Add tests for uint8, uint16, uint32 and uint64. #76

Author: igorborgest

testing/test_awswrangler/test_data_lake.py

@@ -1396,3 +1396,38 @@ def test_unsigned_parquet(bucket, database):
     df["c0"] = df.c0.astype("uint64")
     with pytest.raises(wr.exceptions.UnsupportedType):
         wr.s3.to_parquet(df=df, path=path, dataset=True, database=database, table=table, mode="overwrite")
+
+    wr.s3.delete_objects(path=path)
+    wr.catalog.delete_table_if_exists(database=database, table=table)
+
+
+def test_parquet_uint64(bucket):
+    path = f"s3://{bucket}/test_parquet_uint64/"
+    wr.s3.delete_objects(path=path)
+    df = pd.DataFrame(
+        {
+            "c0": [0, 0, (2 ** 8) - 1],
+            "c1": [0, 0, (2 ** 16) - 1],
+            "c2": [0, 0, (2 ** 32) - 1],
+            "c3": [0, 0, (2 ** 64) - 1],
+            "c4": [0, 1, 2],
+        }
+    )
+    print(df)
+    df["c0"] = df.c0.astype("uint8")
+    df["c1"] = df.c1.astype("uint16")
+    df["c2"] = df.c2.astype("uint32")
+    df["c3"] = df.c3.astype("uint64")
+    paths = wr.s3.to_parquet(df=df, path=path, dataset=True, mode="overwrite", partition_cols=["c4"])["paths"]
+    wr.s3.wait_objects_exist(paths=paths, use_threads=False)
+    df = wr.s3.read_parquet(path=path, dataset=True)
+    print(df)
+    print(df.dtypes)
+    assert len(df.index) == 3
+    assert len(df.columns) == 5
+    assert df.c0.max() == (2 ** 8) - 1
+    assert df.c1.max() == (2 ** 16) - 1
+    assert df.c2.max() == (2 ** 32) - 1
+    assert df.c3.max() == (2 ** 64) - 1
+    assert df.c4.astype("uint8").sum() == 3
+    wr.s3.delete_objects(path=path)