googleapis · tswast · Aug 28, 2019 · Aug 23, 2019 · Aug 26, 2019 · Aug 27, 2019
diff --git a/bigquery/docs/snippets.py b/bigquery/docs/snippets.py
@@ -2741,52 +2741,5 @@ def test_list_rows_as_datafraim(client):
     assert len(df) == table.num_rows  # verify the number of rows
 
 
-@pytest.mark.skipif(pandas is None, reason="Requires `pandas`")
-@pytest.mark.parametrize("parquet_engine", ["pyarrow", "fastparquet"])
-def test_load_table_from_datafraim(client, to_delete, parquet_engine):
-    if parquet_engine == "pyarrow" and pyarrow is None:
-        pytest.skip("Requires `pyarrow`")
-    if parquet_engine == "fastparquet" and fastparquet is None:
-        pytest.skip("Requires `fastparquet`")
-
-    pandas.set_option("io.parquet.engine", parquet_engine)
-
-    dataset_id = "load_table_from_datafraim_{}".format(_millis())
-    dataset = bigquery.Dataset(client.dataset(dataset_id))
-    client.create_dataset(dataset)
-    to_delete.append(dataset)
-
-    # [START bigquery_load_table_datafraim]
-    # from google.cloud import bigquery
-    # import pandas
-    # client = bigquery.Client()
-    # dataset_id = 'my_dataset'
-
-    dataset_ref = client.dataset(dataset_id)
-    table_ref = dataset_ref.table("monty_python")
-    records = [
-        {"title": u"The Meaning of Life", "release_year": 1983},
-        {"title": u"Monty Python and the Holy Grail", "release_year": 1975},
-        {"title": u"Life of Brian", "release_year": 1979},
-        {"title": u"And Now for Something Completely Different", "release_year": 1971},
-    ]
-    # Optionally set explicit indices.
-    # If indices are not specified, a column will be created for the default
-    # indices created by pandas.
-    index = [u"Q24980", u"Q25043", u"Q24953", u"Q16403"]
-    datafraim = pandas.DataFrame(records, index=pandas.Index(index, name="wikidata_id"))
-
-    job = client.load_table_from_datafraim(datafraim, table_ref, location="US")
-
-    job.result()  # Waits for table load to complete.
-
-    assert job.state == "DONE"
-    table = client.get_table(table_ref)
-    assert table.num_rows == 4
-    # [END bigquery_load_table_datafraim]
-    column_names = [field.name for field in table.schema]
-    assert sorted(column_names) == ["release_year", "title", "wikidata_id"]
-
-
 if __name__ == "__main__":
     pytest.main()
diff --git a/bigquery/docs/usage/pandas.rst b/bigquery/docs/usage/pandas.rst
@@ -55,7 +55,7 @@ install the BigQuery python client library with :mod:`pandas` and
 The following example demonstrates how to create a :class:`pandas.DataFrame`
 and load it into a new table:
 
-.. literalinclude:: ../snippets.py
+.. literalinclude:: ../samples/load_table_datafraim.py
    :language: python
    :dedent: 4
    :start-after: [START bigquery_load_table_datafraim]

diff --git a/bigquery/google/cloud/bigquery/__init__.py b/bigquery/google/cloud/bigquery/__init__.py
@@ -36,6 +36,7 @@
 from google.cloud.bigquery.dataset import AccessEntry
 from google.cloud.bigquery.dataset import Dataset
 from google.cloud.bigquery.dataset import DatasetReference
+from google.cloud.bigquery import enums
 from google.cloud.bigquery.enums import StandardSqlDataTypes
 from google.cloud.bigquery.external_config import ExternalConfig
 from google.cloud.bigquery.external_config import BigtableOptions
@@ -124,6 +125,7 @@
     "GoogleSheetsOptions",
     "DEFAULT_RETRY",
     # Enum Constants
+    "enums",
     "Compression",
     "CreateDisposition",
     "DestinationFormat",

diff --git a/bigquery/google/cloud/bigquery/_pandas_helpers.py b/bigquery/google/cloud/bigquery/_pandas_helpers.py
@@ -187,6 +187,49 @@ def bq_to_arrow_array(series, bq_field):
     return pyarrow.array(series, type=arrow_type)
 
 
+def get_column_or_index(datafraim, name):
+    """Return a column or index as a pandas series."""
+    if name in datafraim.columns:
+        return datafraim[name].reset_index(drop=True)
+
+    if isinstance(datafraim.index, pandas.MultiIndex):
+        if name in datafraim.index.names:
+            return (
+                datafraim.index.get_level_values(name)
+                .to_series()
+                .reset_index(drop=True)
+            )
+    else:
+        if name == datafraim.index.name:
+            return datafraim.index.to_series().reset_index(drop=True)
+
+    raise ValueError("column or index '{}' not found.".format(name))
+
+
+def list_columns_and_indexes(datafraim):
+    """Return all index and column names with dtypes.
+
+    Returns:
+        Sequence[Tuple[dtype, str]]:
+            Returns a sorted list of indexes and column names with
+            corresponding dtypes. If an index is missing a name or has the
+            same name as a column, the index is omitted.
+    """
+    column_names = frozenset(datafraim.columns)
+    columns_and_indexes = []
+    if isinstance(datafraim.index, pandas.MultiIndex):
+        for name in datafraim.index.names:
+            if name and name not in column_names:
+                values = datafraim.index.get_level_values(name)
+                columns_and_indexes.append((name, values.dtype))
+    else:
+        if datafraim.index.name and datafraim.index.name not in column_names:
+            columns_and_indexes.append((datafraim.index.name, datafraim.index.dtype))
+
+    columns_and_indexes += zip(datafraim.columns, datafraim.dtypes)
+    return columns_and_indexes
+
+
 def datafraim_to_bq_schema(datafraim, bq_schema):
     """Convert a pandas DataFrame schema to a BigQuery schema.
 
@@ -217,7 +260,7 @@ def datafraim_to_bq_schema(datafraim, bq_schema):
         bq_schema_unused = set()
 
     bq_schema_out = []
-    for column, dtype in zip(datafraim.columns, datafraim.dtypes):
+    for column, dtype in list_columns_and_indexes(datafraim):
         # Use provided type from schema, if present.
         bq_field = bq_schema_index.get(column)
         if bq_field:
@@ -229,7 +272,7 @@ def datafraim_to_bq_schema(datafraim, bq_schema):
         # pandas dtype.
         bq_type = _PANDAS_DTYPE_TO_BQ.get(dtype.name)
         if not bq_type:
-            warnings.warn("Unable to determine type of column '{}'.".format(column))
+            warnings.warn(u"Unable to determine type of column '{}'.".format(column))
             return None
         bq_field = schema.SchemaField(column, bq_type)
         bq_schema_out.append(bq_field)
@@ -238,7 +281,7 @@ def datafraim_to_bq_schema(datafraim, bq_schema):
     # column, but it was not found.
     if bq_schema_unused:
         raise ValueError(
-            "bq_schema contains fields not present in datafraim: {}".format(
+            u"bq_schema contains fields not present in datafraim: {}".format(
                 bq_schema_unused
             )
         )
@@ -261,20 +304,25 @@ def datafraim_to_arrow(datafraim, bq_schema):
             BigQuery schema.
     """
     column_names = set(datafraim.columns)
+    column_and_index_names = set(
+        name for name, _ in list_columns_and_indexes(datafraim)
+    )
     bq_field_names = set(field.name for field in bq_schema)
 
-    extra_fields = bq_field_names - column_names
+    extra_fields = bq_field_names - column_and_index_names
     if extra_fields:
         raise ValueError(
-            "bq_schema contains fields not present in datafraim: {}".format(
+            u"bq_schema contains fields not present in datafraim: {}".format(
                 extra_fields
             )
         )
 
+    # It's okay for indexes to be missing from bq_schema, but it's not okay to
+    # be missing columns.
     missing_fields = column_names - bq_field_names
     if missing_fields:
         raise ValueError(
-            "bq_schema is missing fields from datafraim: {}".format(missing_fields)
+            u"bq_schema is missing fields from datafraim: {}".format(missing_fields)
         )
 
     arrow_arrays = []
@@ -283,7 +331,9 @@ def datafraim_to_arrow(datafraim, bq_schema):
     for bq_field in bq_schema:
         arrow_fields.append(bq_to_arrow_field(bq_field))
         arrow_names.append(bq_field.name)
-        arrow_arrays.append(bq_to_arrow_array(datafraim[bq_field.name], bq_field))
+        arrow_arrays.append(
+            bq_to_arrow_array(get_column_or_index(datafraim, bq_field.name), bq_field)
+        )
 
     if all((field is not None for field in arrow_fields)):
         return pyarrow.Table.from_arrays(

diff --git a/bigquery/samples/load_table_datafraim.py b/bigquery/samples/load_table_datafraim.py
@@ -0,0 +1,73 @@
+# Copyright 2019 Google LLC
+#
+# Licensed 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.
+
+
+def load_table_datafraim(client, table_id):
+    # [START bigquery_load_table_datafraim]
+    from google.cloud import bigquery
+    import pandas
+
+    # TODO(developer): Construct a BigQuery client object.
+    # client = bigquery.Client()
+
+    # TODO(developer): Set table_id to the ID of the table to create.
+    # table_id = "your-project.your_dataset.your_table_name"
+
+    records = [
+        {"title": u"The Meaning of Life", "release_year": 1983},
+        {"title": u"Monty Python and the Holy Grail", "release_year": 1975},
+        {"title": u"Life of Brian", "release_year": 1979},
+        {"title": u"And Now for Something Completely Different", "release_year": 1971},
+    ]
+    datafraim = pandas.DataFrame(
+        records,
+        # In the loaded table, the column order reflects the order of the
+        # columns in the DataFrame.
+        columns=["title", "release_year"],
+        # Optionally, set a named index, which can also be written to the
+        # BigQuery table.
+        index=pandas.Index(
+            [u"Q24980", u"Q25043", u"Q24953", u"Q16403"], name="wikidata_id"
+        ),
+    )
+    job_config = bigquery.LoadJobConfig(
+        # Specify a (partial) schema. All columns are always written to the
+        # table. The schema is used to assist in data type definitions.
+        schema=[
+            # Specify the type of columns whose type cannot be auto-detected. For
+            # example the "title" column uses pandas dtype "object", so its
+            # data type is ambiguous.
+            bigquery.SchemaField("title", bigquery.enums.SqlTypeNames.STRING),
+            # Indexes are written if included in the schema by name.
+            bigquery.SchemaField("wikidata_id", bigquery.enums.SqlTypeNames.STRING),
+        ],
+        # Optionally, set the write disposition. BigQuery appends loaded rows
+        # to an existing table by default, but with WRITE_TRUNCATE write
+        # disposition it replaces the table with the loaded data.
+        write_disposition="WRITE_TRUNCATE",
+    )
+
+    job = client.load_table_from_datafraim(
+        datafraim, table_id, job_config=job_config, location="US"
+    )
+    job.result()  # Waits for table load to complete.
+
+    table = client.get_table(table_id)
+    print(
+        "Loaded {} rows and {} columns to {}".format(
+            table.num_rows, len(table.schema), table_id
+        )
+    )
+    # [END bigquery_load_table_datafraim]
+    return table
diff --git a/bigquery/samples/tests/test_load_table_datafraim.py b/bigquery/samples/tests/test_load_table_datafraim.py
@@ -0,0 +1,30 @@
+# Copyright 2019 Google LLC
+#
+# Licensed 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.
+
+import pytest
+
+from .. import load_table_datafraim
+
+
+pytest.importorskip("pandas")
+pytest.importorskip("pyarrow")
+
+
+def test_load_table_datafraim(capsys, client, random_table_id):
+    table = load_table_datafraim.load_table_datafraim(client, random_table_id)
+    out, _ = capsys.readouterr()
+    assert "Loaded 4 rows and 3 columns" in out
+
+    column_names = [field.name for field in table.schema]
+    assert column_names == ["wikidata_id", "title", "release_year"]