diff --git a/.gitignore b/.gitignore
index 678636a7b..693ffceca 100644
--- a/.gitignore
+++ b/.gitignore
@@ -79,4 +79,7 @@ target/
 *.ipynb.syncdoc
 .ipynb_checkpoints
 .ipython-daemon.json
-.cache
+
+.idea/
+.pybuilder/
+_SUCCESS
diff --git a/.travis.yml b/.travis.yml
index 33f91240d..0c0079ca5 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -10,7 +10,8 @@ python:
 install:
  - pip install --upgrade pip
  - "if [[ $TRAVIS_PYTHON_VERSION != 'pypy'* ]]; then pip install pylzma; fi"
- - "pip install .[test]"
+ - "pip install -r 'requirements-build.txt'"
 script:
  - pylint pysparkling
- - python -m pytest -vv
+ - pyb -X
+
diff --git a/build.py b/build.py
new file mode 100644
index 000000000..eed1f9d89
--- /dev/null
+++ b/build.py
@@ -0,0 +1,143 @@
+#   -*- coding: utf-8 -*-
+import logging
+from pathlib import Path
+
+from pybuilder.core import use_plugin, init, before, after, Author
+from pybuilder.errors import BuildFailedException
+
+use_plugin("python.core")
+use_plugin("python.flake8")
+use_plugin("python.distutils")
+# use_plugin("python.unittest")
+# use_plugin("python.coverage")
+# https://github.com/AlexeySanko/pybuilder_pytest
+# use_plugin('pypi:pybuilder_pytest')
+# https://github.com/AlexeySanko/pybuilder_pytest_coverage
+# use_plugin('pypi:pybuilder_pytest_coverage')
+
+
+def _get_pysparkling_version() -> str:
+    """Returns the pysparkling version based on the one mentioned in the __init__.py file under the package."""
+    from pathlib import Path
+    import re
+
+    with open(Path(__file__).parent / 'src/main/python/pysparkling/__init__.py') as fp:
+        version_line = next(l for l in fp if l.startswith('__version__'))
+        return re.search(r'=\s*(["\'])(.*)(\1)\s*$', version_line).group(2)
+
+
+name = "pysparkling"
+default_task = "publish"
+version = _get_pysparkling_version()
+license = 'MIT'
+summary = 'Pure Python implementation of the Spark RDD interface.'
+description = None
+authors = [
+    Author(name='Sven Kreiss', email='me@svenkreiss.com'),
+    Author(name="Erwan Guyomarc'h", email='tools4origins@gmail.com'),
+    Author(name='Steven Van Ingelgem', email='steven@vaningelgem.be'),
+]
+maintainers = [
+    Author(name="Erwan Guyomarc'h", email='tools4origins@gmail.com'),
+]
+requires_python = '>= 3.4'
+url = 'https://github.com/tools4origins/pysparkling'
+
+_logging_root_level: int = logging.root.getEffectiveLevel()
+
+
+@before('run_unit_tests')
+def _set_debug_mode():
+    logging.root.setLevel('DEBUG')
+
+
+@after('run_unit_tests')
+def _set_debug_mode_after():
+    logging.root.setLevel(_logging_root_level)
+
+
+@after('package')
+def _add_extras_require(project, logger):
+    indent_size = 4
+    encoding = 'utf-8'
+
+    setup_script = Path(project.expand_path("$dir_dist", "setup.py"))
+    logger.info("Adding 'extras_require' to setup.py")
+    setup = setup_script.read_text(encoding=encoding).rstrip()
+    if setup[-1] != ')':
+        raise BuildFailedException("This setup.py seems to be wrong?")
+
+    # Get the requirements-dev.txt file line by line, ready for insertion.
+    requirements_dev = '\n'.join(
+        ' '*4*indent_size + "'" + x.strip() + "',"
+        for x in (Path(__file__).parent / 'requirements-build.txt').read_text().split('\n')
+        if x
+    )
+
+    # TODO: find a nicer way to embed this!
+    new_setup = (
+        setup[:-1].rstrip()
+        + f"""
+        extras_require={{
+            'hdfs': ['hdfs>=2.0.0'],
+            'pandas': ['pandas>=0.23.2'],
+            'performance': ['matplotlib>=1.5.3'],
+            'streaming': ['tornado>=4.3'],
+            'test': [
+{requirements_dev}
+            ]
+        }},
+    )
+"""
+    )
+
+    setup_script.write_text(new_setup, encoding=encoding)
+
+
+@init
+def set_properties(project):
+    # Small tweak to project.list_scripts() as that method lists EVERYTHING in the scripts directory.
+    #   and we're only interested in *.py files:
+    old_project_list_scripts = project.list_scripts
+
+    def _my_list_scripts():
+        return [
+            filename
+            for filename in old_project_list_scripts()
+            if filename.lower().endswith('.py')
+        ]
+    setattr(project, 'list_scripts', _my_list_scripts)
+
+    project.depends_on_requirements(file='requirements.txt')
+
+    project.set_property('distutils_readme_description', True)
+    project.set_property('distutils_readme_file', 'README.rst')
+
+    project.set_property_if_unset("pytest_extra_args", [])
+    project.get_property("pytest_extra_args").append("-x")  # Fail on first failing unittest
+    project.set_property('pytest_coverage_break_build_threshold', 0)  # Don't let coverage break the build (for now)
+
+    project.set_property('distutils_console_scripts', [])
+    project.set_property(
+        'distutils_classifiers',
+        [
+            'Development Status :: 4 - Beta',
+            'Intended Audience :: Developers',
+            'Natural Language :: English',
+            'License :: OSI Approved :: MIT License',
+            'Operating System :: OS Independent',
+            'Programming Language :: Python',
+            'Programming Language :: Python :: 3.4',
+            'Programming Language :: Python :: 3.5',
+            'Programming Language :: Python :: 3.6',
+            'Programming Language :: Python :: 3.7',
+            'Programming Language :: Python :: 3.8',
+            'Programming Language :: Python :: 3.9',
+            'Programming Language :: Python :: Implementation :: PyPy',
+        ]
+    )
+
+
+if __name__ == '__main__':
+    from pybuilder.cli import main
+    main('-CX', '--no-venvs')
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 000000000..950f54989
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,3 @@
+[build-system]
+requires = ["pybuilder>=0.12.0"]
+build-backend = "pybuilder.pep517"
diff --git a/pysparkling/tests/pyspark/key_value.txt.bz2/_SUCCESS b/pysparkling/tests/pyspark/key_value.txt.bz2/_SUCCESS
deleted file mode 100644
index e69de29bb..000000000
diff --git a/pysparkling/tests/pyspark/key_value.txt.gz/_SUCCESS b/pysparkling/tests/pyspark/key_value.txt.gz/_SUCCESS
deleted file mode 100644
index e69de29bb..000000000
diff --git a/requirements-build.txt b/requirements-build.txt
new file mode 100644
index 000000000..f5ebc02d0
--- /dev/null
+++ b/requirements-build.txt
@@ -0,0 +1,8 @@
+backports.tempfile==1.0rc1
+cloudpickle>=0.1.0
+futures>=3.0.1
+pylint>=2.3,<2.6
+memory_profiler>=0.47
+pytest
+tornado>=4.3
+pybuilder
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 000000000..757301857
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,5 @@
+boto>=2.36.0
+future>=0.15
+requests>=2.6.0
+pytz>=2019.3
+python-dateutil>=2.8.0
diff --git a/setup.cfg b/setup.cfg
index 3ded2f1dc..f23707245 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
 [flake8]
 ignore = H301
-exclude = venv*,logo,docs,build
+exclude = venv*,logo,docs,build,target
 
 [tool:pytest]
 addopts = --doctest-modules
diff --git a/setup.py b/setup.py
deleted file mode 100644
index 0c692dba7..000000000
--- a/setup.py
+++ /dev/null
@@ -1,69 +0,0 @@
-from setuptools import setup, find_packages
-
-# workaround: nosetests don't exit cleanly with older
-# python version (<=2.6 and even <2.7.4)
-try:
-    import multiprocessing  # noqa
-except ImportError:
-    pass
-
-
-# extract version from __init__.py
-with open('pysparkling/__init__.py', 'r') as f:
-    version_line = [l for l in f if l.startswith('__version__')][0]
-    VERSION = version_line.split('=')[1].strip()[1:-1]
-
-
-setup(
-    name='pysparkling',
-    version=VERSION,
-    packages=find_packages(),
-    license='MIT',
-    description='Pure Python implementation of the Spark RDD interface.',
-    long_description=open('README.rst').read(),
-    author='Sven Kreiss',
-    author_email='me@svenkreiss.com',
-    url='https://github.com/svenkreiss/pysparkling',
-
-    install_requires=[
-        'boto>=2.36.0',
-        'future>=0.15',
-        'requests>=2.6.0',
-        'pytz>=2019.3',
-        'python-dateutil>=2.8.0'
-    ],
-    extras_require={
-        'hdfs': ['hdfs>=2.0.0'],
-        'pandas': ['pandas>=0.23.2'],
-        'performance': ['matplotlib>=1.5.3'],
-        'streaming': ['tornado>=4.3'],
-        'test': [
-            'backports.tempfile==1.0rc1',
-            'cloudpickle>=0.1.0',
-            'futures>=3.0.1',
-            'pylint>=2.3,<2.6',
-            'memory-profiler>=0.47',
-            'pytest',
-            'tornado>=4.3',
-        ]
-    },
-    entry_points={
-        'console_scripts': [],
-    },
-
-    classifiers=[
-        'Development Status :: 4 - Beta',
-        'Intended Audience :: Developers',
-        'Natural Language :: English',
-        'License :: OSI Approved :: MIT License',
-        'Operating System :: OS Independent',
-        'Programming Language :: Python',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
-        'Programming Language :: Python :: 3.8',
-        'Programming Language :: Python :: 3.9',
-        'Programming Language :: Python :: Implementation :: PyPy',
-    ]
-)
diff --git a/pysparkling/__init__.py b/src/main/python/pysparkling/__init__.py
similarity index 100%
rename from pysparkling/__init__.py
rename to src/main/python/pysparkling/__init__.py
diff --git a/pysparkling/accumulators.py b/src/main/python/pysparkling/accumulators.py
similarity index 100%
rename from pysparkling/accumulators.py
rename to src/main/python/pysparkling/accumulators.py
diff --git a/pysparkling/broadcast.py b/src/main/python/pysparkling/broadcast.py
similarity index 100%
rename from pysparkling/broadcast.py
rename to src/main/python/pysparkling/broadcast.py
diff --git a/pysparkling/cache_manager.py b/src/main/python/pysparkling/cache_manager.py
similarity index 100%
rename from pysparkling/cache_manager.py
rename to src/main/python/pysparkling/cache_manager.py
diff --git a/pysparkling/context.py b/src/main/python/pysparkling/context.py
similarity index 100%
rename from pysparkling/context.py
rename to src/main/python/pysparkling/context.py
index 851903010..7541e572f 100644
--- a/pysparkling/context.py
+++ b/src/main/python/pysparkling/context.py
@@ -3,17 +3,17 @@
 from __future__ import (absolute_import, division, print_function,
                         unicode_literals)
 
-from collections import defaultdict
 import itertools
 import logging
 import pickle
 import struct
 import time
 import traceback
+from collections import defaultdict
 
 from . import __version__ as PYSPARKLING_VERSION
-from .broadcast import Broadcast
 from . import accumulators
+from .broadcast import Broadcast
 from .cache_manager import CacheManager
 from .exceptions import ContextIsLockedException
 from .fileio import File, TextFile
diff --git a/pysparkling/exceptions.py b/src/main/python/pysparkling/exceptions.py
similarity index 100%
rename from pysparkling/exceptions.py
rename to src/main/python/pysparkling/exceptions.py
diff --git a/pysparkling/fileio/__init__.py b/src/main/python/pysparkling/fileio/__init__.py
similarity index 99%
rename from pysparkling/fileio/__init__.py
rename to src/main/python/pysparkling/fileio/__init__.py
index ecc31675f..0cbb879a3 100644
--- a/pysparkling/fileio/__init__.py
+++ b/src/main/python/pysparkling/fileio/__init__.py
@@ -1,7 +1,8 @@
 from __future__ import absolute_import
-# flake8: noqa
 
 from .file import File
 from .textfile import TextFile
 
+# flake8: noqa
+
 __all__ = ['File', 'TextFile']
diff --git a/pysparkling/fileio/codec/__init__.py b/src/main/python/pysparkling/fileio/codec/__init__.py
similarity index 100%
rename from pysparkling/fileio/codec/__init__.py
rename to src/main/python/pysparkling/fileio/codec/__init__.py
diff --git a/pysparkling/fileio/codec/bz2.py b/src/main/python/pysparkling/fileio/codec/bz2.py
similarity index 100%
rename from pysparkling/fileio/codec/bz2.py
rename to src/main/python/pysparkling/fileio/codec/bz2.py
index 2a26b2a9c..1c73f9adb 100644
--- a/pysparkling/fileio/codec/bz2.py
+++ b/src/main/python/pysparkling/fileio/codec/bz2.py
@@ -1,8 +1,8 @@
 from __future__ import absolute_import
 
 import bz2
-from io import BytesIO
 import logging
+from io import BytesIO
 
 from .codec import Codec
 
diff --git a/pysparkling/fileio/codec/codec.py b/src/main/python/pysparkling/fileio/codec/codec.py
similarity index 100%
rename from pysparkling/fileio/codec/codec.py
rename to src/main/python/pysparkling/fileio/codec/codec.py
diff --git a/pysparkling/fileio/codec/gz.py b/src/main/python/pysparkling/fileio/codec/gz.py
similarity index 100%
rename from pysparkling/fileio/codec/gz.py
rename to src/main/python/pysparkling/fileio/codec/gz.py
index 28a4dcb1d..9312e13c2 100644
--- a/pysparkling/fileio/codec/gz.py
+++ b/src/main/python/pysparkling/fileio/codec/gz.py
@@ -1,8 +1,8 @@
 from __future__ import absolute_import
 
 import gzip
-from io import BytesIO
 import logging
+from io import BytesIO
 
 from .codec import Codec
 
diff --git a/pysparkling/fileio/codec/lzma.py b/src/main/python/pysparkling/fileio/codec/lzma.py
similarity index 100%
rename from pysparkling/fileio/codec/lzma.py
rename to src/main/python/pysparkling/fileio/codec/lzma.py
diff --git a/pysparkling/fileio/codec/sevenz.py b/src/main/python/pysparkling/fileio/codec/sevenz.py
similarity index 100%
rename from pysparkling/fileio/codec/sevenz.py
rename to src/main/python/pysparkling/fileio/codec/sevenz.py
diff --git a/pysparkling/fileio/codec/tar.py b/src/main/python/pysparkling/fileio/codec/tar.py
similarity index 100%
rename from pysparkling/fileio/codec/tar.py
rename to src/main/python/pysparkling/fileio/codec/tar.py
index c3ae44fbe..2617fd062 100644
--- a/pysparkling/fileio/codec/tar.py
+++ b/src/main/python/pysparkling/fileio/codec/tar.py
@@ -1,8 +1,8 @@
 from __future__ import absolute_import
 
-from io import BytesIO
 import logging
 import tarfile
+from io import BytesIO
 
 from .codec import Codec
 
diff --git a/pysparkling/fileio/codec/zip.py b/src/main/python/pysparkling/fileio/codec/zip.py
similarity index 100%
rename from pysparkling/fileio/codec/zip.py
rename to src/main/python/pysparkling/fileio/codec/zip.py
index 4aaaba3f6..2bfde66e0 100644
--- a/pysparkling/fileio/codec/zip.py
+++ b/src/main/python/pysparkling/fileio/codec/zip.py
@@ -1,8 +1,8 @@
 from __future__ import absolute_import
 
-from io import BytesIO
 import logging
 import zipfile
+from io import BytesIO
 
 from .codec import Codec
 
diff --git a/pysparkling/fileio/file.py b/src/main/python/pysparkling/fileio/file.py
similarity index 100%
rename from pysparkling/fileio/file.py
rename to src/main/python/pysparkling/fileio/file.py
index 32b5cf0a1..1e55f2c2e 100644
--- a/pysparkling/fileio/file.py
+++ b/src/main/python/pysparkling/fileio/file.py
@@ -1,7 +1,7 @@
 from __future__ import absolute_import
 
-from io import BytesIO
 import logging
+from io import BytesIO
 
 from . import codec
 from . import fs
diff --git a/pysparkling/fileio/fs/__init__.py b/src/main/python/pysparkling/fileio/fs/__init__.py
similarity index 99%
rename from pysparkling/fileio/fs/__init__.py
rename to src/main/python/pysparkling/fileio/fs/__init__.py
index fe0192986..95f922386 100644
--- a/pysparkling/fileio/fs/__init__.py
+++ b/src/main/python/pysparkling/fileio/fs/__init__.py
@@ -7,7 +7,6 @@
 from .local import Local
 from .s3 import S3
 
-
 __all__ = ['FileSystem', 'GS', 'Hdfs', 'Http', 'Local', 'S3']
 
 
diff --git a/pysparkling/fileio/fs/file_system.py b/src/main/python/pysparkling/fileio/fs/file_system.py
similarity index 100%
rename from pysparkling/fileio/fs/file_system.py
rename to src/main/python/pysparkling/fileio/fs/file_system.py
diff --git a/pysparkling/fileio/fs/gs.py b/src/main/python/pysparkling/fileio/fs/gs.py
similarity index 100%
rename from pysparkling/fileio/fs/gs.py
rename to src/main/python/pysparkling/fileio/fs/gs.py
index 59636679f..c1e6d617a 100644
--- a/pysparkling/fileio/fs/gs.py
+++ b/src/main/python/pysparkling/fileio/fs/gs.py
@@ -1,12 +1,12 @@
 from __future__ import absolute_import
 
-from fnmatch import fnmatch
 import logging
+from fnmatch import fnmatch
 from io import BytesIO, StringIO
 
+from .file_system import FileSystem
 from ...exceptions import FileSystemNotSupported
 from ...utils import Tokenizer, parse_file_uri
-from .file_system import FileSystem
 
 log = logging.getLogger(__name__)
 
diff --git a/pysparkling/fileio/fs/hdfs.py b/src/main/python/pysparkling/fileio/fs/hdfs.py
similarity index 100%
rename from pysparkling/fileio/fs/hdfs.py
rename to src/main/python/pysparkling/fileio/fs/hdfs.py
index 9d9902f3e..de9fe46a6 100644
--- a/pysparkling/fileio/fs/hdfs.py
+++ b/src/main/python/pysparkling/fileio/fs/hdfs.py
@@ -1,12 +1,12 @@
 from __future__ import absolute_import, unicode_literals
 
-from fnmatch import fnmatch
 import logging
+from fnmatch import fnmatch
 from io import BytesIO, StringIO
 
+from .file_system import FileSystem
 from ...exceptions import FileSystemNotSupported
 from ...utils import parse_file_uri, format_file_uri
-from .file_system import FileSystem
 
 log = logging.getLogger(__name__)
 
diff --git a/pysparkling/fileio/fs/http.py b/src/main/python/pysparkling/fileio/fs/http.py
similarity index 100%
rename from pysparkling/fileio/fs/http.py
rename to src/main/python/pysparkling/fileio/fs/http.py
diff --git a/pysparkling/fileio/fs/local.py b/src/main/python/pysparkling/fileio/fs/local.py
similarity index 100%
rename from pysparkling/fileio/fs/local.py
rename to src/main/python/pysparkling/fileio/fs/local.py
index db91961af..e1ec3155b 100644
--- a/pysparkling/fileio/fs/local.py
+++ b/src/main/python/pysparkling/fileio/fs/local.py
@@ -1,13 +1,13 @@
 from __future__ import absolute_import, unicode_literals
 
 import glob
-from fnmatch import fnmatch
 import io
 import logging
 import os
+from fnmatch import fnmatch
 
-from ...utils import Tokenizer
 from .file_system import FileSystem
+from ...utils import Tokenizer
 
 log = logging.getLogger(__name__)
 
diff --git a/pysparkling/fileio/fs/s3.py b/src/main/python/pysparkling/fileio/fs/s3.py
similarity index 100%
rename from pysparkling/fileio/fs/s3.py
rename to src/main/python/pysparkling/fileio/fs/s3.py
index 9d123fe22..3f530be1b 100644
--- a/pysparkling/fileio/fs/s3.py
+++ b/src/main/python/pysparkling/fileio/fs/s3.py
@@ -1,12 +1,12 @@
 from __future__ import absolute_import
 
+import logging
 from fnmatch import fnmatch
 from io import BytesIO, StringIO
-import logging
 
+from .file_system import FileSystem
 from ...exceptions import FileSystemNotSupported
 from ...utils import Tokenizer, parse_file_uri
-from .file_system import FileSystem
 
 log = logging.getLogger(__name__)
 
diff --git a/pysparkling/fileio/textfile.py b/src/main/python/pysparkling/fileio/textfile.py
similarity index 100%
rename from pysparkling/fileio/textfile.py
rename to src/main/python/pysparkling/fileio/textfile.py
diff --git a/pysparkling/partition.py b/src/main/python/pysparkling/partition.py
similarity index 100%
rename from pysparkling/partition.py
rename to src/main/python/pysparkling/partition.py
diff --git a/pysparkling/rdd.py b/src/main/python/pysparkling/rdd.py
similarity index 100%
rename from pysparkling/rdd.py
rename to src/main/python/pysparkling/rdd.py
index 3a423b242..ce4af2221 100644
--- a/pysparkling/rdd.py
+++ b/src/main/python/pysparkling/rdd.py
@@ -3,20 +3,20 @@
 from __future__ import (division, absolute_import, print_function,
                         unicode_literals)
 
-import math
-from builtins import range, zip
-from collections import defaultdict
 import copy
 import functools
 import io
 import itertools
 import logging
-from operator import itemgetter
+import math
 import os
 import pickle
 import random
 import subprocess
 import sys
+from builtins import range, zip
+from collections import defaultdict
+from operator import itemgetter
 
 try:
     import numpy
diff --git a/pysparkling/samplers.py b/src/main/python/pysparkling/samplers.py
similarity index 100%
rename from pysparkling/samplers.py
rename to src/main/python/pysparkling/samplers.py
diff --git a/pysparkling/sql/__init__.py b/src/main/python/pysparkling/sql/__init__.py
similarity index 100%
rename from pysparkling/sql/__init__.py
rename to src/main/python/pysparkling/sql/__init__.py
diff --git a/pysparkling/sql/casts.py b/src/main/python/pysparkling/sql/casts.py
similarity index 100%
rename from pysparkling/sql/casts.py
rename to src/main/python/pysparkling/sql/casts.py
diff --git a/pysparkling/sql/column.py b/src/main/python/pysparkling/sql/column.py
similarity index 100%
rename from pysparkling/sql/column.py
rename to src/main/python/pysparkling/sql/column.py
diff --git a/pysparkling/sql/conf.py b/src/main/python/pysparkling/sql/conf.py
similarity index 100%
rename from pysparkling/sql/conf.py
rename to src/main/python/pysparkling/sql/conf.py
diff --git a/pysparkling/sql/context.py b/src/main/python/pysparkling/sql/context.py
similarity index 100%
rename from pysparkling/sql/context.py
rename to src/main/python/pysparkling/sql/context.py
diff --git a/pysparkling/sql/dataframe.py b/src/main/python/pysparkling/sql/dataframe.py
similarity index 100%
rename from pysparkling/sql/dataframe.py
rename to src/main/python/pysparkling/sql/dataframe.py
diff --git a/pysparkling/sql/expressions/__init__.py b/src/main/python/pysparkling/sql/expressions/__init__.py
similarity index 100%
rename from pysparkling/sql/expressions/__init__.py
rename to src/main/python/pysparkling/sql/expressions/__init__.py
diff --git a/pysparkling/sql/expressions/aggregate/__init__.py b/src/main/python/pysparkling/sql/expressions/aggregate/__init__.py
similarity index 100%
rename from pysparkling/sql/expressions/aggregate/__init__.py
rename to src/main/python/pysparkling/sql/expressions/aggregate/__init__.py
diff --git a/pysparkling/sql/expressions/aggregate/aggregations.py b/src/main/python/pysparkling/sql/expressions/aggregate/aggregations.py
similarity index 100%
rename from pysparkling/sql/expressions/aggregate/aggregations.py
rename to src/main/python/pysparkling/sql/expressions/aggregate/aggregations.py
diff --git a/pysparkling/sql/expressions/aggregate/collectors.py b/src/main/python/pysparkling/sql/expressions/aggregate/collectors.py
similarity index 100%
rename from pysparkling/sql/expressions/aggregate/collectors.py
rename to src/main/python/pysparkling/sql/expressions/aggregate/collectors.py
diff --git a/pysparkling/sql/expressions/aggregate/covariance_aggregations.py b/src/main/python/pysparkling/sql/expressions/aggregate/covariance_aggregations.py
similarity index 100%
rename from pysparkling/sql/expressions/aggregate/covariance_aggregations.py
rename to src/main/python/pysparkling/sql/expressions/aggregate/covariance_aggregations.py
diff --git a/pysparkling/sql/expressions/aggregate/stat_aggregations.py b/src/main/python/pysparkling/sql/expressions/aggregate/stat_aggregations.py
similarity index 100%
rename from pysparkling/sql/expressions/aggregate/stat_aggregations.py
rename to src/main/python/pysparkling/sql/expressions/aggregate/stat_aggregations.py
diff --git a/pysparkling/sql/expressions/arrays.py b/src/main/python/pysparkling/sql/expressions/arrays.py
similarity index 100%
rename from pysparkling/sql/expressions/arrays.py
rename to src/main/python/pysparkling/sql/expressions/arrays.py
diff --git a/pysparkling/sql/expressions/csvs.py b/src/main/python/pysparkling/sql/expressions/csvs.py
similarity index 100%
rename from pysparkling/sql/expressions/csvs.py
rename to src/main/python/pysparkling/sql/expressions/csvs.py
diff --git a/pysparkling/sql/expressions/dates.py b/src/main/python/pysparkling/sql/expressions/dates.py
similarity index 100%
rename from pysparkling/sql/expressions/dates.py
rename to src/main/python/pysparkling/sql/expressions/dates.py
diff --git a/pysparkling/sql/expressions/explodes.py b/src/main/python/pysparkling/sql/expressions/explodes.py
similarity index 99%
rename from pysparkling/sql/expressions/explodes.py
rename to src/main/python/pysparkling/sql/expressions/explodes.py
index 448d8e54d..12f42ae73 100644
--- a/pysparkling/sql/expressions/explodes.py
+++ b/src/main/python/pysparkling/sql/expressions/explodes.py
@@ -1,6 +1,5 @@
-from pysparkling.sql.types import StructField, IntegerType, DataType
-
 from pysparkling.sql.expressions.expressions import UnaryExpression
+from pysparkling.sql.types import StructField, IntegerType, DataType
 
 
 class Explode(UnaryExpression):
diff --git a/pysparkling/sql/expressions/expressions.py b/src/main/python/pysparkling/sql/expressions/expressions.py
similarity index 100%
rename from pysparkling/sql/expressions/expressions.py
rename to src/main/python/pysparkling/sql/expressions/expressions.py
diff --git a/pysparkling/sql/expressions/fields.py b/src/main/python/pysparkling/sql/expressions/fields.py
similarity index 99%
rename from pysparkling/sql/expressions/fields.py
rename to src/main/python/pysparkling/sql/expressions/fields.py
index 1ba5a48be..d14c28f7b 100644
--- a/pysparkling/sql/expressions/fields.py
+++ b/src/main/python/pysparkling/sql/expressions/fields.py
@@ -1,6 +1,5 @@
-from pysparkling.sql.types import StructField
-
 from pysparkling.sql.expressions.expressions import Expression
+from pysparkling.sql.types import StructField
 from pysparkling.sql.utils import AnalysisException
 
 
diff --git a/pysparkling/sql/expressions/jsons.py b/src/main/python/pysparkling/sql/expressions/jsons.py
similarity index 100%
rename from pysparkling/sql/expressions/jsons.py
rename to src/main/python/pysparkling/sql/expressions/jsons.py
diff --git a/pysparkling/sql/expressions/literals.py b/src/main/python/pysparkling/sql/expressions/literals.py
similarity index 100%
rename from pysparkling/sql/expressions/literals.py
rename to src/main/python/pysparkling/sql/expressions/literals.py
diff --git a/pysparkling/sql/expressions/mappers.py b/src/main/python/pysparkling/sql/expressions/mappers.py
similarity index 100%
rename from pysparkling/sql/expressions/mappers.py
rename to src/main/python/pysparkling/sql/expressions/mappers.py
diff --git a/pysparkling/sql/expressions/operators.py b/src/main/python/pysparkling/sql/expressions/operators.py
similarity index 100%
rename from pysparkling/sql/expressions/operators.py
rename to src/main/python/pysparkling/sql/expressions/operators.py
diff --git a/pysparkling/sql/expressions/orders.py b/src/main/python/pysparkling/sql/expressions/orders.py
similarity index 100%
rename from pysparkling/sql/expressions/orders.py
rename to src/main/python/pysparkling/sql/expressions/orders.py
diff --git a/pysparkling/sql/expressions/strings.py b/src/main/python/pysparkling/sql/expressions/strings.py
similarity index 100%
rename from pysparkling/sql/expressions/strings.py
rename to src/main/python/pysparkling/sql/expressions/strings.py
diff --git a/pysparkling/sql/expressions/userdefined.py b/src/main/python/pysparkling/sql/expressions/userdefined.py
similarity index 100%
rename from pysparkling/sql/expressions/userdefined.py
rename to src/main/python/pysparkling/sql/expressions/userdefined.py
diff --git a/pysparkling/sql/functions.py b/src/main/python/pysparkling/sql/functions.py
similarity index 100%
rename from pysparkling/sql/functions.py
rename to src/main/python/pysparkling/sql/functions.py
diff --git a/pysparkling/sql/group.py b/src/main/python/pysparkling/sql/group.py
similarity index 100%
rename from pysparkling/sql/group.py
rename to src/main/python/pysparkling/sql/group.py
diff --git a/pysparkling/sql/internal_utils/__init__.py b/src/main/python/pysparkling/sql/internal_utils/__init__.py
similarity index 100%
rename from pysparkling/sql/internal_utils/__init__.py
rename to src/main/python/pysparkling/sql/internal_utils/__init__.py
diff --git a/pysparkling/sql/internal_utils/column.py b/src/main/python/pysparkling/sql/internal_utils/column.py
similarity index 100%
rename from pysparkling/sql/internal_utils/column.py
rename to src/main/python/pysparkling/sql/internal_utils/column.py
diff --git a/pysparkling/sql/internal_utils/joins.py b/src/main/python/pysparkling/sql/internal_utils/joins.py
similarity index 100%
rename from pysparkling/sql/internal_utils/joins.py
rename to src/main/python/pysparkling/sql/internal_utils/joins.py
diff --git a/pysparkling/sql/internal_utils/options.py b/src/main/python/pysparkling/sql/internal_utils/options.py
similarity index 100%
rename from pysparkling/sql/internal_utils/options.py
rename to src/main/python/pysparkling/sql/internal_utils/options.py
diff --git a/pysparkling/sql/internal_utils/readers/__init__.py b/src/main/python/pysparkling/sql/internal_utils/readers/__init__.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/__init__.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/__init__.py
diff --git a/pysparkling/sql/internal_utils/readers/common.py b/src/main/python/pysparkling/sql/internal_utils/readers/common.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/common.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/common.py
diff --git a/pysparkling/sql/internal_utils/readers/csvreader.py b/src/main/python/pysparkling/sql/internal_utils/readers/csvreader.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/csvreader.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/csvreader.py
diff --git a/pysparkling/sql/internal_utils/readers/jsonreader.py b/src/main/python/pysparkling/sql/internal_utils/readers/jsonreader.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/jsonreader.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/jsonreader.py
diff --git a/pysparkling/sql/internal_utils/readers/textreader.py b/src/main/python/pysparkling/sql/internal_utils/readers/textreader.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/textreader.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/textreader.py
diff --git a/pysparkling/sql/internal_utils/readers/utils.py b/src/main/python/pysparkling/sql/internal_utils/readers/utils.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readers/utils.py
rename to src/main/python/pysparkling/sql/internal_utils/readers/utils.py
diff --git a/pysparkling/sql/internal_utils/readwrite.py b/src/main/python/pysparkling/sql/internal_utils/readwrite.py
similarity index 100%
rename from pysparkling/sql/internal_utils/readwrite.py
rename to src/main/python/pysparkling/sql/internal_utils/readwrite.py
diff --git a/pysparkling/sql/internal_utils/writers.py b/src/main/python/pysparkling/sql/internal_utils/writers.py
similarity index 100%
rename from pysparkling/sql/internal_utils/writers.py
rename to src/main/python/pysparkling/sql/internal_utils/writers.py
diff --git a/pysparkling/sql/internals.py b/src/main/python/pysparkling/sql/internals.py
similarity index 99%
rename from pysparkling/sql/internals.py
rename to src/main/python/pysparkling/sql/internals.py
index aaf095f25..e84c45672 100644
--- a/pysparkling/sql/internals.py
+++ b/src/main/python/pysparkling/sql/internals.py
@@ -17,6 +17,7 @@
 from pysparkling.sql.column import parse
 from pysparkling.sql.utils import IllegalArgumentException
 from pysparkling.stat_counter import RowStatHelper, CovarianceCounter
+from pysparkling.storagelevel import StorageLevel
 from pysparkling.utils import get_keyfunc, compute_weighted_percentiles, \
     reservoir_sample_and_size, pad_cell, str_half_width, format_cell, merge_rows, \
     merge_rows_joined_on_values, portable_hash
diff --git a/pysparkling/sql/readwriter.py b/src/main/python/pysparkling/sql/readwriter.py
similarity index 100%
rename from pysparkling/sql/readwriter.py
rename to src/main/python/pysparkling/sql/readwriter.py
diff --git a/pysparkling/sql/schema_utils.py b/src/main/python/pysparkling/sql/schema_utils.py
similarity index 99%
rename from pysparkling/sql/schema_utils.py
rename to src/main/python/pysparkling/sql/schema_utils.py
index ffe17249c..b1583b716 100644
--- a/pysparkling/sql/schema_utils.py
+++ b/src/main/python/pysparkling/sql/schema_utils.py
@@ -1,6 +1,6 @@
 from functools import reduce
 
-from pysparkling.sql.internal_utils.joins import INNER_JOIN, CROSS_JOIN, LEFT_JOIN,\
+from pysparkling.sql.internal_utils.joins import INNER_JOIN, CROSS_JOIN, LEFT_JOIN, \
     LEFT_ANTI_JOIN, LEFT_SEMI_JOIN, RIGHT_JOIN, FULL_JOIN
 from pysparkling.sql.types import _infer_schema, _has_nulltype, _merge_type, \
     StructType, StructField, _get_null_fields
diff --git a/pysparkling/sql/session.py b/src/main/python/pysparkling/sql/session.py
similarity index 99%
rename from pysparkling/sql/session.py
rename to src/main/python/pysparkling/sql/session.py
index 9ea3d30f8..eccd80bc8 100644
--- a/pysparkling/sql/session.py
+++ b/src/main/python/pysparkling/sql/session.py
@@ -1,17 +1,16 @@
 import sys
 from threading import RLock
 
-from pysparkling.sql.types import _make_type_verifier, DataType, StructType, \
-    _create_converter, _infer_schema, _has_nulltype, _merge_type
-
 import pysparkling
 from pysparkling import RDD
 from pysparkling.context import Context
 from pysparkling.sql.conf import RuntimeConfig
-from pysparkling.sql.internals import DataFrameInternal
 from pysparkling.sql.dataframe import DataFrame
+from pysparkling.sql.internals import DataFrameInternal
 from pysparkling.sql.readwriter import DataFrameReader
 from pysparkling.sql.schema_utils import infer_schema_from_list
+from pysparkling.sql.types import _make_type_verifier, DataType, StructType, \
+    _create_converter, _infer_schema, _has_nulltype, _merge_type
 from pysparkling.sql.utils import require_minimum_pandas_version
 
 if sys.version >= '3':
diff --git a/pysparkling/sql/types.py b/src/main/python/pysparkling/sql/types.py
similarity index 99%
rename from pysparkling/sql/types.py
rename to src/main/python/pysparkling/sql/types.py
index 3242f625b..d39eff251 100644
--- a/pysparkling/sql/types.py
+++ b/src/main/python/pysparkling/sql/types.py
@@ -14,20 +14,19 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-import itertools
-import os
-import sys
-import decimal
+import ctypes
 import datetime
+import decimal
+import itertools
 import json as _json
+import os
+import platform
 import re
+import sys
 from array import array
-import ctypes
-import platform
 
 from pysparkling.sql.utils import ParseException, require_minimum_pandas_version
 
-
 if sys.version >= "3":
     long = int
     basestring = unicode = str
diff --git a/pysparkling/sql/utils.py b/src/main/python/pysparkling/sql/utils.py
similarity index 100%
rename from pysparkling/sql/utils.py
rename to src/main/python/pysparkling/sql/utils.py
diff --git a/pysparkling/stat_counter.py b/src/main/python/pysparkling/stat_counter.py
similarity index 100%
rename from pysparkling/stat_counter.py
rename to src/main/python/pysparkling/stat_counter.py
diff --git a/pysparkling/storagelevel.py b/src/main/python/pysparkling/storagelevel.py
similarity index 100%
rename from pysparkling/storagelevel.py
rename to src/main/python/pysparkling/storagelevel.py
diff --git a/pysparkling/streaming/__init__.py b/src/main/python/pysparkling/streaming/__init__.py
similarity index 100%
rename from pysparkling/streaming/__init__.py
rename to src/main/python/pysparkling/streaming/__init__.py
diff --git a/pysparkling/streaming/context.py b/src/main/python/pysparkling/streaming/context.py
similarity index 100%
rename from pysparkling/streaming/context.py
rename to src/main/python/pysparkling/streaming/context.py
diff --git a/pysparkling/streaming/dstream.py b/src/main/python/pysparkling/streaming/dstream.py
similarity index 100%
rename from pysparkling/streaming/dstream.py
rename to src/main/python/pysparkling/streaming/dstream.py
diff --git a/pysparkling/streaming/filestream.py b/src/main/python/pysparkling/streaming/filestream.py
similarity index 100%
rename from pysparkling/streaming/filestream.py
rename to src/main/python/pysparkling/streaming/filestream.py
diff --git a/pysparkling/streaming/queuestream.py b/src/main/python/pysparkling/streaming/queuestream.py
similarity index 100%
rename from pysparkling/streaming/queuestream.py
rename to src/main/python/pysparkling/streaming/queuestream.py
diff --git a/pysparkling/streaming/tcpstream.py b/src/main/python/pysparkling/streaming/tcpstream.py
similarity index 99%
rename from pysparkling/streaming/tcpstream.py
rename to src/main/python/pysparkling/streaming/tcpstream.py
index 968028fee..13140fac7 100644
--- a/pysparkling/streaming/tcpstream.py
+++ b/src/main/python/pysparkling/streaming/tcpstream.py
@@ -2,6 +2,7 @@
 
 import logging
 import struct
+
 from tornado.gen import coroutine, moment
 from tornado.iostream import StreamClosedError
 from tornado.tcpserver import TCPServer
diff --git a/pysparkling/task_context.py b/src/main/python/pysparkling/task_context.py
similarity index 100%
rename from pysparkling/task_context.py
rename to src/main/python/pysparkling/task_context.py
diff --git a/pysparkling/utils.py b/src/main/python/pysparkling/utils.py
similarity index 100%
rename from pysparkling/utils.py
rename to src/main/python/pysparkling/utils.py
index 2cac017db..6a887701a 100644
--- a/pysparkling/utils.py
+++ b/src/main/python/pysparkling/utils.py
@@ -12,9 +12,9 @@
 from pytz import UnknownTimeZoneError
 
 from pysparkling.sql.casts import get_time_formatter
-from pysparkling.sql.schema_utils import get_on_fields
 from pysparkling.sql.internal_utils.joins import FULL_JOIN, RIGHT_JOIN, LEFT_JOIN, \
     CROSS_JOIN, INNER_JOIN, LEFT_SEMI_JOIN, LEFT_ANTI_JOIN
+from pysparkling.sql.schema_utils import get_on_fields
 from pysparkling.sql.types import Row, create_row, row_from_keyed_values
 from pysparkling.sql.utils import IllegalArgumentException
 
diff --git a/scripts/benchmark_csv.py b/src/main/scripts/benchmark_csv.py
similarity index 99%
rename from scripts/benchmark_csv.py
rename to src/main/scripts/benchmark_csv.py
index 5de705c6c..871256a8a 100644
--- a/scripts/benchmark_csv.py
+++ b/src/main/scripts/benchmark_csv.py
@@ -1,9 +1,10 @@
 """Benchmark csv reading performance."""
 
 import argparse
-import pysparkling
 import random
 
+import pysparkling
+
 
 def create_csv(filename, lines=10000000, columns=12):
     with open(filename, 'w') as f:
diff --git a/scripts/benchmark_generators.py b/src/main/scripts/benchmark_generators.py
similarity index 100%
rename from scripts/benchmark_generators.py
rename to src/main/scripts/benchmark_generators.py
diff --git a/scripts/ipcluster_simple.py b/src/main/scripts/ipcluster_simple.py
similarity index 100%
rename from scripts/ipcluster_simple.py
rename to src/main/scripts/ipcluster_simple.py
diff --git a/scripts/log_streaming.py b/src/main/scripts/log_streaming.py
similarity index 100%
rename from scripts/log_streaming.py
rename to src/main/scripts/log_streaming.py
diff --git a/scripts/multiprocessing_performance_plot.pdf b/src/main/scripts/multiprocessing_performance_plot.pdf
similarity index 100%
rename from scripts/multiprocessing_performance_plot.pdf
rename to src/main/scripts/multiprocessing_performance_plot.pdf
diff --git a/scripts/multiprocessing_performance_plot.png b/src/main/scripts/multiprocessing_performance_plot.png
similarity index 100%
rename from scripts/multiprocessing_performance_plot.png
rename to src/main/scripts/multiprocessing_performance_plot.png
diff --git a/scripts/multiprocessing_performance_plot.py b/src/main/scripts/multiprocessing_performance_plot.py
similarity index 99%
rename from scripts/multiprocessing_performance_plot.py
rename to src/main/scripts/multiprocessing_performance_plot.py
index 22393792b..b19968325 100644
--- a/scripts/multiprocessing_performance_plot.py
+++ b/src/main/scripts/multiprocessing_performance_plot.py
@@ -1,5 +1,6 @@
 import matplotlib.pyplot as plt
 import numpy as np
+
 import test_multiprocessing
 
 
diff --git a/scripts/pyspark_comparisons.py b/src/main/scripts/pyspark_comparisons.py
similarity index 100%
rename from scripts/pyspark_comparisons.py
rename to src/main/scripts/pyspark_comparisons.py
diff --git a/scripts/pyspark_streaming.py b/src/main/scripts/pyspark_streaming.py
similarity index 99%
rename from scripts/pyspark_streaming.py
rename to src/main/scripts/pyspark_streaming.py
index 0433290b1..b375916ee 100644
--- a/scripts/pyspark_streaming.py
+++ b/src/main/scripts/pyspark_streaming.py
@@ -5,10 +5,10 @@
 
 from __future__ import print_function
 
-import pyspark
-import pyspark.streaming
 import time
 
+import pyspark.streaming
+
 
 def simple_queue(ssc):
     ssc.queueStream([range(5), ['a', 'b'], ['c']], oneAtATime=False).pprint()
diff --git a/scripts/readme_example.py b/src/main/scripts/readme_example.py
similarity index 100%
rename from scripts/readme_example.py
rename to src/main/scripts/readme_example.py
diff --git a/scripts/readme_example_common_crawl.py b/src/main/scripts/readme_example_common_crawl.py
similarity index 100%
rename from scripts/readme_example_common_crawl.py
rename to src/main/scripts/readme_example_common_crawl.py
diff --git a/scripts/readme_example_human_microbiome.py b/src/main/scripts/readme_example_human_microbiome.py
similarity index 100%
rename from scripts/readme_example_human_microbiome.py
rename to src/main/scripts/readme_example_human_microbiome.py
diff --git a/scripts/readme_example_word_count.py b/src/main/scripts/readme_example_word_count.py
similarity index 100%
rename from scripts/readme_example_word_count.py
rename to src/main/scripts/readme_example_word_count.py
diff --git a/scripts/starcluster_simple.py b/src/main/scripts/starcluster_simple.py
similarity index 100%
rename from scripts/starcluster_simple.py
rename to src/main/scripts/starcluster_simple.py
diff --git a/scripts/tcpperf_client.py b/src/main/scripts/tcpperf_client.py
similarity index 99%
rename from scripts/tcpperf_client.py
rename to src/main/scripts/tcpperf_client.py
index 02a023990..0911564d2 100644
--- a/scripts/tcpperf_client.py
+++ b/src/main/scripts/tcpperf_client.py
@@ -3,16 +3,17 @@
 from __future__ import absolute_import, division
 
 import argparse
-from contextlib import closing
 import json
 import random
 import struct
 import sys
 import time
+from contextlib import closing
+
 from tornado import gen
-from tornado.tcpclient import TCPClient
 from tornado.ioloop import IOLoop, PeriodicCallback
 from tornado.iostream import StreamClosedError
+from tornado.tcpclient import TCPClient
 
 
 class Emitter(object):
diff --git a/scripts/tcpperf_connections.csv b/src/main/scripts/tcpperf_connections.csv
similarity index 100%
rename from scripts/tcpperf_connections.csv
rename to src/main/scripts/tcpperf_connections.csv
diff --git a/scripts/tcpperf_connections.csv.pdf b/src/main/scripts/tcpperf_connections.csv.pdf
similarity index 100%
rename from scripts/tcpperf_connections.csv.pdf
rename to src/main/scripts/tcpperf_connections.csv.pdf
diff --git a/scripts/tcpperf_connections.csv.png b/src/main/scripts/tcpperf_connections.csv.png
similarity index 100%
rename from scripts/tcpperf_connections.csv.png
rename to src/main/scripts/tcpperf_connections.csv.png
diff --git a/scripts/tcpperf_messages.csv b/src/main/scripts/tcpperf_messages.csv
similarity index 100%
rename from scripts/tcpperf_messages.csv
rename to src/main/scripts/tcpperf_messages.csv
diff --git a/scripts/tcpperf_messages.csv.pdf b/src/main/scripts/tcpperf_messages.csv.pdf
similarity index 100%
rename from scripts/tcpperf_messages.csv.pdf
rename to src/main/scripts/tcpperf_messages.csv.pdf
diff --git a/scripts/tcpperf_messages.csv.png b/src/main/scripts/tcpperf_messages.csv.png
similarity index 100%
rename from scripts/tcpperf_messages.csv.png
rename to src/main/scripts/tcpperf_messages.csv.png
diff --git a/scripts/tcpperf_plot.py b/src/main/scripts/tcpperf_plot.py
similarity index 99%
rename from scripts/tcpperf_plot.py
rename to src/main/scripts/tcpperf_plot.py
index 7eafcad6f..a3c6cff86 100644
--- a/scripts/tcpperf_plot.py
+++ b/src/main/scripts/tcpperf_plot.py
@@ -1,6 +1,8 @@
-from collections import namedtuple
 import csv
+from collections import namedtuple
+
 import matplotlib
+
 matplotlib.use('Agg')
 import matplotlib.pyplot as plt
 
diff --git a/scripts/tcpperf_server.py b/src/main/scripts/tcpperf_server.py
similarity index 100%
rename from scripts/tcpperf_server.py
rename to src/main/scripts/tcpperf_server.py
index 8d7384b9b..f6ec346c9 100644
--- a/scripts/tcpperf_server.py
+++ b/src/main/scripts/tcpperf_server.py
@@ -1,14 +1,14 @@
 from __future__ import print_function, division
 
-from collections import defaultdict
 import json
 import logging
 import math
 import os
-import pysparkling
 import struct
 import time
+from collections import defaultdict
 
+import pysparkling
 
 N_CONNECTIONS = (100, 1000, 2000, 3000, 3500, 4000, 4500, 5000,
                  6000, 7000, 8000)
diff --git a/pysparkling/sql/tests/__init__.py b/src/unittest/python/__init__.py
similarity index 100%
rename from pysparkling/sql/tests/__init__.py
rename to src/unittest/python/__init__.py
diff --git a/pysparkling/tests/data.7z b/src/unittest/python/data.7z
similarity index 100%
rename from pysparkling/tests/data.7z
rename to src/unittest/python/data.7z
diff --git a/pysparkling/tests/data.tar.gz b/src/unittest/python/data.tar.gz
similarity index 100%
rename from pysparkling/tests/data.tar.gz
rename to src/unittest/python/data.tar.gz
diff --git a/pysparkling/tests/profile_textfile.py b/src/unittest/python/profile_textfile.py
similarity index 100%
rename from pysparkling/tests/profile_textfile.py
rename to src/unittest/python/profile_textfile.py
diff --git a/pysparkling/tests/__init__.py b/src/unittest/python/sql_tests/__init__.py
similarity index 100%
rename from pysparkling/tests/__init__.py
rename to src/unittest/python/sql_tests/__init__.py
diff --git a/pysparkling/sql/tests/data/fundings/part-0.csv b/src/unittest/python/sql_tests/data/fundings/part-0.csv
similarity index 100%
rename from pysparkling/sql/tests/data/fundings/part-0.csv
rename to src/unittest/python/sql_tests/data/fundings/part-0.csv
diff --git a/pysparkling/sql/tests/test_casts.py b/src/unittest/python/sql_tests/test_casts.py
similarity index 100%
rename from pysparkling/sql/tests/test_casts.py
rename to src/unittest/python/sql_tests/test_casts.py
diff --git a/pysparkling/sql/tests/test_read.py b/src/unittest/python/sql_tests/test_read.py
similarity index 100%
rename from pysparkling/sql/tests/test_read.py
rename to src/unittest/python/sql_tests/test_read.py
diff --git a/pysparkling/sql/tests/test_session.py b/src/unittest/python/sql_tests/test_session.py
similarity index 100%
rename from pysparkling/sql/tests/test_session.py
rename to src/unittest/python/sql_tests/test_session.py
index cf819761d..faffcecbb 100644
--- a/pysparkling/sql/tests/test_session.py
+++ b/src/unittest/python/sql_tests/test_session.py
@@ -2,11 +2,11 @@
 
 import pytest
 
+from pysparkling import Context
 from pysparkling import StorageLevel
+from pysparkling.sql.session import SparkSession
 from pysparkling.sql.types import Row, StructType, StructField, LongType, StringType, DoubleType, \
     ArrayType, MapType, IntegerType, row_from_keyed_values
-from pysparkling.sql.session import SparkSession
-from pysparkling import Context
 from pysparkling.sql.utils import require_minimum_pandas_version
 
 try:
diff --git a/pysparkling/sql/tests/test_write.py b/src/unittest/python/sql_tests/test_write.py
similarity index 100%
rename from pysparkling/sql/tests/test_write.py
rename to src/unittest/python/sql_tests/test_write.py
diff --git a/pysparkling/tests/test_cache.py b/src/unittest/python/test_cache.py
similarity index 100%
rename from pysparkling/tests/test_cache.py
rename to src/unittest/python/test_cache.py
diff --git a/pysparkling/tests/test_context.py b/src/unittest/python/test_context.py
similarity index 100%
rename from pysparkling/tests/test_context.py
rename to src/unittest/python/test_context.py
diff --git a/pysparkling/tests/test_multiprocessing.py b/src/unittest/python/test_multiprocessing.py
similarity index 100%
rename from pysparkling/tests/test_multiprocessing.py
rename to src/unittest/python/test_multiprocessing.py
index 2715f04dd..e06c0750b 100644
--- a/pysparkling/tests/test_multiprocessing.py
+++ b/src/unittest/python/test_multiprocessing.py
@@ -1,6 +1,5 @@
 from __future__ import division, print_function
 
-from concurrent import futures
 import logging
 import math
 import multiprocessing
@@ -12,6 +11,7 @@
 import time
 import timeit
 import unittest
+from concurrent import futures
 
 import cloudpickle
 
diff --git a/pysparkling/tests/test_rdd.py b/src/unittest/python/test_rdd.py
similarity index 100%
rename from pysparkling/tests/test_rdd.py
rename to src/unittest/python/test_rdd.py
index cc9f70d46..20967bed5 100644
--- a/pysparkling/tests/test_rdd.py
+++ b/src/unittest/python/test_rdd.py
@@ -1,6 +1,6 @@
 import unittest
-
 from operator import add
+
 from pysparkling import Context
 
 
diff --git a/pysparkling/tests/test_resolve_filenames.py b/src/unittest/python/test_resolve_filenames.py
similarity index 100%
rename from pysparkling/tests/test_resolve_filenames.py
rename to src/unittest/python/test_resolve_filenames.py
diff --git a/pysparkling/tests/test_sample.py b/src/unittest/python/test_sample.py
similarity index 99%
rename from pysparkling/tests/test_sample.py
rename to src/unittest/python/test_sample.py
index 09f6152c6..1845cdad2 100644
--- a/pysparkling/tests/test_sample.py
+++ b/src/unittest/python/test_sample.py
@@ -1,6 +1,7 @@
 from __future__ import print_function
 
 import logging
+
 import pysparkling
 
 
diff --git a/pysparkling/tests/test_stat_counter.py b/src/unittest/python/test_stat_counter.py
similarity index 100%
rename from pysparkling/tests/test_stat_counter.py
rename to src/unittest/python/test_stat_counter.py
index adf5f13ec..ed79c5dc2 100644
--- a/pysparkling/tests/test_stat_counter.py
+++ b/src/unittest/python/test_stat_counter.py
@@ -1,9 +1,9 @@
 from __future__ import division
 
 import pysparkling
-from pysparkling.stat_counter import ColumnStatHelper
-from pysparkling.sql.types import Row, StructType, StructField, IntegerType
 from pysparkling.sql.functions import col
+from pysparkling.sql.types import Row, StructType, StructField, IntegerType
+from pysparkling.stat_counter import ColumnStatHelper
 
 
 def test_mean():
diff --git a/pysparkling/tests/test_streaming_files.py b/src/unittest/python/test_streaming_files.py
similarity index 100%
rename from pysparkling/tests/test_streaming_files.py
rename to src/unittest/python/test_streaming_files.py
diff --git a/pysparkling/tests/test_streaming_queue.py b/src/unittest/python/test_streaming_queue.py
similarity index 100%
rename from pysparkling/tests/test_streaming_queue.py
rename to src/unittest/python/test_streaming_queue.py
diff --git a/pysparkling/tests/test_streaming_tcp.py b/src/unittest/python/test_streaming_tcp.py
similarity index 99%
rename from pysparkling/tests/test_streaming_tcp.py
rename to src/unittest/python/test_streaming_tcp.py
index 432e610da..292161ac8 100644
--- a/pysparkling/tests/test_streaming_tcp.py
+++ b/src/unittest/python/test_streaming_tcp.py
@@ -1,8 +1,9 @@
 from __future__ import print_function
 
+import struct
 from collections import Counter
 from contextlib import closing
-import struct
+
 import tornado.gen
 import tornado.tcpclient
 import tornado.testing
diff --git a/pysparkling/tests/test_textFile.py b/src/unittest/python/test_textFile.py
similarity index 100%
rename from pysparkling/tests/test_textFile.py
rename to src/unittest/python/test_textFile.py