[SPARK-23081][PYTHON]Add colRegex API to PySpark

python/pyspark/sql/dataframe.py

@@ -819,6 +819,29 @@ def columns(self):
         """
         return [f.name for f in self.schema.fields]
 
+    @since(2.3)
+    def colRegex(self, colName):
+        """
+        Selects column based on the column name specified as a regex and returns it
+        as :class:`Column`.
+
+        :param colName: string, column name specified as a regex.
+
+        >>> df = spark.createDataFrame([("a", 1), ("b", 2), ("c",  3)], ["Col1", "Col2"])
+        >>> df.select(df.colRegex("`(Col1)?+.+`")).show()
+        +----+
+        |Col2|
+        +----+
+        |   1|
+        |   2|
+        |   3|
+        +----+
+        """
+        if not isinstance(colName, basestring):
+            raise ValueError("colName should be provided as string")
+        jc = self._jdf.colRegex(colName)
+        return Column(jc)
+
     @ignore_unicode_prefix
     @since(1.3)
     def alias(self, alias):

sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala

@@ -1194,7 +1194,7 @@ class Dataset[T] private[sql](
   def orderBy(sortExprs: Column*): Dataset[T] = sort(sortExprs : _*)
 
   /**
-   * Selects column based on the column name and return it as a [[Column]].
+   * Selects column based on the column name and returns it as a [[Column]].
    *
    * @note The column name can also reference to a nested column like `a.b`.
    *
@@ -1220,7 +1220,7 @@ class Dataset[T] private[sql](
   }
 
   /**
-   * Selects column based on the column name and return it as a [[Column]].
+   * Selects column based on the column name and returns it as a [[Column]].
    *
    * @note The column name can also reference to a nested column like `a.b`.
    *
@@ -1240,7 +1240,7 @@ class Dataset[T] private[sql](
   }
 
   /**
-   * Selects column based on the column name specified as a regex and return it as [[Column]].
+   * Selects column based on the column name specified as a regex and returns it as [[Column]].
    * @group untypedrel
    * @since 2.3.0
    */
@@ -2729,7 +2729,7 @@ class Dataset[T] private[sql](
   }
 
   /**
-   * Return an iterator that contains all rows in this Dataset.
+   * Returns an iterator that contains all rows in this Dataset.
    *
    * The iterator will consume as much memory as the largest partition in this Dataset.
    *