to_redshift_int_na(bucket, redshift_parameters):
                           iam_role=redshift_parameters.get("RedshiftRole"),
                           mode="overwrite",
                           preserve_index=False,
-                          cast_columns={
-                              "col4": "INT8"
-                          })
+                          cast_columns={"col4": "INT8"})
     conn = wr.glue.get_connection("aws-data-wrangler-redshift")
     with conn.cursor() as cursor:
         cursor.execute("SELECT * FROM public.test_to_redshift_int_na")

testing/test_awswrangler/test_redshift.py

@@ -236,9 +236,5 @@ def test_wait_object_exists(bucket):
 def test_head_object_with_retry(bucket):
     key = "test_head_object_with_retry"
     boto3.resource("s3").Object(bucket, key).put(Body=str("Hello!"))
-    res = wr.s3.head_object_with_retry(
-        client_s3=boto3.client("s3"),
-        bucket=bucket,
-        key=key
-    )
+    res = wr.s3.head_object_with_retry(client_s3=boto3.client("s3"), bucket=bucket, key=key)
     assert res["ResponseMetadata"]["HTTPHeaders"]["content-length"] == "6"