Skip to content

[SPARK-40012][PYTHON][DOCS] Make pyspark.sql.dataframe examples self-contained (Part 1) #37444

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

Closed
Transurgeon wants to merge 8 commits into from
Closed

[SPARK-40012][PYTHON][DOCS] Make pyspark.sql.dataframe examples self-contained (Part 1) #37444

Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
380149f
adding self-contained examples for pyspark dataframe
Transurgeon Aug 9, 2022
1fed3ca
adding additional self-contained examples for dataframe API
Transurgeon Aug 9, 2022
24c4769
splitting instantion of df to two lines to avoid overflow of example …
Transurgeon Aug 23, 2022
60605d3
Apply suggestions from code review
Transurgeon Aug 25, 2022
1ce9604
adding descriptions and removing duplicate dataframe initialisations
Transurgeon Aug 25, 2022
096ab81
Merge branch 'master' into master
Transurgeon Aug 25, 2022
dfa5726
running python lint and reformat
Transurgeon Aug 26, 2022
aadf3d0
making some additional small detail changes
Transurgeon Aug 26, 2022
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
219 changes: 183 additions & 36 deletions python/pyspark/sql/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,9 +363,17 @@ def schema(self) -> StructType:

Examples
Comment thread
HyukjinKwon marked this conversation as resolved.
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.schema
Comment thread
Transurgeon marked this conversation as resolved.
StructType([StructField('age', IntegerType(), True),
StructField('name', StringType(), True)])
StructType([StructField('age', LongType(), True), StructField('name', StringType(), True)])
Comment thread
Transurgeon marked this conversation as resolved.
Outdated
"""
if self._schema is None:
try:
Expand Down Expand Up @@ -571,29 +579,41 @@ def show(self, n: int = 20, truncate: Union[bool, int] = True, vertical: bool =

Examples
--------
>>> df
DataFrame[age: int, name: string]
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 2|Alice|
| 5| Bob|
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.show(2)
Comment thread
Transurgeon marked this conversation as resolved.
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
+---+-----+
only showing top 2 rows
>>> df.show(truncate=3)
+---+----+
|age|name|
+---+----+
| 2| Ali|
| 5| Bob|
| 14| Tom|
| 23| Ali|
| 16| Bob|
+---+----+
>>> df.show(vertical=True)
-RECORD 0-----
age | 2
name | Alice
age | 14
name | Tom
-RECORD 1-----
age | 5
name | Bob
age | 23
name | Alice
-RECORD 2-----
age | 16
name | Bob
"""

if not isinstance(n, int) or isinstance(n, bool):
Expand Down Expand Up @@ -798,8 +818,18 @@ def count(self) -> int:

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+

>>> df.count()
Comment thread
Transurgeon marked this conversation as resolved.
2
3
"""
return int(self._jdf.count())

Expand Down Expand Up @@ -862,8 +892,17 @@ def take(self, num: int) -> List[Row]:

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.take(2)
Comment thread
Transurgeon marked this conversation as resolved.
[Row(age=2, name='Alice'), Row(age=5, name='Bob')]
[Row(age=14, name='Tom'), Row(age=23, name='Alice')]
"""
return self.limit(num).collect()

Expand All @@ -878,8 +917,17 @@ def tail(self, num: int) -> List[Row]:

Examples
--------
>>> df.tail(1)
[Row(age=5, name='Bob')]
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.tail(2)
[Row(age=23, name='Alice'), Row(age=16, name='Bob')]
"""
with SCCallSiteSync(self._sc):
sock_info = self._jdf.tailToPython(num)
Expand Down Expand Up @@ -1179,6 +1227,16 @@ def distinct(self) -> "DataFrame":

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (23, "Alice")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 23|Alice|
+---+-----+

>>> df.distinct().count()
Comment thread
Transurgeon marked this conversation as resolved.
2
"""
Expand Down Expand Up @@ -1375,8 +1433,17 @@ def dtypes(self) -> List[Tuple[str, str]]:

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
+---+-----+

>>> df.dtypes
Comment thread
Transurgeon marked this conversation as resolved.
[('age', 'int'), ('name', 'string')]
[('age', 'bigint'), ('name', 'string')]
"""
return [(str(f.name), f.dataType.simpleString()) for f in self.schema.fields]

Expand Down Expand Up @@ -2743,7 +2810,17 @@ def fillna(

Examples
--------
>>> df4.na.fill(50).show()
>>> df = spark.createDataFrame([(10, 80, "Alice"), (5, None, "Bob"), (None, None, "Tom"), (None, None, None)], ["age", "height", "name"])
>>> df.show()
+----+------+-----+
| age|height| name|
+----+------+-----+
| 10| 80|Alice|
| 5| null| Bob|
|null| null| Tom|
|null| null| null|
+----+------+-----+
>>> df.na.fill(50).show()
Comment thread
Transurgeon marked this conversation as resolved.
+---+------+-----+
|age|height| name|
+---+------+-----+
Expand All @@ -2753,7 +2830,16 @@ def fillna(
| 50| 50| null|
+---+------+-----+

>>> df5.na.fill(False).show()
>>> df = spark.createDataFrame([(10, "Alice", None), (5, "Bob", None), (None, "Mallory", True)], ["age", "name", "spy"])
>>> df.show()
+----+-------+----+
| age| name| spy|
+----+-------+----+
| 10| Alice|null|
| 5| Bob|null|
|null|Mallory|true|
+----+-------+----+
>>> df.na.fill(False).show()
Comment thread
Transurgeon marked this conversation as resolved.
+----+-------+-----+
| age| name| spy|
+----+-------+-----+
Expand All @@ -2762,7 +2848,17 @@ def fillna(
|null|Mallory| true|
+----+-------+-----+

>>> df4.na.fill({'age': 50, 'name': 'unknown'}).show()
>>> df = spark.createDataFrame([(10, 80, "Alice"), (5, None, "Bob"), (None, None, "Tom"), (None, None, None)], ["age", "height", "name"])
>>> df.show()
+----+------+-----+
| age|height| name|
+----+------+-----+
| 10| 80|Alice|
| 5| null| Bob|
|null| null| Tom|
|null| null| null|
+----+------+-----+
>>> df.na.fill({'age': 50, 'name': 'unknown'}).show()
+---+------+-------+
|age|height| name|
+---+------+-------+
Expand Down Expand Up @@ -2869,7 +2965,17 @@ def replace( # type: ignore[misc]

Examples
--------
>>> df4.na.replace(10, 20).show()
>>> df = spark.createDataFrame([(10, 80, "Alice"), (5, None, "Bob"), (None, None, "Tom"), (None, None, None)], ["age", "height", "name"])
>>> df.show()
+----+------+-----+
| age|height| name|
+----+------+-----+
| 10| 80|Alice|
| 5| null| Bob|
|null| null| Tom|
|null| null| null|
+----+------+-----+
>>> df.na.replace(10, 20).show()
Comment thread
Transurgeon marked this conversation as resolved.
+----+------+-----+
| age|height| name|
+----+------+-----+
Expand All @@ -2879,17 +2985,19 @@ def replace( # type: ignore[misc]
|null| null| null|
+----+------+-----+

>>> df4.na.replace('Alice', None).show()
+----+------+----+
| age|height|name|
+----+------+----+
| 10| 80|null|
| 5| null| Bob|
|null| null| Tom|
|null| null|null|
+----+------+----+
Replace all instances of Alice to null

>>> df4.na.replace({'Alice': None}).show()
>>> df = spark.createDataFrame([(10, 80, "Alice"), (5, None, "Bob"), (None, None, "Tom"), (None, None, None)], ["age", "height", "name"])
>>> df.show()
+----+------+-----+
| age|height| name|
+----+------+-----+
| 10| 80|Alice|
| 5| null| Bob|
|null| null| Tom|
|null| null| null|
+----+------+-----+
>>> df.na.replace('Alice', None).show()
+----+------+----+
| age|height|name|
+----+------+----+
Expand All @@ -2899,7 +3007,19 @@ def replace( # type: ignore[misc]
|null| null|null|
+----+------+----+

>>> df4.na.replace(['Alice', 'Bob'], ['A', 'B'], 'name').show()
Replace all instances of Alice to 'A' and Bob to 'B' under the name column

>>> df = spark.createDataFrame([(10, 80, "Alice"), (5, None, "Bob"), (None, None, "Tom"), (None, None, None)], ["age", "height", "name"])
>>> df.show()
+----+------+-----+
| age|height| name|
+----+------+-----+
| 10| 80|Alice|
| 5| null| Bob|
|null| null| Tom|
|null| null| null|
+----+------+-----+
>>> df.na.replace(['Alice', 'Bob'], ['A', 'B'], 'name').show()
+----+------+----+
| age|height|name|
+----+------+----+
Expand Down Expand Up @@ -3356,11 +3476,29 @@ def drop(self, *cols: "ColumnOrName") -> "DataFrame": # type: ignore[misc]

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.drop('age').collect()
Comment thread
Transurgeon marked this conversation as resolved.
Outdated
[Row(name='Alice'), Row(name='Bob')]
[Row(name='Tom'), Row(name='Alice'), Row(name='Bob')]

>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.drop(df.age).collect()
[Row(name='Alice'), Row(name='Bob')]
[Row(name='Tom'), Row(name='Alice'), Row(name='Bob')]

>>> df.join(df2, df.name == df2.name, 'inner').drop(df.name).collect()

@Transurgeon Transurgeon Aug 23, 2022

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not sure what these 3 inner joins do exactly. I dont see anywhere an instantiation of df2..

What should I do with these 3 examples?

@HyukjinKwon HyukjinKwon Aug 23, 2022

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's showing a common example that join and drop the join key.

[Row(age=5, height=85, name='Bob')]
Expand Down Expand Up @@ -3393,12 +3531,21 @@ def toDF(self, *cols: "ColumnOrName") -> "DataFrame":
Parameters
----------
cols : str
new column names
new column names. The length of the list needs to be the same as the number of columns in the initial DataFrame
Comment thread
Transurgeon marked this conversation as resolved.
Outdated

Examples
--------
>>> df = spark.createDataFrame([(14, "Tom"), (23, "Alice"), (16, "Bob")], ["age", "name"])
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 14| Tom|
| 23|Alice|
| 16| Bob|
+---+-----+
>>> df.toDF('f1', 'f2').collect()
[Row(f1=2, f2='Alice'), Row(f1=5, f2='Bob')]
[Row(f1=14, f2='Tom'), Row(f1=23, f2='Alice'), Row(f1=16, f2='Bob')]
"""
jdf = self._jdf.toDF(self._jseq(cols))
return DataFrame(jdf, self.sparkSession)
Expand Down