Remove underscore from check methods.

Author: ueshin

python/pyspark/sql/dataframe.py

@@ -1906,9 +1906,9 @@ def toPandas(self):
         if self.sql_ctx.getConf("spark.sql.execution.arrow.enabled", "false").lower() == "true":
             try:
                 from pyspark.sql.types import _check_dataframe_localize_timestamps
-                from pyspark.sql.utils import _require_minimum_pyarrow_version
+                from pyspark.sql.utils import require_minimum_pyarrow_version
                 import pyarrow
-                _require_minimum_pyarrow_version()
+                require_minimum_pyarrow_version()
                 tables = self._collectAsArrow()
                 if tables:
                     table = pyarrow.concat_tables(tables)

python/pyspark/sql/session.py

@@ -494,11 +494,11 @@ def _create_from_pandas_with_arrow(self, pdf, schema, timezone):
         """
         from pyspark.serializers import ArrowSerializer, _create_batch
         from pyspark.sql.types import from_arrow_schema, to_arrow_type, TimestampType
-        from pyspark.sql.utils import _require_minimum_pandas_version, \
-            _require_minimum_pyarrow_version
+        from pyspark.sql.utils import require_minimum_pandas_version, \
+            require_minimum_pyarrow_version
 
-        _require_minimum_pandas_version()
-        _require_minimum_pyarrow_version()
+        require_minimum_pandas_version()
+        require_minimum_pyarrow_version()
 
         from pandas.api.types import is_datetime64_dtype, is_datetime64tz_dtype
 

python/pyspark/sql/tests.py

@@ -53,8 +53,8 @@
 try:
     import pandas
     try:
-        from pyspark.sql.utils import _require_minimum_pandas_version
-        _require_minimum_pandas_version()
+        from pyspark.sql.utils import require_minimum_pandas_version
+        require_minimum_pandas_version()
         _have_pandas = True
     except:
         _have_old_pandas = True

python/pyspark/sql/types.py

@@ -1686,8 +1686,8 @@ def _check_dataframe_localize_timestamps(pdf, timezone):
     :param timezone: the timezone to convert. if None then use local timezone
     :return pandas.DataFrame where any timezone aware columns have been converted to tz-naive
     """
-    from pyspark.sql.utils import _require_minimum_pandas_version
-    _require_minimum_pandas_version()
+    from pyspark.sql.utils import require_minimum_pandas_version
+    require_minimum_pandas_version()
 
     from pandas.api.types import is_datetime64tz_dtype
     tz = timezone or 'tzlocal()'
@@ -1707,8 +1707,8 @@ def _check_series_convert_timestamps_internal(s, timezone):
     :param timezone: the timezone to convert. if None then use local timezone
     :return pandas.Series where if it is a timestamp, has been UTC normalized without a time zone
     """
-    from pyspark.sql.utils import _require_minimum_pandas_version
-    _require_minimum_pandas_version()
+    from pyspark.sql.utils import require_minimum_pandas_version
+    require_minimum_pandas_version()
 
     from pandas.api.types import is_datetime64_dtype, is_datetime64tz_dtype
     # TODO: handle nested timestamps, such as ArrayType(TimestampType())?
@@ -1730,8 +1730,8 @@ def _check_series_convert_timestamps_localize(s, from_timezone, to_timezone):
     :param to_timezone: the timezone to convert to. if None then use local timezone
     :return pandas.Series where if it is a timestamp, has been converted to tz-naive
     """
-    from pyspark.sql.utils import _require_minimum_pandas_version
-    _require_minimum_pandas_version()
+    from pyspark.sql.utils import require_minimum_pandas_version
+    require_minimum_pandas_version()
 
     import pandas as pd
     from pandas.api.types import is_datetime64tz_dtype, is_datetime64_dtype

python/pyspark/sql/udf.py

@@ -37,9 +37,9 @@ def _create_udf(f, returnType, evalType):
     if evalType == PythonEvalType.SQL_PANDAS_SCALAR_UDF or \
             evalType == PythonEvalType.SQL_PANDAS_GROUP_MAP_UDF:
         import inspect
-        from pyspark.sql.utils import _require_minimum_pyarrow_version
+        from pyspark.sql.utils import require_minimum_pyarrow_version
 
-        _require_minimum_pyarrow_version()
+        require_minimum_pyarrow_version()
         argspec = inspect.getargspec(f)
 
         if evalType == PythonEvalType.SQL_PANDAS_SCALAR_UDF and len(argspec.args) == 0 and \

python/pyspark/sql/utils.py

@@ -112,7 +112,7 @@ def toJArray(gateway, jtype, arr):
     return jarr
 
 
-def _require_minimum_pandas_version():
+def require_minimum_pandas_version():
     """ Raise ImportError if minimum version of Pandas is not installed
     """
     from distutils.version import LooseVersion
@@ -121,7 +121,7 @@ def _require_minimum_pandas_version():
         raise ImportError("Pandas >= 0.19.2 must be installed on calling Python process")
 
 
-def _require_minimum_pyarrow_version():
+def require_minimum_pyarrow_version():
     """ Raise ImportError if minimum version of pyarrow is not installed
     """
     from distutils.version import LooseVersion