[SPARK-20442][PYTHON][DOCS] Fill up documentations for functions in Column API in PySpark

python/pyspark/sql/column.py

@@ -185,17 +185,52 @@ def __contains__(self, item):
                          "in a string column or 'array_contains' function for an array column.")
 
     # bitwise operators
-    bitwiseOR = _bin_op("bitwiseOR")
-    bitwiseAND = _bin_op("bitwiseAND")
-    bitwiseXOR = _bin_op("bitwiseXOR")
+    _bitwiseOR_doc = """
+    Compute bitwise OR of this expression with another expression.
+
+    :param other: a value or :class:`Column` to calculate bitwise or(|) against
+                  this :class:`Column`.
+
+    >>> from pyspark.sql import Row
+    >>> df3 = spark.createDataFrame([Row(a=170, b=75)])
+    >>> df3.select(df3.a.bitwiseOR(df3.b)).collect()
+    [Row((a | b)=235)]
+    """
+
+    _bitwiseAND_doc = """
+    Compute bitwise AND of this expression with another expression.
+
+    :param other: a value or :class:`Column` to calculate bitwise and(&) against
+                  this :class:`Column`.
+
+    >>> from pyspark.sql import Row
+    >>> df3 = spark.createDataFrame([Row(a=170, b=75)])
+    >>> df3.select(df3.a.bitwiseAND(df3.b)).collect()
+    [Row((a & b)=10)]
+    """
+
+    _bitwiseXOR_doc = """
+    Compute bitwise XOR of this expression with another expression.
+
+    :param other: a value or :class:`Column` to calculate bitwise xor(^) against
+                  this :class:`Column`.
+
+    >>> from pyspark.sql import Row
+    >>> df3 = spark.createDataFrame([Row(a=170, b=75)])
+    >>> df3.select(df3.a.bitwiseXOR(df3.b)).collect()
+    [Row((a ^ b)=225)]
+    """
+    bitwiseOR = _bin_op("bitwiseOR", _bitwiseOR_doc)
+    bitwiseAND = _bin_op("bitwiseAND", _bitwiseAND_doc)
+    bitwiseXOR = _bin_op("bitwiseXOR", _bitwiseXOR_doc)
 
     @since(1.3)
     def getItem(self, key):
         """
         An expression that gets an item at position ``ordinal`` out of a list,
         or gets an item by key out of a dict.
 
-        >>> df = sc.parallelize([([1, 2], {"key": "value"})]).toDF(["l", "d"])
+        >>> df = spark.createDataFrame([([1, 2], {"key": "value"})], ["l", "d"])
         >>> df.select(df.l.getItem(0), df.d.getItem("key")).show()
         +----+------+
         |l[0]|d[key]|
@@ -217,7 +252,7 @@ def getField(self, name):
         An expression that gets a field by name in a StructField.
 
         >>> from pyspark.sql import Row
-        >>> df = sc.parallelize([Row(r=Row(a=1, b="b"))]).toDF()
+        >>> df = spark.createDataFrame([Row(r=Row(a=1, b="b"))])
         >>> df.select(df.r.getField("b")).show()
         +---+
         |r.b|
@@ -251,15 +286,16 @@ def __iter__(self):
 
     # string methods
     _rlike_doc = """
-    Return a Boolean :class:`Column` based on a regex match.
+    SQL RLIKE expression (LIKE with Regex). Returns a boolean :class:`Column` based on a regex
+    match.
 
     :param other: an extended regex expression
 
     >>> df.filter(df.name.rlike('ice$')).collect()
     [Row(age=2, name=u'Alice')]
     """
     _like_doc = """
-    Return a Boolean :class:`Column` based on a SQL LIKE match.
+    SQL like expression. Returns a boolean :class:`Column` based on a SQL LIKE match.
 
     :param other: a SQL LIKE pattern
 
@@ -269,17 +305,17 @@ def __iter__(self):
     [Row(age=2, name=u'Alice')]
     """
     _startswith_doc = """
-    Return a Boolean :class:`Column` based on a string match.
+    String starts with. Returns a boolean :class:`Column` based on a string match.
 
-    :param other: string at end of line (do not use a regex `^`)
+    :param other: string at start of line (do not use a regex `^`)
 
     >>> df.filter(df.name.startswith('Al')).collect()
     [Row(age=2, name=u'Alice')]
     >>> df.filter(df.name.startswith('^Al')).collect()
     []
     """
     _endswith_doc = """
-    Return a Boolean :class:`Column` based on matching end of string.
+    String ends with. Returns a boolean :class:`Column` based on a string match.
 
     :param other: string at end of line (do not use a regex `$`)
 
@@ -288,8 +324,16 @@ def __iter__(self):
     >>> df.filter(df.name.endswith('ice$')).collect()
     []
     """
+    _contains_doc = """
+    Contains the other element. Returns a boolean :class:`Column` based on a string match.
+
+    :param other: string in line
+
+    >>> df.filter(df.name.contains('o')).collect()
+    [Row(age=5, name=u'Bob')]
+    """
 
-    contains = _bin_op("contains")
+    contains = ignore_unicode_prefix(_bin_op("contains", _contains_doc))
     rlike = ignore_unicode_prefix(_bin_op("rlike", _rlike_doc))
     like = ignore_unicode_prefix(_bin_op("like", _like_doc))
     startswith = ignore_unicode_prefix(_bin_op("startsWith", _startswith_doc))
@@ -337,26 +381,39 @@ def isin(self, *cols):
         return Column(jc)
 
     # order
-    asc = _unary_op("asc", "Returns a sort expression based on the"
-                           " ascending order of the given column name.")
-    desc = _unary_op("desc", "Returns a sort expression based on the"
-                             " descending order of the given column name.")
+    _asc_doc = """
+    Returns an ascending ordering used in sorting.
+
+    >>> from pyspark.sql import Row
+    >>> df2 = spark.createDataFrame([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)])
+    >>> df2.select(df2.name).orderBy(df2.name.asc()).collect()
+    [Row(name=u'Alice'), Row(name=u'Tom')]
+    """
+    _desc_doc = """
+    Returns a descending ordering used in sorting.
+
+    >>> from pyspark.sql import Row
+    >>> df2 = spark.createDataFrame([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)])
+    >>> df2.select(df2.name).orderBy(df2.name.desc()).collect()
+    [Row(name=u'Tom'), Row(name=u'Alice')]
+    """
+
+    asc = ignore_unicode_prefix(_unary_op("asc", _asc_doc))
+    desc = ignore_unicode_prefix(_unary_op("desc", _desc_doc))
 
     _isNull_doc = """
-    True if the current expression is null. Often combined with
-    :func:`DataFrame.filter` to select rows with null values.
+    True if the current expression is null.
 
     >>> from pyspark.sql import Row
-    >>> df2 = sc.parallelize([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)]).toDF()
+    >>> df2 = spark.createDataFrame([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)])
     >>> df2.filter(df2.height.isNull()).collect()
     [Row(height=None, name=u'Alice')]
     """
     _isNotNull_doc = """
-    True if the current expression is null. Often combined with
-    :func:`DataFrame.filter` to select rows with non-null values.
+    True if the current expression is NOT null.
 
     >>> from pyspark.sql import Row
-    >>> df2 = sc.parallelize([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)]).toDF()
+    >>> df2 = spark.createDataFrame([Row(name=u'Tom', height=80), Row(name=u'Alice', height=None)])
     >>> df2.filter(df2.height.isNotNull()).collect()
     [Row(height=80, name=u'Tom')]
     """
@@ -527,7 +584,7 @@ def _test():
         .appName("sql.column tests")\
         .getOrCreate()
     sc = spark.sparkContext
-    globs['sc'] = sc
+    globs['spark'] = spark
     globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')]) \
         .toDF(StructType([StructField('age', IntegerType()),
                           StructField('name', StringType())]))

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitwiseExpressions.scala

@@ -86,7 +86,7 @@ case class BitwiseOr(left: Expression, right: Expression) extends BinaryArithmet
 }
 
 /**
- * A function that calculates bitwise xor of two numbers.
+ * A function that calculates bitwise xor({@literal ^}) of two numbers.
  *
  * Code generation inherited from BinaryArithmetic.
  */

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

@@ -779,15 +779,16 @@ class Column(val expr: Expression) extends Logging {
   def isin(list: Any*): Column = withExpr { In(expr, list.map(lit(_).expr)) }
 
   /**
-   * SQL like expression.
+   * SQL like expression. Returns a boolean column based on a SQL LIKE match.
    *
    * @group expr_ops
    * @since 1.3.0
    */
   def like(literal: String): Column = withExpr { Like(expr, lit(literal).expr) }
 
   /**
-   * SQL RLIKE expression (LIKE with Regex).
+   * SQL RLIKE expression (LIKE with Regex). Returns a boolean column based on a regex
+   * match.
    *
    * @group expr_ops
    * @since 1.3.0
@@ -838,39 +839,39 @@ class Column(val expr: Expression) extends Logging {
   }
 
   /**
-   * Contains the other element.
+   * Contains the other element. Returns a boolean column based on a string match.
    *
    * @group expr_ops
    * @since 1.3.0
    */
   def contains(other: Any): Column = withExpr { Contains(expr, lit(other).expr) }
 
   /**
-   * String starts with.
+   * String starts with. Returns a boolean column based on a string match.
    *
    * @group expr_ops
    * @since 1.3.0
    */
   def startsWith(other: Column): Column = withExpr { StartsWith(expr, lit(other).expr) }
 
   /**
-   * String starts with another string literal.
+   * String starts with another string literal. Returns a boolean column based on a string match.
    *
    * @group expr_ops
    * @since 1.3.0
    */
   def startsWith(literal: String): Column = this.startsWith(lit(literal))
 
   /**
-   * String ends with.
+   * String ends with. Returns a boolean column based on a string match.
    *
    * @group expr_ops
    * @since 1.3.0
    */
   def endsWith(other: Column): Column = withExpr { EndsWith(expr, lit(other).expr) }
 
   /**
-   * String ends with another string literal.
+   * String ends with another string literal. Returns a boolean column based on a string match.
    *
    * @group expr_ops
    * @since 1.3.0
@@ -1008,7 +1009,7 @@ class Column(val expr: Expression) extends Logging {
   def cast(to: String): Column = cast(CatalystSqlParser.parseDataType(to))
 
   /**
-   * Returns an ordering used in sorting.
+   * Returns a descending ordering used in sorting.
    * {{{
    *   // Scala
    *   df.sort(df("age").desc)
@@ -1083,7 +1084,7 @@ class Column(val expr: Expression) extends Logging {
   def asc_nulls_first: Column = withExpr { SortOrder(expr, Ascending, NullsFirst, Set.empty) }
 
   /**
-   * Returns an ordering used in sorting, where null values appear after non-null values.
+   * Returns an ascending ordering used in sorting, where null values appear after non-null values.
    * {{{
    *   // Scala: sort a DataFrame by age column in ascending order and null values appearing last.
    *   df.sort(df("age").asc_nulls_last)