Skip to content

BigQuery: Allow subset of schema to be passed into load_table_from_dataframe. #9064

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tswast merged 9 commits into from
Aug 22, 2019
+295 −88
Merged

BigQuery: Allow subset of schema to be passed into load_table_from_dataframe. #9064

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
aedca10
Allow subset of schema to be passed into `load_table_from_dataframe`.
tswast Aug 20, 2019
a580425
Use OrderedDict for brevity.
tswast Aug 21, 2019
105ebc9
Use OrderedDict for DataFrame in system tests.
tswast Aug 21, 2019
b8489fd
Warn when it's not possible to determine a column type.
tswast Aug 21, 2019
718c172
Refactor for coverage.
tswast Aug 21, 2019
8788441
Move struct type detection to _pandas_helpers
tswast Aug 21, 2019
1fa9389
Set schema to None if can't be autodetected.
tswast Aug 22, 2019
a94a95b
Merge remote-tracking branch 'upstream/master' into issue8140-partial…
tswast Aug 22, 2019
ca303a6
Explicitly use unicode strings in tests.
tswast Aug 22, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
119 changes: 67 additions & 52 deletions bigquery/tests/system.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -743,21 +743,22 @@ def test_load_table_from_dataframe_w_nulls(self):
)
num_rows = 100
nulls = [None] * num_rows
dataframe = pandas.DataFrame(
{
"bool_col": nulls,
"bytes_col": nulls,
"date_col": nulls,
"dt_col": nulls,
"float_col": nulls,
"geo_col": nulls,
"int_col": nulls,
"num_col": nulls,
"str_col": nulls,
"time_col": nulls,
"ts_col": nulls,
}
df_data = collections.OrderedDict(
[
("bool_col", nulls),
("bytes_col", nulls),
("date_col", nulls),
("dt_col", nulls),
("float_col", nulls),
("geo_col", nulls),
("int_col", nulls),
("num_col", nulls),
("str_col", nulls),
("time_col", nulls),
("ts_col", nulls),
]
)
dataframe = pandas.DataFrame(df_data, columns=df_data.keys())

dataset_id = _make_dataset_id("bq_load_test")
self.temp_dataset(dataset_id)
Expand Down Expand Up @@ -796,7 +797,7 @@ def test_load_table_from_dataframe_w_required(self):
)

records = [{"name": "Chip", "age": 2}, {"name": "Dale", "age": 3}]
dataframe = pandas.DataFrame(records)
dataframe = pandas.DataFrame(records, columns=["name", "age"])
job_config = bigquery.LoadJobConfig(schema=table_schema)
dataset_id = _make_dataset_id("bq_load_test")
self.temp_dataset(dataset_id)
Expand Down Expand Up @@ -847,44 +848,58 @@ def test_load_table_from_dataframe_w_explicit_schema(self):
# https://jira.apache.org/jira/browse/ARROW-2587
# bigquery.SchemaField("struct_col", "RECORD", fields=scalars_schema),
)
dataframe = pandas.DataFrame(
{
"bool_col": [True, None, False],
"bytes_col": [b"abc", None, b"def"],
"date_col": [datetime.date(1, 1, 1), None, datetime.date(9999, 12, 31)],
"dt_col": [
datetime.datetime(1, 1, 1, 0, 0, 0),
None,
datetime.datetime(9999, 12, 31, 23, 59, 59, 999999),
],
"float_col": [float("-inf"), float("nan"), float("inf")],
"geo_col": [
"POINT(30 10)",
None,
"POLYGON ((30 10, 40 40, 20 40, 10 20, 30 10))",
],
"int_col": [-9223372036854775808, None, 9223372036854775807],
"num_col": [
decimal.Decimal("-99999999999999999999999999999.999999999"),
None,
decimal.Decimal("99999999999999999999999999999.999999999"),
],
"str_col": ["abc", None, "def"],
"time_col": [
datetime.time(0, 0, 0),
None,
datetime.time(23, 59, 59, 999999),
],
"ts_col": [
datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.utc),
None,
datetime.datetime(
9999, 12, 31, 23, 59, 59, 999999, tzinfo=pytz.utc
),
],
},
dtype="object",
df_data = collections.OrderedDict(
[
("bool_col", [True, None, False]),
("bytes_col", [b"abc", None, b"def"]),
(
"date_col",
[datetime.date(1, 1, 1), None, datetime.date(9999, 12, 31)],
),
(
"dt_col",
[
datetime.datetime(1, 1, 1, 0, 0, 0),
None,
datetime.datetime(9999, 12, 31, 23, 59, 59, 999999),
],
),
("float_col", [float("-inf"), float("nan"), float("inf")]),
(
"geo_col",
[
"POINT(30 10)",
None,
"POLYGON ((30 10, 40 40, 20 40, 10 20, 30 10))",
],
),
("int_col", [-9223372036854775808, None, 9223372036854775807]),
(
"num_col",
[
decimal.Decimal("-99999999999999999999999999999.999999999"),
None,
decimal.Decimal("99999999999999999999999999999.999999999"),
],
),
("str_col", ["abc", None, "def"]),
Comment thread
tswast marked this conversation as resolved.
Outdated
(
"time_col",
[datetime.time(0, 0, 0), None, datetime.time(23, 59, 59, 999999)],
),
(
"ts_col",
[
datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.utc),
None,
datetime.datetime(
9999, 12, 31, 23, 59, 59, 999999, tzinfo=pytz.utc
Comment thread
tswast marked this conversation as resolved.
),
],
),
]
)
dataframe = pandas.DataFrame(df_data, dtype="object", columns=df_data.keys())

dataset_id = _make_dataset_id("bq_load_test")
self.temp_dataset(dataset_id)
Expand Down