mirror of
https://github.com/donnemartin/data-science-ipython-notebooks.git
synced 2024-03-22 13:30:56 +08:00
618 lines
13 KiB
Plaintext
618 lines
13 KiB
Plaintext
{
|
|
"metadata": {
|
|
"name": "",
|
|
"signature": "sha256:13e6414e26c196bc6cbaf0093750187f11c2637e20975d01f8e38416d518abb0"
|
|
},
|
|
"nbformat": 3,
|
|
"nbformat_minor": 0,
|
|
"worksheets": [
|
|
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Basics"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## References"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"a = [1, 2, 3]\n",
|
|
"b = a\n",
|
|
"a == b"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 1,
|
|
"text": [
|
|
"True"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 1
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"a is b"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 2,
|
|
"text": [
|
|
"True"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 2
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# list always creates a new list\n",
|
|
"c = list(a)\n",
|
|
"a == c"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 3,
|
|
"text": [
|
|
"True"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 3
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"a is c"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 4,
|
|
"text": [
|
|
"False"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 4
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Types"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# Knowing the type of an object is important, as it's useful to write \n",
|
|
"# functions that can handle many types of input.\n",
|
|
"type('foo')"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 5,
|
|
"text": [
|
|
"str"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 5
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# isinstance can take a type or tuple\n",
|
|
"isinstance(7, (int, float))"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 6,
|
|
"text": [
|
|
"True"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 6
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Attributes and Methods"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# List all attributes and methods\n",
|
|
"dir('foo')"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 7,
|
|
"text": [
|
|
"['__add__',\n",
|
|
" '__class__',\n",
|
|
" '__contains__',\n",
|
|
" '__delattr__',\n",
|
|
" '__doc__',\n",
|
|
" '__eq__',\n",
|
|
" '__format__',\n",
|
|
" '__ge__',\n",
|
|
" '__getattribute__',\n",
|
|
" '__getitem__',\n",
|
|
" '__getnewargs__',\n",
|
|
" '__getslice__',\n",
|
|
" '__gt__',\n",
|
|
" '__hash__',\n",
|
|
" '__init__',\n",
|
|
" '__le__',\n",
|
|
" '__len__',\n",
|
|
" '__lt__',\n",
|
|
" '__mod__',\n",
|
|
" '__mul__',\n",
|
|
" '__ne__',\n",
|
|
" '__new__',\n",
|
|
" '__reduce__',\n",
|
|
" '__reduce_ex__',\n",
|
|
" '__repr__',\n",
|
|
" '__rmod__',\n",
|
|
" '__rmul__',\n",
|
|
" '__setattr__',\n",
|
|
" '__sizeof__',\n",
|
|
" '__str__',\n",
|
|
" '__subclasshook__',\n",
|
|
" '_formatter_field_name_split',\n",
|
|
" '_formatter_parser',\n",
|
|
" 'capitalize',\n",
|
|
" 'center',\n",
|
|
" 'count',\n",
|
|
" 'decode',\n",
|
|
" 'encode',\n",
|
|
" 'endswith',\n",
|
|
" 'expandtabs',\n",
|
|
" 'find',\n",
|
|
" 'format',\n",
|
|
" 'index',\n",
|
|
" 'isalnum',\n",
|
|
" 'isalpha',\n",
|
|
" 'isdigit',\n",
|
|
" 'islower',\n",
|
|
" 'isspace',\n",
|
|
" 'istitle',\n",
|
|
" 'isupper',\n",
|
|
" 'join',\n",
|
|
" 'ljust',\n",
|
|
" 'lower',\n",
|
|
" 'lstrip',\n",
|
|
" 'partition',\n",
|
|
" 'replace',\n",
|
|
" 'rfind',\n",
|
|
" 'rindex',\n",
|
|
" 'rjust',\n",
|
|
" 'rpartition',\n",
|
|
" 'rsplit',\n",
|
|
" 'rstrip',\n",
|
|
" 'split',\n",
|
|
" 'splitlines',\n",
|
|
" 'startswith',\n",
|
|
" 'strip',\n",
|
|
" 'swapcase',\n",
|
|
" 'title',\n",
|
|
" 'translate',\n",
|
|
" 'upper',\n",
|
|
" 'zfill']"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 7
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# Access help\n",
|
|
"help(str.upper)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"Help on method_descriptor:\n",
|
|
"\n",
|
|
"upper(...)\n",
|
|
" S.upper() -> string\n",
|
|
" \n",
|
|
" Return a copy of the string S converted to uppercase.\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 8
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# Access an attribute or method by name\n",
|
|
"# getattr, hasattr, and setattr can be used to write generic, reusable code\n",
|
|
"getattr('foo', 'split')"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 9,
|
|
"text": [
|
|
"<function split>"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 9
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Duck Typing Utilities"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"%%file type_util.py\n",
|
|
"class Util:\n",
|
|
"\n",
|
|
" @classmethod\n",
|
|
" def is_iterable(cls, obj):\n",
|
|
" \"\"\"Determines if obj is iterable.\n",
|
|
"\n",
|
|
" Useful when writing functions that can accept multiple types of\n",
|
|
" input (list, tuple, ndarray, iterator). Pairs well with\n",
|
|
" convert_to_list.\n",
|
|
" \"\"\"\n",
|
|
" try:\n",
|
|
" iter(obj)\n",
|
|
" return True\n",
|
|
" except TypeError:\n",
|
|
" return False\n",
|
|
"\n",
|
|
" @classmethod\n",
|
|
" def convert_to_list(cls, obj):\n",
|
|
" \"\"\"Converts obj to a list if it is not a list and it is iterable, else\n",
|
|
" returns the original obj.\n",
|
|
" \"\"\"\n",
|
|
" if not isinstance(obj, list) and cls.is_iterable(obj):\n",
|
|
" obj = list(obj)\n",
|
|
" return obj\n"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"Overwriting type_util.py\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 10
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Duck Typing Utilities Unit Tests"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"%%file tests/test_type_util.py\n",
|
|
"from nose.tools import assert_equal\n",
|
|
"from pydatasnippets.core.type_util import Util\n",
|
|
"\n",
|
|
"\n",
|
|
"class TestUtil():\n",
|
|
"\n",
|
|
" def test_is_iterable(self):\n",
|
|
" assert_equal(Util.is_iterable('foo'), True)\n",
|
|
" assert_equal(Util.is_iterable(7), False)\n",
|
|
"\n",
|
|
" def test_convert_to_list(self):\n",
|
|
" assert_equal(isinstance(Util.convert_to_list('foo'), list), True)\n",
|
|
" assert_equal(isinstance(Util.convert_to_list(7), list), False)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"Overwriting tests/test_type_util.py\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 11
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"!nosetests tests/test_type_util.py"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"..\r\n",
|
|
"----------------------------------------------------------------------\r\n",
|
|
"Ran 2 tests in 0.001s\r\n",
|
|
"\r\n",
|
|
"OK\r\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 12
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Exceptions"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"def convert_to_float(x):\n",
|
|
" try:\n",
|
|
" x = float(x)\n",
|
|
" except ValueError:\n",
|
|
" print('Failed')\n",
|
|
" else: \n",
|
|
" # Executes only when try succeeds\n",
|
|
" print('Succeeded')\n",
|
|
" finally: \n",
|
|
" # Always executes\n",
|
|
" print('Completed convert_to_float')\n",
|
|
" return x"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"prompt_number": 13
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"x = convert_to_float('7')\n",
|
|
"x"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"Succeeded\n",
|
|
"Completed convert_to_float\n"
|
|
]
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 14,
|
|
"text": [
|
|
"7.0"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 14
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"x = convert_to_float('a')\n",
|
|
"x"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"Failed\n",
|
|
"Completed convert_to_float\n"
|
|
]
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 15,
|
|
"text": [
|
|
"'a'"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 15
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## range and xrange"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# Note: range is no longer avalable in Python 3\n",
|
|
"# Generate a list of evenly spaced integers\n",
|
|
"range(10)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 16,
|
|
"text": [
|
|
"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 16
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# Range can take start, stop, and step arguments\n",
|
|
"range(0, 20, 3)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"metadata": {},
|
|
"output_type": "pyout",
|
|
"prompt_number": 17,
|
|
"text": [
|
|
"[0, 3, 6, 9, 12, 15, 18]"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 17
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# It is very common to iterate through sequences by index with range\n",
|
|
"seq = [1, 2, 3]\n",
|
|
"for i in range(len(seq)):\n",
|
|
" val = seq[i]\n",
|
|
" print(val)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"1\n",
|
|
"2\n",
|
|
"3\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 18
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [
|
|
"# xrange is recommended for longer ranges and is available in Python 3 as \n",
|
|
"# range. It returns an iterator that generates integers one by one rather\n",
|
|
"# than all at once and storing them in a large list.\n",
|
|
"sum = 0\n",
|
|
"for i in xrange(100000):\n",
|
|
" if i % 2 == 0:\n",
|
|
" sum += 1\n",
|
|
"print(sum)"
|
|
],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"stream": "stdout",
|
|
"text": [
|
|
"50000\n"
|
|
]
|
|
}
|
|
],
|
|
"prompt_number": 19
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"collapsed": false,
|
|
"input": [],
|
|
"language": "python",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"prompt_number": 19
|
|
}
|
|
],
|
|
"metadata": {}
|
|
}
|
|
]
|
|
} |