Support SBT 1.xx and latest databricks

build.sbt

@@ -1,41 +1,36 @@
 name := "spark-tree-plotting"
 
-version := "0.2"
+version := "0.3"
 
-scalaVersion := "2.11.12"
+scalaVersion := "2.12.10"
 
-libraryDependencies += "net.liftweb" % "lift-json_2.11" % "3.3.0"
-
-
-assemblyShadeRules in assembly := Seq(
-    ShadeRule.rename("net.liftweb.json.**" -> "org.lift.web.library.json.@1").inAll
+libraryDependencies ++= Seq(
+  "net.liftweb" % "lift-json_2.12" % "3.5.0",
+  "org.apache.spark" % "spark-core_2.12" % "3.1.0" % "provided",
+  "org.apache.spark" % "spark-mllib_2.12" % "3.1.0" % "provided"
 )
 
-// Spark Packages config
-spName := "julioasotodv/spark-tree-plotting"
-
-sparkVersion := "2.3.2"
-
-sparkComponents += "mllib"
-
-credentials += Credentials(Path.userHome / ".ivy2" / ".sbtcredentials")
+lazy val spShortDescription = "A simple tool for plotting Spark ML's Decision Trees"
 
-spShortDescription := "A simple tool for plotting Spark ML's Decision Trees"
-
-spDescription := """This module provides a simple tool for plotting an easy to understand graphical representation
+lazy val spDescription = """This module provides a simple tool for plotting an easy to understand graphical representation
                     |of Spark ML's DecisionTreeClassificationModels, very similar to the one Python's Scikit-Learn provides.
                     |Given a DecisionTreeClassificationModel, spark_tree_plotting generates a JSON file with 
                     |the relevant metadata in order to plot the tree. Moreover, a simple JSON-to-DOT python
                     |script allows you to plot trees in PySpark in a very simple manner (just as in Scikit-Learn)""".stripMargin
 
 licenses += "MIT" -> url("https://opensource.org/licenses/MIT")
 
-spIncludeMaven := false
-
-
 // Resulting name for the assembly jar
-assemblyJarName in assembly := "spark-tree-plotting_0.2.jar"
+assembly / assemblyJarName := { name.value + "-assembly-" + version.value + ".jar" }
 
 // Do not include the Scala library itself in the jar 
-assemblyOption in assembly := (assemblyOption in assembly).value.copy(includeScala = false)
-
+assembly / assemblyOption := (assembly / assemblyOption).value.withIncludeScala(false)
+
+assemblyMergeStrategy := {
+  case m if m.toLowerCase.endsWith("manifest.mf") => MergeStrategy.discard
+  case m if m.toLowerCase.matches("meta-inf.*\\.sf$") => MergeStrategy.discard
+  case "log4j.properties" => MergeStrategy.discard
+  case m if m.toLowerCase.startsWith("meta-inf/services/") => MergeStrategy.filterDistinctLines
+  case "reference.conf" => MergeStrategy.concat
+  case _ => MergeStrategy.first
+}

project/assembly.sbt

@@ -1,3 +1,3 @@
 resolvers += Resolver.sbtPluginRepo("releases")
 
-addSbtPlugin("com.eed3si9n" %% "sbt-assembly" % "0.14.4")
+addSbtPlugin("com.eed3si9n" %% "sbt-assembly" % "1.0.0")

project/build.properties

@@ -1 +1 @@
-sbt.version=0.13.17
+sbt.version=1.6.2

python/spark_tree_plotting/README.md

@@ -0,0 +1,9 @@
+A Simple tool for plotting Spark ML's Decision Trees
+--
+If you like to use API, you can install the package
+
+python setup.py install
+
+Create wheel package
+--
+python setup.py bdist_wheel

python/spark_tree_plotting/setup.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Appreciatively cargo-culted from: https://github.com/kennethreitz/setup.py 
+
+# Note: To use the 'upload' functionality of this file, you must:
+#   $ pip install twine
+
+import io
+import os
+import sys
+from shutil import rmtree
+
+from setuptools import find_packages, setup, Command
+
+# Package meta-data.
+NAME = 'spark_tree_plotting'
+DESCRIPTION = 'A simple tool for plotting Spark ML Decision Trees'
+URL = 'https://github.com/julioasotodv/spark-tree-plotting'
+EMAIL = '[email protected]'
+AUTHOR = 'Julio Antonio Soto'
+
+# What packages are required for this module to be executed?
+REQUIRED = [
+    'pydot'
+]
+
+# The rest you shouldn't have to touch too much :)
+# ------------------------------------------------
+# Except, perhaps the License and Trove Classifiers!
+# If you do change the License, remember to change the Trove Classifier for that!
+
+here = os.path.abspath(os.path.dirname(__file__))
+
+# Import the README and use it as the long-description.
+# Note: this will only work if 'README.md' is present in your MANIFEST.in file!
+with io.open(os.path.join(here, 'README.md'), encoding='utf-8') as f:
+    long_description = '\n' + f.read()
+
+# Load the package's __version__.py module as a dictionary.
+about = {}
+with open(os.path.join(here, NAME, '__version__.py')) as f:
+    exec(f.read(), about)
+
+
+class UploadCommand(Command):
+    """Support setup.py upload."""
+
+    description = 'Build and publish the package.'
+    user_options = []
+
+    @staticmethod
+    def status(s):
+        """Prints things in bold."""
+        print('\033[1m{0}\033[0m'.format(s))
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        try:
+            self.status('Removing previous builds…')
+            rmtree(os.path.join(here, 'dist'))
+        except OSError:
+            pass
+
+        self.status('Building Source and Wheel (universal) distribution…')
+        os.system('{0} setup.py sdist bdist_wheel --universal'.format(sys.executable))
+
+        self.status('Uploading the package to PyPi via Twine…')
+        os.system('twine upload dist/*')
+
+        sys.exit()
+
+
+# Where the magic happens:
+setup(
+    name=NAME,
+    version=about['__version__'],
+    description=DESCRIPTION,
+    long_description=long_description,
+    author=AUTHOR,
+    author_email=EMAIL,
+    url=URL,
+    packages=find_packages(exclude=('tests',)),
+    # If your package is a single module, use this instead of 'packages':
+    # py_modules=['mypackage'],
+
+    # entry_points={
+    #     'console_scripts': ['mycli=mymodule:cli'],
+    # },
+
+    test_suite = 'spark_tree_plotting.tests',
+
+    install_requires=REQUIRED,
+    include_package_data=True,
+    license='Apache Software License',
+    classifiers=[
+        # Trove classifiers
+        # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
+        'License :: OSI Approved :: Apache Software License',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: Implementation :: CPython',
+        'Programming Language :: Python :: Implementation :: PyPy',
+        'Development Status :: 3 - Alpha',
+        'Topic :: Scientific/Engineering',
+    ],
+    # $ setup.py publish support.
+    cmdclass={
+        'upload': UploadCommand,
+    },
+)

python/spark_tree_plotting/spark_tree_plotting/__version__.py

@@ -0,0 +1 @@
+__version__ = '0.3.0'

python/spark_tree_plotting.py → python/spark_tree_plotting/spark_tree_plotting/spark_tree_plotting.py

@@ -424,7 +424,7 @@ def plot_tree(DecisionTreeClassificationModel, featureNames=None, categoryNames=
         from pydot import graph_from_dot_data
     except ImportError:
         raise ImportError(
-            "This function requires pydot3 dot be installed. You can easily install it with pip install pydot3"
+            "This function requires pydot dot be installed. You can easily install it with pip install pydot"
             )
 
     graph = graph_from_dot_data(export_graphviz(DecisionTreeClassificationModel,
@@ -441,4 +441,4 @@ def plot_tree(DecisionTreeClassificationModel, featureNames=None, categoryNames=
     else:
         plot = graph.create_png()
     return plot
-
+