StarMirror/data-science-ipython-notebooks
1
0
Fork 0
mirror of https://github.com/donnemartin/data-science-ipython-notebooks.git synced 2024-03-22 13:30:56 +08:00
Code Issues Projects Releases Wiki Activity

Added functions snippet IPython Notebook.

Browse Source
This commit is contained in:
Donne Martin 2015-01-26 13:56:49 -05:00
parent 6fa1d5f20e
commit 42f6f9f6b5
4 changed files with 207 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -7,6 +7,7 @@ IPython Notebooks geared towards Python data analysis (core Python, NumPy, panda
* [data structures](http://nbviewer.ipython.org/github/donnemartin/pydatanotebooks/blob/master/core/structs.ipynb)
* [data structure utilities](http://nbviewer.ipython.org/github/donnemartin/pydatanotebooks/blob/master/core/structs_utils.ipynb)
* [functions](http://nbviewer.ipython.org/github/donnemartin/pydatanotebooks/blob/master/core/functions.ipynb)
* [datetime](http://nbviewer.ipython.org/github/donnemartin/pydatanotebooks/blob/master/core/datetime.ipynb)
* [unit tests](http://nbviewer.ipython.org/github/donnemartin/pydatanotebooks/blob/master/core/unit_tests.ipynb)

159
core/functions.ipynb Normal file
View File

@ -0,0 +1,159 @@
{
"metadata": {
"name": "",
"signature": "sha256:8c91cadf8bbcbcdd5a60fc0a89e964b846a6f5328eaa57d57afbaedda06ad3ca"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Functions"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* Functions as Objects\n",
"* Lambdas\n",
"* Closures\n",
"* \\*args, \\*\\*kwargs\n",
"* Currying\n",
"* Generators\n",
"* Generator Expressions"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Functions as Objects"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Python treats functions as objects which can simplify data cleaning"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"%%file transform_util.py\n",
"import re\n",
"\n",
"\n",
"class TransformUtil:\n",
"\n",
" @classmethod\n",
" def remove_punctuation(cls, value):\n",
" \"\"\"Removes !, #, and ?.\n",
" \"\"\" \n",
" return re.sub('[!#?]', '', value) \n",
"\n",
" @classmethod\n",
" def clean_strings(cls, strings, ops): \n",
" \"\"\"General purpose method to clean strings.\n",
"\n",
" Pass in a sequence of strings and the operations to perform.\n",
" \"\"\" \n",
" result = [] \n",
" for value in strings: \n",
" for function in ops: \n",
" value = function(value) \n",
" result.append(value) \n",
" return result"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Overwriting transform_util.py\n"
]
}
],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"%%file tests/test_transform_util.py\n",
"from nose.tools import assert_equal\n",
"from ..transform_util import TransformUtil\n",
"\n",
"\n",
"class TestTransformUtil():\n",
"\n",
" states = [' Alabama ', 'Georgia!', 'Georgia', 'georgia', \\\n",
" 'FlOrIda', 'south carolina##', 'West virginia?']\n",
" \n",
" expected_output = ['Alabama',\n",
" 'Georgia',\n",
" 'Georgia',\n",
" 'Georgia',\n",
" 'Florida',\n",
" 'South Carolina',\n",
" 'West Virginia']\n",
" \n",
" def test_remove_punctuation(self):\n",
" assert_equal(TransformUtil.remove_punctuation('!#?'), '')\n",
"\n",
" def test_clean_strings(self):\n",
" clean_ops = [str.strip, TransformUtil.remove_punctuation, str.title] \n",
" output = TransformUtil.clean_strings(self.states, clean_ops)\n",
" assert_equal(output, self.expected_output)\n"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Overwriting tests/test_transform_util.py\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!nosetests tests/test_transform_util.py -v"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"core.tests.test_transform_util.TestTransformUtil.test_clean_strings ... ok\r\n",
"core.tests.test_transform_util.TestTransformUtil.test_remove_punctuation ... ok\r\n",
"\r\n",
"----------------------------------------------------------------------\r\n",
"Ran 2 tests in 0.001s\r\n",
"\r\n",
"OK\r\n"
]
}
],
"prompt_number": 3
}
],
"metadata": {}
}
]
}

24
core/tests/test_transform_util.py Normal file
View File

@ -0,0 +1,24 @@
from nose.tools import assert_equal
from ..transform_util import TransformUtil
class TestTransformUtil():
states = [' Alabama ', 'Georgia!', 'Georgia', 'georgia', \
'FlOrIda', 'south carolina##', 'West virginia?']
expected_output = ['Alabama',
'Georgia',
'Georgia',
'Georgia',
'Florida',
'South Carolina',
'West Virginia']
def test_remove_punctuation(self):
assert_equal(TransformUtil.remove_punctuation('!#?'), '')
def test_clean_strings(self):
clean_ops = [str.strip, TransformUtil.remove_punctuation, str.title]
output = TransformUtil.clean_strings(self.states, clean_ops)
assert_equal(output, self.expected_output)

23
core/transform_util.py Normal file
View File

@ -0,0 +1,23 @@
import re
class TransformUtil:
@classmethod
def remove_punctuation(cls, value):
"""Removes !, #, and ?.
"""
return re.sub('[!#?]', '', value)
@classmethod
def clean_strings(cls, strings, ops):
"""General purpose method to clean strings.
Pass in a sequence of strings and the operations to perform.
"""
result = []
for value in strings:
for function in ops:
value = function(value)
result.append(value)
return result