first commit

.gitignore

@@ -0,0 +1,142 @@
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode
+
+### VisualStudioCode ###
+.vscode/*
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode
+
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don’t work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# End of https://www.toptal.com/developers/gitignore/api/python

README.md

@@ -0,0 +1 @@
+# Word-Vectors-Basics

src/colors2vec.py

@@ -0,0 +1,26 @@
+import requests
+import json
+from vector_utils import Vector
+
+
+def hex_to_int(s):
+    s = s.lstrip('#')
+    return [int(s[:2], 16), int(s[2:4], 16), int(s[4:6], 16)]
+
+
+def get_json(url):
+    response = requests.get(url)
+    content = response.content.decode()
+    data = json.loads(content)
+    return data
+
+
+def parse_colors(data_set):
+    return dict((item['color'], hex_to_int(item['hex'])) for item in data_set['colors'])
+
+
+if __name__ == '__main__':
+    data_set_url = "https://raw.githubusercontent.com/dariusk/corpora/master/data/colors/xkcd.json"
+    data_set = get_json(data_set_url)
+    colors = parse_colors(data_set)
+

src/vector_utils.py

@@ -0,0 +1,19 @@
+import math
+from functools import reduce
+
+class Vector:
+    @staticmethod
+    def distance(v1, v2):
+        return math.sqrt(sum((i - j)**2 for i, j in zip(v1, v2)))
+
+    @staticmethod
+    def add(*vecs):
+        return [i + j for i, j in zip(*vecs)]
+
+    @staticmethod
+    def subs(*vecs):
+        return [i - j for i, j in zip(*vecs)]
+
+    @staticmethod
+    def mean(*vecs):
+        return [float(coord) / len(vecs) for coord in reduce(Vector.add, vecs)]

test/test_vector.py

@@ -0,0 +1,39 @@
+import unittest
+from src.vector_utils import Vector
+
+
+class TestStringMethods(unittest.TestCase):
+
+    def test_add(self):
+        v1 = [2, 3]
+        v2 = [3, 4]
+        self.assertEqual([5, 7], Vector.add(v1, v2))
+
+        v1 = [5, 12, 32, 12]
+        v2 = [34, 3, 4, 2]
+        self.assertEqual([39, 15, 36, 14], Vector.add(v1, v2))
+
+    def test_substract(self):
+        v1 = [2, 3]
+        v2 = [3, 4]
+        self.assertEqual([-1, -1], Vector.subs(v1, v2))
+
+        v1 = [5, 12, 32, 12]
+        v2 = [34, 3, 4, 2]
+        self.assertEqual([-29, 9, 28, 10], Vector.subs(v1, v2))
+
+    def test_distance(self):
+        v1 = [7, 4, 3]
+        v2 = [17, 6, 2]
+        self.assertAlmostEqual(10.24695, Vector.distance(v1, v2), places=4)
+
+        v1 = [23, 43, 12]
+        v2 = [45, 21, 10]
+        self.assertAlmostEqual(31.176915, Vector.distance(v1, v2), places=4)
+
+    def test_mean(self):
+        self.assertEqual([2.0, 2.0], Vector.mean([0, 1], [2, 2], [4, 3]))
+
+
+if __name__ == '__main__':
+    unittest.main()