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 Series ranking snippets. Tweaked some of the comments positions relative to the code. Minor tweaks to some snippets.

Browse Source
This commit is contained in:
Donne Martin 2015-02-01 07:33:19 -05:00
parent 91cdd02752
commit 3f5e508eb6
1 changed files with 250 additions and 115 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

365
pandas/pandas.ipynb
View File

@ -1,7 +1,7 @@
{ {
"metadata": { "metadata": {
"name": "", "name": "",
"signature": "sha256:17491453ae73630f23f856b3c0724fbd00a52c4f53b239a07e340ec3113ea230" "signature": "sha256:2b6aa402b58aa2da8c06d378f19732970903abe573b39f9a7490982d0e2ebcbc"
}, },
"nbformat": 3, "nbformat": 3,
"nbformat_minor": 0, "nbformat_minor": 0,
@ -3331,6 +3331,13 @@
"## Arithmetic and Data Alignment" "## Arithmetic and Data Alignment"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Adding Series objects results in the union of index pairs if the pairs are not the same, resulting in NaN for indices that do not overlap:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3338,7 +3345,7 @@
"np.random.seed(0)\n", "np.random.seed(0)\n",
"ser_6 = Series(np.random.randn(5),\n", "ser_6 = Series(np.random.randn(5),\n",
" index=['a', 'b', 'c', 'd', 'e'])\n", " index=['a', 'b', 'c', 'd', 'e'])\n",
"ser_6\n" "ser_6"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -3387,13 +3394,6 @@
], ],
"prompt_number": 65 "prompt_number": 65
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Adding objects results in the union of index pairs if the pairs are not the same, resulting in NaN for indices that do not overlap:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3455,6 +3455,13 @@
], ],
"prompt_number": 67 "prompt_number": 67
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Adding DataFrame objects results in the union of index pairs for rows and columns if the pairs are not the same, resulting in NaN for indices that do not overlap:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3575,13 +3582,6 @@
], ],
"prompt_number": 69 "prompt_number": 69
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Adding objects results in the union of index pairs for rows and columns if the pairs are not the same, resulting in NaN for indices that do not overlap:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3784,6 +3784,13 @@
], ],
"prompt_number": 72 "prompt_number": 72
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Match the index of the Series on the DataFrame's columns, broadcasting down the rows and union the indices that do not match:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3808,13 +3815,6 @@
], ],
"prompt_number": 73 "prompt_number": 73
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Match the index of the Series on the DataFrame's columns, broadcasting down the rows and union the indices that do not match:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3880,6 +3880,13 @@
], ],
"prompt_number": 74 "prompt_number": 74
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Broadcast over the columns and match the rows (axis=0) by using an arithmetic method:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
@ -3946,37 +3953,30 @@
"collapsed": false, "collapsed": false,
"input": [ "input": [
"ser_10 = Series([100, 200, 300])\n", "ser_10 = Series([100, 200, 300])\n",
"print ser_10" "ser_10"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"output_type": "stream", "metadata": {},
"stream": "stdout", "output_type": "pyout",
"prompt_number": 76,
"text": [ "text": [
"0 100\n", "0 100\n",
"1 200\n", "1 200\n",
"2 300\n", "2 300\n",
"dtype: int64\n" "dtype: int64"
] ]
} }
], ],
"prompt_number": 76 "prompt_number": 76
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Broadcast over the columns and match the rows (axis=0) by using an arithmetic method:"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_11 = df_10.sub(ser_10, axis=0)\n", "df_10.sub(ser_10, axis=0)"
"df_11"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4051,8 +4051,8 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_12 = np.abs(df_11)\n", "df_11 = np.abs(df_11)\n",
"df_12" "df_11"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4073,24 +4073,24 @@
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td> 99.451186</td>\n", " <td> 0.000000</td>\n",
" <td> 98.867789</td>\n", " <td> 0.000000</td>\n",
" <td> 98.676912</td>\n", " <td> 0.000000</td>\n",
" <td> 99.999886</td>\n", " <td> 0.000000</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>1</th>\n", " <th>1</th>\n",
" <td> 199.455117</td>\n", " <td> 0.003930</td>\n",
" <td> 199.274013</td>\n", " <td> 0.406224</td>\n",
" <td> 199.207350</td>\n", " <td> 0.530438</td>\n",
" <td> 199.907661</td>\n", " <td> 0.092224</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>2</th>\n", " <th>2</th>\n",
" <td> 299.562413</td>\n", " <td> 0.111226</td>\n",
" <td> 298.921967</td>\n", " <td> 0.054178</td>\n",
" <td> 298.690777</td>\n", " <td> 0.013864</td>\n",
" <td> 299.603233</td>\n", " <td> 0.396653</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
@ -4100,10 +4100,10 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 78, "prompt_number": 78,
"text": [ "text": [
" a b c d\n", " a b c d\n",
"0 99.451186 98.867789 98.676912 99.999886\n", "0 0.000000 0.000000 0.000000 0.000000\n",
"1 199.455117 199.274013 199.207350 199.907661\n", "1 0.003930 0.406224 0.530438 0.092224\n",
"2 299.562413 298.921967 298.690777 299.603233" "2 0.111226 0.054178 0.013864 0.396653"
] ]
} }
], ],
@ -4121,7 +4121,7 @@
"collapsed": false, "collapsed": false,
"input": [ "input": [
"func_1 = lambda x: x.max() - x.min()\n", "func_1 = lambda x: x.max() - x.min()\n",
"df_12.apply(func_1)" "df_11.apply(func_1)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4131,10 +4131,10 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 79, "prompt_number": 79,
"text": [ "text": [
"a 200.111226\n", "a 0.111226\n",
"b 200.054178\n", "b 0.406224\n",
"c 200.013864\n", "c 0.530438\n",
"d 199.603347\n", "d 0.396653\n",
"dtype: float64" "dtype: float64"
] ]
} }
@ -4152,7 +4152,7 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_12.apply(func_1, axis=1)" "df_11.apply(func_1, axis=1)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4162,9 +4162,9 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 80, "prompt_number": 80,
"text": [ "text": [
"0 1.322973\n", "0 0.000000\n",
"1 0.700311\n", "1 0.526508\n",
"2 0.912456\n", "2 0.382789\n",
"dtype: float64" "dtype: float64"
] ]
} }
@ -4183,7 +4183,7 @@
"collapsed": false, "collapsed": false,
"input": [ "input": [
"func_2 = lambda x: Series([x.min(), x.max()], index=['min', 'max'])\n", "func_2 = lambda x: Series([x.min(), x.max()], index=['min', 'max'])\n",
"df_12.apply(func_2)" "df_11.apply(func_2)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4204,17 +4204,17 @@
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>min</th>\n", " <th>min</th>\n",
" <td> 99.451186</td>\n", " <td> 0.000000</td>\n",
" <td> 98.867789</td>\n", " <td> 0.000000</td>\n",
" <td> 98.676912</td>\n", " <td> 0.000000</td>\n",
" <td> 99.999886</td>\n", " <td> 0.000000</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>max</th>\n", " <th>max</th>\n",
" <td> 299.562413</td>\n", " <td> 0.111226</td>\n",
" <td> 298.921967</td>\n", " <td> 0.406224</td>\n",
" <td> 298.690777</td>\n", " <td> 0.530438</td>\n",
" <td> 299.603233</td>\n", " <td> 0.396653</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
@ -4224,9 +4224,9 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 81, "prompt_number": 81,
"text": [ "text": [
" a b c d\n", " a b c d\n",
"min 99.451186 98.867789 98.676912 99.999886\n", "min 0.000000 0.000000 0.000000 0.000000\n",
"max 299.562413 298.921967 298.690777 299.603233" "max 0.111226 0.406224 0.530438 0.396653"
] ]
} }
], ],
@ -4244,7 +4244,7 @@
"collapsed": false, "collapsed": false,
"input": [ "input": [
"func_3 = lambda x: '%.2f' %x\n", "func_3 = lambda x: '%.2f' %x\n",
"df_12.applymap(func_3)" "df_11.applymap(func_3)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4265,24 +4265,24 @@
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td> 99.45</td>\n", " <td> 0.00</td>\n",
" <td> 98.87</td>\n", " <td> 0.00</td>\n",
" <td> 98.68</td>\n", " <td> 0.00</td>\n",
" <td> 100.00</td>\n", " <td> 0.00</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>1</th>\n", " <th>1</th>\n",
" <td> 199.46</td>\n", " <td> 0.00</td>\n",
" <td> 199.27</td>\n", " <td> 0.41</td>\n",
" <td> 199.21</td>\n", " <td> 0.53</td>\n",
" <td> 199.91</td>\n", " <td> 0.09</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>2</th>\n", " <th>2</th>\n",
" <td> 299.56</td>\n", " <td> 0.11</td>\n",
" <td> 298.92</td>\n", " <td> 0.05</td>\n",
" <td> 298.69</td>\n", " <td> 0.01</td>\n",
" <td> 299.60</td>\n", " <td> 0.40</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
@ -4292,10 +4292,10 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 82, "prompt_number": 82,
"text": [ "text": [
" a b c d\n", " a b c d\n",
"0 99.45 98.87 98.68 100.00\n", "0 0.00 0.00 0.00 0.00\n",
"1 199.46 199.27 199.21 199.91\n", "1 0.00 0.41 0.53 0.09\n",
"2 299.56 298.92 298.69 299.60" "2 0.11 0.05 0.01 0.40"
] ]
} }
], ],
@ -4312,7 +4312,7 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_12['a'].map(func_3)" "df_11['a'].map(func_3)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4322,9 +4322,9 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 83, "prompt_number": 83,
"text": [ "text": [
"0 99.45\n", "0 0.00\n",
"1 199.46\n", "1 0.00\n",
"2 299.56\n", "2 0.11\n",
"Name: a, dtype: object" "Name: a, dtype: object"
] ]
} }
@ -4350,7 +4350,7 @@
{ {
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 114, "prompt_number": 84,
"text": [ "text": [
"fo 100\n", "fo 100\n",
"br 200\n", "br 200\n",
@ -4360,7 +4360,7 @@
] ]
} }
], ],
"prompt_number": 114 "prompt_number": 84
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -4381,7 +4381,7 @@
{ {
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 115, "prompt_number": 85,
"text": [ "text": [
"br 200\n", "br 200\n",
"bz 300\n", "bz 300\n",
@ -4391,7 +4391,7 @@
] ]
} }
], ],
"prompt_number": 115 "prompt_number": 85
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -4412,7 +4412,7 @@
{ {
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 132, "prompt_number": 86,
"text": [ "text": [
"fo 100\n", "fo 100\n",
"br 200\n", "br 200\n",
@ -4422,16 +4422,16 @@
] ]
} }
], ],
"prompt_number": 132 "prompt_number": 86
}, },
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_13 = DataFrame(np.arange(12).reshape((3, 4)),\n", "df_12 = DataFrame(np.arange(12).reshape((3, 4)),\n",
" index=['three', 'one', 'two'],\n", " index=['three', 'one', 'two'],\n",
" columns=['c', 'a', 'b', 'd'])\n", " columns=['c', 'a', 'b', 'd'])\n",
"df_13" "df_12"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4477,7 +4477,7 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 128, "prompt_number": 87,
"text": [ "text": [
" c a b d\n", " c a b d\n",
"three 0 1 2 3\n", "three 0 1 2 3\n",
@ -4486,7 +4486,7 @@
] ]
} }
], ],
"prompt_number": 128 "prompt_number": 87
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -4499,7 +4499,7 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_13.sort_index()" "df_12.sort_index()"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4545,7 +4545,7 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 129, "prompt_number": 88,
"text": [ "text": [
" c a b d\n", " c a b d\n",
"one 4 5 6 7\n", "one 4 5 6 7\n",
@ -4554,7 +4554,7 @@
] ]
} }
], ],
"prompt_number": 129 "prompt_number": 88
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -4567,7 +4567,7 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_13.sort_index(axis=1, ascending=False)" "df_12.sort_index(axis=1, ascending=False)"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4613,7 +4613,7 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 131, "prompt_number": 89,
"text": [ "text": [
" d c b a\n", " d c b a\n",
"three 3 0 2 1\n", "three 3 0 2 1\n",
@ -4622,7 +4622,7 @@
] ]
} }
], ],
"prompt_number": 131 "prompt_number": 89
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -4635,7 +4635,7 @@
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_13.sort_index(by=['d', 'c'])" "df_12.sort_index(by=['d', 'c'])"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -4681,7 +4681,7 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 134, "prompt_number": 90,
"text": [ "text": [
" c a b d\n", " c a b d\n",
"three 0 1 2 3\n", "three 0 1 2 3\n",
@ -4690,7 +4690,142 @@
] ]
} }
], ],
"prompt_number": 134 "prompt_number": 90
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Ranking is similar to numpy.argsort except that ties are broken by assigning each group the mean rank:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"ser_11 = Series([7, -5, 7, 4, 2, 0, 4, 7])\n",
"ser_11 = ser_11.order()\n",
"ser_11"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 91,
"text": [
"1 -5\n",
"5 0\n",
"4 2\n",
"3 4\n",
"6 4\n",
"0 7\n",
"2 7\n",
"7 7\n",
"dtype: int64"
]
}
],
"prompt_number": 91
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"ser_11.rank()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 92,
"text": [
"1 1.0\n",
"5 2.0\n",
"4 3.0\n",
"3 4.5\n",
"6 4.5\n",
"0 7.0\n",
"2 7.0\n",
"7 7.0\n",
"dtype: float64"
]
}
],
"prompt_number": 92
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Rank a Series according to when they appear in the data:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"ser_11.rank(method='first')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 93,
"text": [
"1 1\n",
"5 2\n",
"4 3\n",
"3 4\n",
"6 5\n",
"0 6\n",
"2 7\n",
"7 8\n",
"dtype: float64"
]
}
],
"prompt_number": 93
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Rank a Series in descending order, using the maximum rank for the group:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"ser_11.rank(ascending=False, method='max')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 94,
"text": [
"1 8\n",
"5 7\n",
"4 6\n",
"3 5\n",
"6 5\n",
"0 3\n",
"2 3\n",
"7 3\n",
"dtype: float64"
]
}
],
"prompt_number": 94
} }
], ],
"metadata": {} "metadata": {}