chore: Bumping pyarrow / pandas (#17290)

* Bumping pyarrow / pandas * Appeasing the pylint gods * Adjusting UPDATING.md * Buping testing requirements
apache · Jan 10, 2022 · 6b7f2d3 · 6b7f2d3
1 parent 403cf79
commit 6b7f2d3
Show file tree

Hide file tree

Showing 13 changed files with 44 additions and 27 deletions.
diff --git a/UPDATING.md b/UPDATING.md
@@ -26,6 +26,7 @@ assists people when migrating to a new version.
 
 ### Breaking Changes
 
+- [17290](https://github.com/apache/superset/pull/17290): Bumps pandas to `1.3.4` and pyarrow to `5.0.0`
 - [16660](https://github.com/apache/incubator-superset/pull/16660): The `columns` Jinja parameter has been renamed `table_columns` to make the `columns` query object parameter available in the Jinja context.
 - [16711](https://github.com/apache/incubator-superset/pull/16711): The `url_param` Jinja function will now by default escape the result. For instance, the value `O'Brien` will now be changed to `O''Brien`. To disable this behavior, call `url_param` with `escape_result` set to `False`: `url_param("my_key", "my default", escape_result=False)`.
 

diff --git a/requirements/base.txt b/requirements/base.txt
@@ -168,7 +168,7 @@ packaging==21.0
     # via
     #   bleach
     #   deprecation
-pandas==1.2.5
+pandas==1.3.4
     # via apache-superset
 parsedatetime==2.6
     # via apache-superset
@@ -178,7 +178,7 @@ polyline==1.4.0
     # via apache-superset
 prison==0.2.1
     # via flask-appbuilder
-pyarrow==4.0.1
+pyarrow==5.0.0
     # via apache-superset
 pycparser==2.20
     # via cffi

diff --git a/requirements/development.in b/requirements/development.in
@@ -17,11 +17,11 @@
 # under the License.
 -r base.in
 flask-cors>=2.0.0
-mysqlclient==1.4.2.post1
+mysqlclient==2.0.3
 pillow>=8.3.1,<9
 pydruid>=0.6.1,<0.7
 pyhive[hive]>=0.6.1
-psycopg2-binary==2.8.5
+psycopg2-binary==2.9.1
 tableschema
 thrift>=0.11.0,<1.0.0
 progress>=1.5,<2

diff --git a/requirements/development.txt b/requirements/development.txt
@@ -1,4 +1,4 @@
-# SHA1:dbd3e93a11a36fc6b18d6194ac96ba29bd0ad2a8
+# SHA1:a2fe77c9b8bffc8c8f3de4df6709c8be957c2f87
 #
 # This file is autogenerated by pip-compile-multi
 # To update, run:
@@ -36,15 +36,15 @@ jsonlines==2.0.0
     # via tabulator
 linear-tsv==1.1.0
     # via tabulator
-mysqlclient==1.4.2.post1
+mysqlclient==2.0.3
     # via -r requirements/development.in
 openpyxl==3.0.7
     # via tabulator
 pillow==8.3.1
     # via -r requirements/development.in
 progress==1.6
     # via -r requirements/development.in
-psycopg2-binary==2.8.5
+psycopg2-binary==2.9.1
     # via -r requirements/development.in
 pure-sasl==0.6.2
     # via thrift-sasl

diff --git a/requirements/testing.in b/requirements/testing.in
@@ -19,13 +19,16 @@
 docker
 flask-testing
 freezegun
+google-cloud-bigquery
 ipdb
 # pinning ipython as pip-compile-multi was bringing higher version
 # of the ipython that was not found in CI
 ipython
 openapi-spec-validator
 openpyxl
+pandas_gbq
 parameterized
+pybigquery
 pyfakefs
 pyhive[presto]>=0.6.3
 pylint==2.9.6

diff --git a/requirements/testing.txt b/requirements/testing.txt
@@ -1,4 +1,4 @@
-# SHA1:a36e63b551290f1060a819fe4f1f50bc6200403c
+# SHA1:4aabffca9a6688f2911d6f8697495e7045a529d0
 #
 # This file is autogenerated by pip-compile-multi
 # To update, run:
@@ -31,7 +31,7 @@ flask-testing==0.8.1
     # via -r requirements/testing.in
 freezegun==1.1.0
     # via -r requirements/testing.in
-google-api-core[grpc]==2.1.0
+google-api-core[grpc]==2.2.1
     # via
     #   google-cloud-bigquery
     #   google-cloud-bigquery-storage
@@ -49,8 +49,9 @@ google-auth-oauthlib==0.4.6
     # via
     #   pandas-gbq
     #   pydata-google-auth
-google-cloud-bigquery[bqstorage,pandas]==2.28.0
+google-cloud-bigquery[bqstorage,pandas]==2.29.0
     # via
+    #   -r requirements/testing.in
     #   apache-superset
     #   pandas-gbq
     #   pybigquery
@@ -60,14 +61,19 @@ google-cloud-core==2.1.0
     # via google-cloud-bigquery
 google-crc32c==1.3.0
     # via google-resumable-media
-google-resumable-media==2.0.3
+google-resumable-media==2.1.0
     # via google-cloud-bigquery
 googleapis-common-protos==1.53.0
-    # via google-api-core
-grpcio==1.41.0
+    # via
+    #   google-api-core
+    #   grpcio-status
+grpcio==1.41.1
     # via
     #   google-api-core
     #   google-cloud-bigquery
+    #   grpcio-status
+grpcio-status==1.41.1
+    # via google-api-core
 iniconfig==1.1.1
     # via pytest
 ipdb==0.13.9
@@ -99,7 +105,9 @@ openapi-schema-validator==0.1.5
 openapi-spec-validator==0.3.1
     # via -r requirements/testing.in
 pandas-gbq==0.15.0
-    # via apache-superset
+    # via
+    #   -r requirements/testing.in
+    #   apache-superset
 parameterized==0.8.1
     # via -r requirements/testing.in
 parso==0.8.2
@@ -110,15 +118,16 @@ pickleshare==0.7.5
     # via ipython
 prompt-toolkit==3.0.19
     # via ipython
-proto-plus==1.19.2
+proto-plus==1.19.7
     # via
     #   google-cloud-bigquery
     #   google-cloud-bigquery-storage
-protobuf==3.18.1
+protobuf==3.19.1
     # via
     #   google-api-core
     #   google-cloud-bigquery
     #   googleapis-common-protos
+    #   grpcio-status
     #   proto-plus
 ptyprocess==0.7.0
     # via pexpect
@@ -129,7 +138,9 @@ pyasn1==0.4.8
 pyasn1-modules==0.2.8
     # via google-auth
 pybigquery==0.10.2
-    # via apache-superset
+    # via
+    #   -r requirements/testing.in
+    #   apache-superset
 pydata-google-auth==1.2.0
     # via pandas-gbq
 pyfakefs==4.5.0

diff --git a/setup.py b/setup.py
@@ -90,15 +90,15 @@ def get_git_sha() -> str:
         "isodate",
         "markdown>=3.0",
         "msgpack>=1.0.0, <1.1",
-        "pandas>=1.2.2, <1.3",
+        "pandas>=1.3.0, <1.4",
         "parsedatetime",
         "pgsanity",
         "polyline",
         "pyparsing>=2.4.7, <3.0.0",
         "python-dateutil",
         "python-dotenv",
         "python-geohash",
-        "pyarrow>=4.0.1, <4.1",
+        "pyarrow>=5.0.0, <6.0",
         "pyyaml>=5.4",
         "PyJWT>=1.7.1, <2",
         "redis",

diff --git a/superset/config.py b/superset/config.py
@@ -37,7 +37,7 @@
 from dateutil import tz
 from flask import Blueprint
 from flask_appbuilder.security.manager import AUTH_DB
-from pandas.io.parsers import STR_NA_VALUES
+from pandas._libs.parsers import STR_NA_VALUES  # pylint: disable=no-name-in-module
 from typing_extensions import Literal
 from werkzeug.local import LocalProxy
 
@@ -1301,7 +1301,7 @@ def SQL_QUERY_MUTATOR(  # pylint: disable=invalid-name,unused-argument
 elif importlib.util.find_spec("superset_config") and not is_test():
     try:
         import superset_config  # pylint: disable=import-error
-        from superset_config import *  # type: ignore # pylint: disable=import-error,wildcard-import
+        from superset_config import *  # type: ignore # pylint: disable=import-error,wildcard-import,unused-wildcard-import
 
         print(f"Loaded your LOCAL configuration at [{superset_config.__file__}]")
     except Exception:

diff --git a/superset/db_engine_specs/bigquery.py b/superset/db_engine_specs/bigquery.py
@@ -384,7 +384,7 @@ def get_parameters_from_uri(
 
     @classmethod
     def get_dbapi_exception_mapping(cls) -> Dict[Type[Exception], Type[Exception]]:
-        # pylint: disable=import-error,import-outside-toplevel
+        # pylint: disable=import-outside-toplevel
         from google.auth.exceptions import DefaultCredentialsError
 
         return {DefaultCredentialsError: SupersetDBAPIDisconnectionError}

diff --git a/superset/db_engine_specs/druid.py b/superset/db_engine_specs/druid.py
@@ -57,10 +57,12 @@ class DruidEngineSpec(BaseEngineSpec):
         "P3M": "TIME_FLOOR(CAST({col} AS TIMESTAMP), 'P3M')",
         "P1Y": "TIME_FLOOR(CAST({col} AS TIMESTAMP), 'P1Y')",
         "P1W/1970-01-03T00:00:00Z": (
-            "TIME_SHIFT(TIME_FLOOR(TIME_SHIFT(CAST({col} AS TIMESTAMP), 'P1D', 1), 'P1W'), 'P1D', 5)"  # pylint: disable=line-too-long
+            "TIME_SHIFT(TIME_FLOOR(TIME_SHIFT(CAST({col} AS TIMESTAMP), "
+            "'P1D', 1), 'P1W'), 'P1D', 5)"
         ),
         "1969-12-28T00:00:00Z/P1W": (
-            "TIME_SHIFT(TIME_FLOOR(TIME_SHIFT(CAST({col} AS TIMESTAMP), 'P1D', 1), 'P1W'), 'P1D', -1)"  # pylint: disable=line-too-long
+            "TIME_SHIFT(TIME_FLOOR(TIME_SHIFT(CAST({col} AS TIMESTAMP), "
+            "'P1D', 1), 'P1W'), 'P1D', -1)"
         ),
     }
 

diff --git a/superset/db_engine_specs/snowflake.py b/superset/db_engine_specs/snowflake.py
@@ -231,7 +231,7 @@ def get_parameters_from_uri(
 
     @classmethod
     def validate_parameters(
-        cls, parameters: SnowflakeParametersType  # pylint: disable=unused-argument
+        cls, parameters: SnowflakeParametersType
     ) -> List[SupersetError]:
         errors: List[SupersetError] = []
         required = {

diff --git a/superset/sql_lab.py b/superset/sql_lab.py
@@ -176,7 +176,7 @@ def get_sql_results(  # pylint: disable=too-many-arguments
             return handle_query_error(ex, query, session)
 
 
-def execute_sql_statement(  # pylint: disable=too-many-arguments,too-many-locals,too-many-statements
+def execute_sql_statement(  # pylint: disable=too-many-arguments,too-many-locals
     sql_statement: str,
     query: Query,
     user_name: Optional[str],

diff --git a/superset/utils/core.py b/superset/utils/core.py
@@ -16,7 +16,7 @@
 # under the License.
 """Utility functions used across Superset"""
 # pylint: disable=too-many-lines
-import _thread  # pylint: disable=C0411
+import _thread
 import collections
 import decimal
 import errno