graphframes · rjurney · Dec 25, 2024 · Dec 25, 2024 · Dec 25, 2024 · Dec 25, 2024
diff --git a/.github/workflows/python-ci.yml b/.github/workflows/python-ci.yml
@@ -7,8 +7,8 @@ jobs:
       matrix:
         include:
           - spark-version: 3.5.4
-            scala-version: 2.12.18
-            python-version: 3.9.19
+            scala-version: 2.12.20
+            python-version: 3.11.11
     runs-on: ubuntu-22.04
     env:
       # define Java options for both official sbt and sbt-extras
@@ -35,8 +35,11 @@ jobs:
       run: |
         python -m pip install --upgrade pip wheel
         pip install -r ./python/requirements.txt
+        pip install -r ./python/requirements-dev.txt
         pip install pyspark==${{ matrix.spark-version }}
     - name: Test
       run: |
+        python python/setup.py install
+        python python/setup.py bdist_wheel
         export SPARK_HOME=$(python -c "import os; from importlib.util import find_spec; print(os.path.join(os.path.dirname(find_spec('pyspark').origin)))")
         ./python/run-tests.sh
diff --git a/.gitignore b/.gitignore
@@ -26,3 +26,13 @@ project/plugins/project/
 
 # Mac
 *.DS_Store
+.vscode
+
+# Python specific
+python/build
+python/dist
+build/lib
+python/graphframes.egg-info
+python/graphframes/tutorials/data
+python/docs/_build
+python/docs/_site
diff --git a/Dockerfile b/Dockerfile
@@ -1,16 +1,16 @@
 FROM ubuntu:22.04
 
-ARG PYTHON_VERSION=3.8
+ARG PYTHON_VERSION=3.9
 ARG DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && \
-    apt-get install -y wget bzip2 build-essential openjdk-8-jdk ssh sudo && \
+    apt-get install -y wget bzip2 build-essential openjdk-11-jdk ssh sudo && \
     apt-get clean
 
 # Install Spark and update env variables.
-ENV SCALA_VERSION 2.12.17
-ENV SPARK_VERSION "3.4.1"
-ENV SPARK_BUILD "spark-${SPARK_VERSION}-bin-hadoop3.2"
+ENV SCALA_VERSION 2.12.20
+ENV SPARK_VERSION "3.5.4"
+ENV SPARK_BUILD "spark-${SPARK_VERSION}-bin-hadoop3"
 ENV SPARK_BUILD_URL "https://dist.apache.org/repos/dist/release/spark/spark-${SPARK_VERSION}/${SPARK_BUILD}.tgz"
 RUN wget --quiet "$SPARK_BUILD_URL" -O /tmp/spark.tgz && \
     tar -C /opt -xf /tmp/spark.tgz && \

diff --git a/README.md b/README.md
@@ -6,34 +6,165 @@
 
 # GraphFrames: DataFrame-based Graphs
 
-This is a package for DataFrame-based graphs on top of Apache Spark.
-Users can write highly expressive queries by leveraging the DataFrame API, combined with a new
-API for motif finding.  The user also benefits from DataFrame performance optimizations
-within the Spark SQL engine.
+This is a package for DataFrame-based graphs on top of Apache Spark. Users can write highly expressive queries by leveraging the DataFrame API, combined with a new API for network motif finding. The user also benefits from DataFrame performance optimizations within the Spark SQL engine. GraphFrames works in Java, Scala, and Python.
 
-You can find user guide and API docs at https://graphframes.github.io/graphframes.
+You can find user guide and API docs at https://graphframes.github.io/graphframes
+
+## Installation and Quick-Start
+
+The easiest way to start using GraphFrames is through the [Spark Packages system](https://spark-packages.org/package/graphframes/graphframes). Just run the following command:
+
+```bash
+# Interactive Scala/Java
+$ spark-shell --packages graphframes:graphframes:0.8.3-spark3.5-s_2.12
+
+# Interactive Python
+$ pyspark --packages graphframes:graphframes:0.8.3-spark3.5-s_2.12
+
+# Submit a script in Scala/Java/Python
+$ spark-submit --packages graphframes:graphframes:0.8.3-spark3.5-s_2.12 script.py
+```
+
+Now you can create a GraphFrame as follows.
+
+In Python:
+
+```python
+from pyspark.sql import SparkSession
+from graphframes import GraphFrame
+
+spark = SparkSession.builder.getOrCreate()
+
+nodes = [
+    (1, "Alice", 30),
+    (2, "Bob", 25),
+    (3, "Charlie", 35)
+]
+nodes_df = spark.createDataFrame(nodes, ["id", "name", "age"])
+
+edges = [
+    (1, 2, "friend"),
+    (2, 1, "friend"),
+    (2, 3, "friend"),
+    (3, 2, "enemy")  # eek!
+]
+edges_df = spark.createDataFrame(edges, ["src", "dst", "relationship"])
+
+g = GraphFrame(nodes_df, edges_df)
+```
+
+Now let's run some graph algorithms at scale!
+
+```python
+g.inDegrees.show()
+
+# +---+--------+
+# | id|inDegree|
+# +---+--------+
+# |  2|       2|
+# |  1|       1|
+# |  3|       1|
+# +---+--------+
+
+g.outDegrees.show()
+
+# +---+---------+
+# | id|outDegree|
+# +---+---------+
+# |  1|        1|
+# |  2|        2|
+# |  3|        1|
+# +---+---------+
+
+g.degrees.show()
+
+# +---+------+
+# | id|degree|
+# +---+------+
+# |  1|     2|
+# |  2|     4|
+# |  3|     2|
+# +---+------+
+
+g2 = g.pageRank(resetProbability=0.15, tol=0.01)
+g2.vertices.show()
+
+# +---+-----+---+------------------+
+# | id| name|age|          pagerank|
+# +---+-----+---+------------------+
+# |  1| John| 30|0.7758750474847483|
+# |  2|Alice| 25|1.4482499050305027|
+# |  3|  Bob| 35|0.7758750474847483|
+# +---+-----+---+------------------+
+
+# GraphFrames' most used feature...
+# Connected components can do big data entity resolution on billions or even trillions of records!
+# First connect records with a similarity metric, then run connectedComponents.
+# This gives you groups of identical records, which you then link by same_as edges or merge into list-based master records.
+sc.setCheckpointDir("/tmp/graphframes-example-connected-components")  # required by GraphFrames.connectedComponents
+g.connectedComponents().show()
+
+# +---+-----+---+---------+
+# | id| name|age|component|
+# +---+-----+---+---------+
+# |  1| John| 30|        1|
+# |  2|Alice| 25|        1|
+# |  3|  Bob| 35|        1|
+# +---+-----+---+---------+
+
+# Find frenemies with network motif finding! See how graph and relational queries are combined?
+(
+    g.find("(a)-[e]->(b); (b)-[e2]->(a)")
+    .filter("e.relationship = 'friend' and e2.relationship = 'enemy'")
+    .show()
+)
+
+# These are paths, which you can aggregate and count to find complex patterns.
+# +------------+--------------+----------------+-------------+
+# |           a|             e|               b|           e2|
+# +------------+--------------+----------------+-------------+
+# |{2, Bob, 25}|{2, 3, friend}|{3, Charlie, 35}|{3, 2, enemy}|
+# +------------+--------------+----------------+-------------+
+```
+
+## Learn GraphFrames
+
+To learn more about GraphFrames, check out these resources:
+
+* [GraphFrames Network Motif Finding Tutorial](https://graphframes.github.io/graphframes/docs/_site/motif-tutorial.html)
+* [Introducing GraphFrames](https://databricks.com/blog/2016/03/03/introducing-graphframes.html)
+* [On-Time Flight Performance with GraphFrames for Apache Spark](https://databricks.com/blog/2016/03/16/on-time-flight-performance-with-graphframes-for-apache-spark.html)
+
+## GraphFrames on PyPI is Unofficial
+
+The project is not in ownership or control of the [graphframes PyPI package](https://pypi.org/project/graphframes/) (installs 0.6.0) or [graphframes-latest PyPI package](https://pypi.org/project/graphframes-latest/) (installs 0.8.3). We recommend using the Spark Packages system to install the latest version of GraphFrames. The PyPI packages are not maintained by the GraphFrames project.
+
+If you are in control of one of these packages, please reach out to us to discuss how we can work together to keep them up to date. Hopefully this situation will be addressed in the near future.
+
+See [Installation and Quick-Start](#installation-and-quick-start) for the best way to install and use GraphFrames.
+
+## GraphFrames Internals
+
+To learn how GraphFrames works internally to combine graph and relational queries, check out the paper [GraphFrames: An Integrated API for Mixing Graph and
+Relational Queries, Dave et al. 2016](https://people.eecs.berkeley.edu/~matei/papers/2016/grades_graphframes.pdf).
 
 ## Building and running unit tests
 
-To compile this project, run `build/sbt assembly` from the project home directory.
-This will also run the Scala unit tests.
+To compile this project, run `build/sbt assembly` from the project home directory. This will also run the Scala unit tests.
 
-To run the Python unit tests, run the `run-tests.sh` script from the `python/` directory.
-You will need to set `SPARK_HOME` to your local Spark installation directory.
+To run the Python unit tests, run the `run-tests.sh` script from the `python/` directory. You will need to set `SPARK_HOME` to your local Spark installation directory.
 
 ## Release new version
+
 Please see guide `dev/release_guide.md`.
 
 ## Spark version compatibility
 
-This project is compatible with Spark 2.4+.  However, significant speed improvements have been
-made to DataFrames in more recent versions of Spark, so you may see speedups from using the latest
-Spark version.
+This project is compatible with Spark 2.4+.  However, significant speed improvements have been made to DataFrames in more recent versions of Spark, so you may see speedups from using the latest Spark version.
 
 ## Contributing
 
-GraphFrames is collaborative effort among UC Berkeley, MIT, and Databricks.
-We welcome open source contributions as well!
+GraphFrames is collaborative effort among UC Berkeley, MIT, Databricks and the open source community. We welcome open source contributions as well!
 
 ## Releases:
 

diff --git a/build.sbt b/build.sbt
@@ -3,7 +3,7 @@ import ReleaseTransformations._
 lazy val sparkVer = sys.props.getOrElse("spark.version", "3.5.4")
 lazy val sparkBranch = sparkVer.substring(0, 3)
 lazy val defaultScalaVer = sparkBranch match {
-  case "3.5" => "2.12.18"
+  case "3.5" => "2.12.20"
   case _ => throw new IllegalArgumentException(s"Unsupported Spark version: $sparkVer.")
 }
 lazy val scalaVer = sys.props.getOrElse("scala.version", defaultScalaVer)

diff --git a/dev/release_guide.md b/dev/release_guide.md
@@ -1,8 +1,8 @@
-# Guild for releasing a new Graphframe version
+# Guild for releasing a new Graphframes version
 
-## How to build GraphFrame package ?
+## How to build GraphFrames package ?
 
-To build a GraphFrame package for releasing, you only need to run the following command:
+To build a GraphFrames package for releasing, you only need to run the following command:
 
 ```
 cd graphframe_repo
@@ -30,10 +30,9 @@ then upload the zip file generated by instructions in "How to build GraphFrame p
 
 ## How to publish the GraphFrame doc ?
 
-GraphFrame doc is hosted in 'https://graphframes.github.io/graphframes/', to publish doc,
-you just need to build doc content, then push the doc content to gh-pages branch of https://github.com/graphframes/graphframes project.
+GraphFrames docs are hosted in 'https://graphframes.github.io/graphframes/'. To publish the docs, you just need to build the doc content, then push the doc content to gh-pages branch of the https://github.com/graphframes/graphframes project.
 
-Before building doc, you need to install jekyll, please refer to 'docs/README.md' for details.
+Before building the docs, you need to install jekyll, please refer to 'docs/README.md' for details.
 
 The following command is for building and publishing doc:
 ```

diff --git a/docs/README.md b/docs/README.md
@@ -1,28 +1,18 @@
 Welcome to the GraphFrames Spark Package documentation!
 
-This readme will walk you through navigating and building the GraphFrames documentation, which is
-included here with the source code.
+This readme will walk you through navigating and building the GraphFrames documentation, which is included here with the source code.
 
-Read on to learn more about viewing documentation in plain text (i.e., markdown) or building the
-documentation yourself. Why build it yourself? So that you have the docs that correspond to
-whichever version of GraphFrames you currently have checked out of revision control.
+Read on to learn more about viewing documentation in plain text (i.e., markdown) or building the documentation yourself. Why build it yourself? So that you have the docs that correspond to whichever version of GraphFrames you currently have checked out of revision control.
 
 ## Generating the Documentation HTML
 
-We include the GraphFrames documentation as part of the source (as opposed to using a hosted wiki, such as
-the github wiki, as the definitive documentation) to enable the documentation to evolve along with
-the source code and be captured by revision control (currently git). This way the code automatically
-includes the version of the documentation that is relevant regardless of which version or release
-you have checked out or downloaded.
+We include the GraphFrames documentation as part of the source (as opposed to using a hosted wiki, such as the github wiki, as the definitive documentation) to enable the documentation to evolve along with the source code and be captured by revision control (currently git). This way the code automatically
+includes the version of the documentation that is relevant regardless of which version or release you have checked out or downloaded.
 
-In this directory you will find textfiles formatted using Markdown, with an ".md" suffix. You can
-read those text files directly if you want. Start with index.md.
+In this directory you will find textfiles formatted using Markdown, with an ".md" suffix. You can read those text files directly if you want. Start with index.md.
 
 The markdown code can be compiled to HTML using the [Jekyll tool](http://jekyllrb.com).
-`Jekyll` and a few dependencies must be installed for this to work. We recommend
-installing via the Ruby Gem dependency manager. Since the exact HTML output
-varies between versions of Jekyll and its dependencies, we list specific versions here
-in some cases:
+`Jekyll` and a few dependencies must be installed for this to work. We recommend installing via the Ruby Gem dependency manager. Since the exact HTML output varies between versions of Jekyll and its dependencies, we list specific versions here in some cases:
 
     $ sudo gem install jekyll
     $ sudo gem install jekyll-redirect-from
@@ -32,8 +22,7 @@ On macOS, with the default Ruby, please install Jekyll with Bundler as [instruct
     $ sudo gem install jekyll bundler
     $ sudo gem install jekyll-redirect-from
 
-Execute `jekyll build` from the `docs/` directory to compile the site. Compiling the site with Jekyll will create a directory
-called `_site` containing index.html as well as the rest of the compiled files.
+Execute `jekyll build` from the `docs/` directory to compile the site. Compiling the site with Jekyll will create a directory called `_site` containing index.html as well as the rest of the compiled files.
 
 You can modify the default Jekyll build as follows:
 
@@ -45,27 +34,23 @@ You can modify the default Jekyll build as follows:
     $ PRODUCTION=1 jekyll build
 
 Note that `SPARK_HOME` must be set to your local Spark installation in order to generate the docs.
+
 To manually point to a specific `Spark` installation,
     $ SPARK_HOME=<your-path-to-spark-home> PRODUCTION=1 jekyll build
 
 ## Sphinx
 
 We use Sphinx to generate Python API docs, so you will need to install it by running
-`sudo pip install sphinx`.
+
+    sudo pip install sphinx
 
 ## API Docs (Scaladoc, Sphinx)
 
 You can build just the scaladoc by running `build/sbt unidoc` from the GRAPHFRAMES_PROJECT_ROOT directory.
 
-Similarly, you can build just the Python docs by running `make html` from the
-GRAPHFRAMES_PROJECT_ROOT/python/docs directory. Documentation is only generated for classes that are listed as
-public in `__init__.py`.
+Similarly, you can build just the Python docs by running `make html` from the GRAPHFRAMES_PROJECT_ROOT/python/docs directory. Documentation is only generated for classes that are listed as public in `__init__.py`.
 
-When you run `jekyll` in the `docs` directory, it will also copy over the scaladoc for the various
-subprojects into the `docs` directory (and then also into the `_site` directory). We use a
-jekyll plugin to run `build/sbt unidoc` before building the site so if you haven't run it (recently) it
-may take some time as it generates all of the scaladoc.  The jekyll plugin also generates the
+When you run `jekyll` in the `docs` directory, it will also copy over the scaladoc for the various subprojects into the `docs` directory (and then also into the `_site` directory). We use a jekyll plugin to run `build/sbt unidoc` before building the site so if you haven't run it (recently) it may take some time as it generates all of the scaladoc.  The jekyll plugin also generates the
 Python docs [Sphinx](http://sphinx-doc.org/).
 
-NOTE: To skip the step of building and copying over the Scala, Python API docs, run `SKIP_API=1
-jekyll build`. To skip building Scala API docs, run `SKIP_SCALADOC=1 jekyll build`; to skip building Python API docs, run `SKIP_PYTHONDOC=1 jekyll build`.
+NOTE: To skip the step of building and copying over the Scala, Python API docs, run `SKIP_API=1 jekyll build`. To skip building Scala API docs, run `SKIP_SCALADOC=1 jekyll build`; to skip building Python API docs, run `SKIP_PYTHONDOC=1 jekyll build`.
diff --git a/docs/_config.yml b/docs/_config.yml
@@ -13,7 +13,7 @@ include:
 
 # These allow the documentation to be updated with newer releases
 # of Spark, Scala, and Mesos.
-GRAPHFRAMES_VERSION: 0.8.4
+GRAPHFRAMES_VERSION: 0.8.5
 #SCALA_BINARY_VERSION: "2.10"
 #SCALA_VERSION: "2.10.4"
 #MESOS_VERSION: 0.21.0

diff --git a/docs/_layouts/global.html b/docs/_layouts/global.html
@@ -74,6 +74,7 @@
                             <ul class="dropdown-menu">
                                 <li><a href="quick-start.html">Quick Start</a></li>
                                 <li><a href="user-guide.html">GraphFrames User Guide</a></li>
+                                <li><a href="motif-tutorial.html">Network Motif Finding Tutorial</a></li>
                             </ul>
                         </li>
 

diff --git a/docs/img/4-node-directed-graphlets.png b/docs/img/4-node-directed-graphlets.png
diff --git a/docs/img/Directed-Graphlet-G17.png b/docs/img/Directed-Graphlet-G17.png
diff --git a/docs/img/Directed-Graphlet-G22.png b/docs/img/Directed-Graphlet-G22.png
diff --git a/docs/img/G11_motif.png b/docs/img/G11_motif.png
diff --git a/docs/img/G4_and_G5_directed_network_motif.png b/docs/img/G4_and_G5_directed_network_motif.png
diff --git a/docs/img/GraphFrames-Logo-Dark-Small.png b/docs/img/GraphFrames-Logo-Dark-Small.png
diff --git a/docs/img/GraphFrames-Logo-Large.png b/docs/img/GraphFrames-Logo-Large.png
diff --git a/docs/img/GraphFrames-Logo-Small.png b/docs/img/GraphFrames-Logo-Small.png
diff --git a/docs/img/directed_graphlets.webp b/docs/img/directed_graphlets.webp
diff --git a/docs/index.md b/docs/index.md
@@ -63,14 +63,21 @@ GraphFrames supplied as a package.
 * [Quick Start](quick-start.html): a quick introduction to the GraphFrames API; start here!
 * [GraphFrames User Guide](user-guide.html): detailed overview of GraphFrames
   in all supported languages (Scala, Java, Python)
+* [Motif Finding Tutorial](motif-tutorial.html): learn to perform pattern recognition with GraphFrames using a technique called network motif finding over the knowledge graph for the `stackexchange.com` subdomain [data dump](https://archive.org/details/stackexchange)
 
 **API Docs:**
 
 * [GraphFrames Scala API (Scaladoc)](api/scala/index.html#org.graphframes.package)
 * [GraphFrames Python API (Sphinx)](api/python/index.html)
 
+**Community Forums:**
+
+* [GraphFrames Mailing List](https://groups.google.com/g/graphframes/): ask questions about GraphFrames here
+* [#graphframes Discord Channel on GraphGeeks](https://discord.com/channels/1162999022819225631/1326257052368113674)
+
 **External Resources:**
 
 * [Apache Spark Homepage](http://spark.apache.org)
 * [Apache Spark Wiki](https://cwiki.apache.org/confluence/display/SPARK)
-* [Mailing Lists](http://spark.apache.org/mailing-lists.html): Ask questions about Spark here
+* [Apache Spark Mailing Lists](http://spark.apache.org/mailing-lists.html)
+* [GraphFrames on Stack Overflow](https://stackoverflow.com/questions/tagged/graphframes)