加入 Gitee

与超过 1200万开发者一起发现、参与优秀开源项目，私有仓库也完全免费：）

文件

克隆/下载

fec_study.ipynb 20.93 KB

{
 "metadata": {
  "name": "",
  "signature": "sha256:28f034a531b1925724959079a55f964ded07e33205fc78a28e8e1109a5cb8032"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Example: 2012 Federal Election Commission Database"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import division\n",
      "from numpy.random import randn\n",
      "import numpy as np\n",
      "import os\n",
      "import matplotlib.pyplot as plt\n",
      "np.random.seed(12345)\n",
      "plt.rc('figure', figsize=(10, 6))\n",
      "from pandas import *\n",
      "import pandas\n",
      "np.set_printoptions(precision=4)\n",
      "%cd book_scripts/fec"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/home/phillip/Documents/code/py/pandas-book/rev_539000/book_scripts/fec\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec = read_csv('P00000001-ALL.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>cmte_id</th>\n",
        "      <th>cand_id</th>\n",
        "      <th>cand_nm</th>\n",
        "      <th>contbr_nm</th>\n",
        "      <th>contbr_city</th>\n",
        "      <th>...</th>\n",
        "      <th>receipt_desc</th>\n",
        "      <th>memo_cd</th>\n",
        "      <th>memo_text</th>\n",
        "      <th>form_tp</th>\n",
        "      <th>file_num</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>             HARVEY, WILLIAM</td>\n",
        "      <td>             MOBILE</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 736166</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>             HARVEY, WILLIAM</td>\n",
        "      <td>             MOBILE</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 736166</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>               SMITH, LANIER</td>\n",
        "      <td>             LANETT</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 749073</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>            BLEVINS, DARONDA</td>\n",
        "      <td>            PIGGOTT</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 749073</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>          WARDENBURG, HAROLD</td>\n",
        "      <td> HOT SPRINGS NATION</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 736166</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>              BECKMAN, JAMES</td>\n",
        "      <td>         SPRINGDALE</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 736166</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6      </th>\n",
        "      <td> C00410118</td>\n",
        "      <td> P20002978</td>\n",
        "      <td> Bachmann, Michelle</td>\n",
        "      <td>            BLEVINS, DARONDA</td>\n",
        "      <td>            PIGGOTT</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 736166</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001724</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td> HEFFERNAN, JILL PRINCE MRS.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001725</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>            ELWOOD, MIKE MR.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001726</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>        GORMAN, CHRIS D. MR.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td> REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...</td>\n",
        "      <td> NaN</td>\n",
        "      <td> REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001727</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>         DUFFY, DAVID A. MR.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001728</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>         GRANE, BRYAN F. MR.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001729</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>          TOLBERT, DARYL MR.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1001730</th>\n",
        "      <td> C00500587</td>\n",
        "      <td> P20003281</td>\n",
        "      <td>        Perry, Rick</td>\n",
        "      <td>      ANDERSON, MARILEE MRS.</td>\n",
        "      <td>     INFO REQUESTED</td>\n",
        "      <td>...</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>                                               NaN</td>\n",
        "      <td> SA17A</td>\n",
        "      <td> 751678</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>1001731 rows \u00d7 16 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "           cmte_id    cand_id             cand_nm  \\\n",
        "0        C00410118  P20002978  Bachmann, Michelle   \n",
        "1        C00410118  P20002978  Bachmann, Michelle   \n",
        "2        C00410118  P20002978  Bachmann, Michelle   \n",
        "3        C00410118  P20002978  Bachmann, Michelle   \n",
        "4        C00410118  P20002978  Bachmann, Michelle   \n",
        "5        C00410118  P20002978  Bachmann, Michelle   \n",
        "6        C00410118  P20002978  Bachmann, Michelle   \n",
        "...            ...        ...                 ...   \n",
        "1001724  C00500587  P20003281         Perry, Rick   \n",
        "1001725  C00500587  P20003281         Perry, Rick   \n",
        "1001726  C00500587  P20003281         Perry, Rick   \n",
        "1001727  C00500587  P20003281         Perry, Rick   \n",
        "1001728  C00500587  P20003281         Perry, Rick   \n",
        "1001729  C00500587  P20003281         Perry, Rick   \n",
        "1001730  C00500587  P20003281         Perry, Rick   \n",
        "\n",
        "                           contbr_nm         contbr_city         ...          \\\n",
        "0                    HARVEY, WILLIAM              MOBILE         ...           \n",
        "1                    HARVEY, WILLIAM              MOBILE         ...           \n",
        "2                      SMITH, LANIER              LANETT         ...           \n",
        "3                   BLEVINS, DARONDA             PIGGOTT         ...           \n",
        "4                 WARDENBURG, HAROLD  HOT SPRINGS NATION         ...           \n",
        "5                     BECKMAN, JAMES          SPRINGDALE         ...           \n",
        "6                   BLEVINS, DARONDA             PIGGOTT         ...           \n",
        "...                              ...                 ...         ...           \n",
        "1001724  HEFFERNAN, JILL PRINCE MRS.      INFO REQUESTED         ...           \n",
        "1001725             ELWOOD, MIKE MR.      INFO REQUESTED         ...           \n",
        "1001726         GORMAN, CHRIS D. MR.      INFO REQUESTED         ...           \n",
        "1001727          DUFFY, DAVID A. MR.      INFO REQUESTED         ...           \n",
        "1001728          GRANE, BRYAN F. MR.      INFO REQUESTED         ...           \n",
        "1001729           TOLBERT, DARYL MR.      INFO REQUESTED         ...           \n",
        "1001730       ANDERSON, MARILEE MRS.      INFO REQUESTED         ...           \n",
        "\n",
        "                                              receipt_desc memo_cd  \\\n",
        "0                                                      NaN     NaN   \n",
        "1                                                      NaN     NaN   \n",
        "2                                                      NaN     NaN   \n",
        "3                                                      NaN     NaN   \n",
        "4                                                      NaN     NaN   \n",
        "5                                                      NaN     NaN   \n",
        "6                                                      NaN     NaN   \n",
        "...                                                    ...     ...   \n",
        "1001724                                                NaN     NaN   \n",
        "1001725                                                NaN     NaN   \n",
        "1001726  REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...     NaN   \n",
        "1001727                                                NaN     NaN   \n",
        "1001728                                                NaN     NaN   \n",
        "1001729                                                NaN     NaN   \n",
        "1001730                                                NaN     NaN   \n",
        "\n",
        "                                                 memo_text form_tp  file_num  \n",
        "0                                                      NaN   SA17A    736166  \n",
        "1                                                      NaN   SA17A    736166  \n",
        "2                                                      NaN   SA17A    749073  \n",
        "3                                                      NaN   SA17A    749073  \n",
        "4                                                      NaN   SA17A    736166  \n",
        "5                                                      NaN   SA17A    736166  \n",
        "6                                                      NaN   SA17A    736166  \n",
        "...                                                    ...     ...       ...  \n",
        "1001724                                                NaN   SA17A    751678  \n",
        "1001725                                                NaN   SA17A    751678  \n",
        "1001726  REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...   SA17A    751678  \n",
        "1001727                                                NaN   SA17A    751678  \n",
        "1001728                                                NaN   SA17A    751678  \n",
        "1001729                                                NaN   SA17A    751678  \n",
        "1001730                                                NaN   SA17A    751678  \n",
        "\n",
        "[1001731 rows x 16 columns]"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec.ix[123456]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "cmte_id            C00431445\n",
        "cand_id            P80003338\n",
        "cand_nm        Obama, Barack\n",
        "contbr_nm        ELLMAN, IRA\n",
        "contbr_city            TEMPE\n",
        "...\n",
        "contb_receipt_dt    01-DEC-11\n",
        "receipt_desc              NaN\n",
        "memo_cd                   NaN\n",
        "memo_text                 NaN\n",
        "form_tp                 SA17A\n",
        "file_num               772372\n",
        "Name: 123456, Length: 16, dtype: object"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "unique_cands = fec.cand_nm.unique()\n",
      "unique_cands\n",
      "unique_cands[2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "'Obama, Barack'"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parties = {'Bachmann, Michelle': 'Republican',\n",
      "           'Cain, Herman': 'Republican',\n",
      "           'Gingrich, Newt': 'Republican',\n",
      "           'Huntsman, Jon': 'Republican',\n",
      "           'Johnson, Gary Earl': 'Republican',\n",
      "           'McCotter, Thaddeus G': 'Republican',\n",
      "           'Obama, Barack': 'Democrat',\n",
      "           'Paul, Ron': 'Republican',\n",
      "           'Pawlenty, Timothy': 'Republican',\n",
      "           'Perry, Rick': 'Republican',\n",
      "           \"Roemer, Charles E. 'Buddy' III\": 'Republican',\n",
      "           'Romney, Mitt': 'Republican',\n",
      "           'Santorum, Rick': 'Republican'}"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "raw",
     "metadata": {},
     "source": [
      "parties = {'Bachmann, Michelle': 'Republican',\n",
      "           'Cain, Herman': 'Republican',\n",
      "           'Gingrich, Newt': 'Republican',\n",
      "           'Huntsman, Jon': 'Republican',\n",
      "           'Johnson, Gary Earl': 'Republican',\n",
      "           'McCotter, Thaddeus G': 'Republican',\n",
      "           'Obama, Barack': 'Democrat',\n",
      "           'Paul, Ron': 'Republican',\n",
      "           'Pawlenty, Timothy': 'Republican',\n",
      "           'Perry, Rick': 'Republican',\n",
      "           \"Roemer, Charles E. 'Buddy' III\": 'Republican',\n",
      "           'Romney, Mitt': 'Republican',\n",
      "           'Santorum, Rick': 'Republican'}"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec.cand_nm[123456:123461]\n",
      "fec.cand_nm[123456:123461].map(parties)\n",
      "# Add it as a column\n",
      "fec['party'] = fec.cand_nm.map(parties)\n",
      "fec['party'].value_counts()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "Democrat      593746\n",
        "Republican    407985\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "(fec.contb_receipt_amt > 0).value_counts()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "True     991475\n",
        "False     10256\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec = fec[fec.contb_receipt_amt > 0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fec_mrbo = fec[fec.cand_nm.isin(['Obama, Barack', 'Romney, Mitt'])]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    }
   ],
   "metadata": {}
  }
 ]
}

一键复制编辑原始数据按行查看历史

提交于 11年前 . add updated ipython notebooks from cpcloud

Example: 2012 Federal Election Commission Database

from __future__ import division
from numpy.random import randn
import numpy as np
import os
import matplotlib.pyplot as plt
np.random.seed(12345)
plt.rc('figure', figsize=(10, 6))
from pandas import *
import pandas
np.set_printoptions(precision=4)
%cd book_scripts/fec

/home/phillip/Documents/code/py/pandas-book/rev_539000/book_scripts/fec

fec = read_csv('P00000001-ALL.csv')

fec

	cmte_id	cand_id	cand_nm	contbr_nm	contbr_city	...	receipt_desc	memo_cd	memo_text	form_tp	file_num
0	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	...	NaN	NaN	NaN	SA17A	736166
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	...	NaN	NaN	NaN	SA17A	736166
2	C00410118	P20002978	Bachmann, Michelle	SMITH, LANIER	LANETT	...	NaN	NaN	NaN	SA17A	749073
3	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	...	NaN	NaN	NaN	SA17A	749073
4	C00410118	P20002978	Bachmann, Michelle	WARDENBURG, HAROLD	HOT SPRINGS NATION	...	NaN	NaN	NaN	SA17A	736166
5	C00410118	P20002978	Bachmann, Michelle	BECKMAN, JAMES	SPRINGDALE	...	NaN	NaN	NaN	SA17A	736166
6	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	...	NaN	NaN	NaN	SA17A	736166
...	...	...	...	...	...	...	...	...	...	...	...
1001724	C00500587	P20003281	Perry, Rick	HEFFERNAN, JILL PRINCE MRS.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678
1001725	C00500587	P20003281	Perry, Rick	ELWOOD, MIKE MR.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678
1001726	C00500587	P20003281	Perry, Rick	GORMAN, CHRIS D. MR.	INFO REQUESTED	...	REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...	NaN	REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...	SA17A	751678
1001727	C00500587	P20003281	Perry, Rick	DUFFY, DAVID A. MR.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678
1001728	C00500587	P20003281	Perry, Rick	GRANE, BRYAN F. MR.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678
1001729	C00500587	P20003281	Perry, Rick	TOLBERT, DARYL MR.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678
1001730	C00500587	P20003281	Perry, Rick	ANDERSON, MARILEE MRS.	INFO REQUESTED	...	NaN	NaN	NaN	SA17A	751678

1001731 rows × 16 columns

fec.ix[123456]

cmte_id            C00431445
cand_id            P80003338
cand_nm        Obama, Barack
contbr_nm        ELLMAN, IRA
contbr_city            TEMPE
...
contb_receipt_dt    01-DEC-11
receipt_desc              NaN
memo_cd                   NaN
memo_text                 NaN
form_tp                 SA17A
file_num               772372
Name: 123456, Length: 16, dtype: object

unique_cands = fec.cand_nm.unique()
unique_cands
unique_cands[2]

'Obama, Barack'

parties = {'Bachmann, Michelle': 'Republican',
           'Cain, Herman': 'Republican',
           'Gingrich, Newt': 'Republican',
           'Huntsman, Jon': 'Republican',
           'Johnson, Gary Earl': 'Republican',
           'McCotter, Thaddeus G': 'Republican',
           'Obama, Barack': 'Democrat',
           'Paul, Ron': 'Republican',
           'Pawlenty, Timothy': 'Republican',
           'Perry, Rick': 'Republican',
           "Roemer, Charles E. 'Buddy' III": 'Republican',
           'Romney, Mitt': 'Republican',
           'Santorum, Rick': 'Republican'}

parties = {'Bachmann, Michelle': 'Republican', 'Cain, Herman': 'Republican', 'Gingrich, Newt': 'Republican', 'Huntsman, Jon': 'Republican', 'Johnson, Gary Earl': 'Republican', 'McCotter, Thaddeus G': 'Republican', 'Obama, Barack': 'Democrat', 'Paul, Ron': 'Republican', 'Pawlenty, Timothy': 'Republican', 'Perry, Rick': 'Republican', "Roemer, Charles E. 'Buddy' III": 'Republican', 'Romney, Mitt': 'Republican', 'Santorum, Rick': 'Republican'}

fec.cand_nm[123456:123461]
fec.cand_nm[123456:123461].map(parties)
# Add it as a column
fec['party'] = fec.cand_nm.map(parties)
fec['party'].value_counts()

Democrat      593746
Republican    407985
dtype: int64

(fec.contb_receipt_amt > 0).value_counts()

True     991475
False     10256
dtype: int64

fec = fec[fec.contb_receipt_amt > 0]

fec_mrbo = fec[fec.cand_nm.isin(['Obama, Barack', 'Romney, Mitt'])]

马建仓 AI 助手

尝试更多

代码解读

代码找茬

代码优化

https://gitee.com/python-deathfans/pydata-book.git

git@gitee.com:python-deathfans/pydata-book.git

python-deathfans

pydata-book

1st-edition

大象乔布斯/pydata-book

Example: 2012 Federal Election Commission Database

简介

发行版

贡献者

近期动态

大象乔布斯/pydata-book .gitee-modal { width: 500px !important; }

Example: 2012 Federal Election Commission Database

简介

发行版

贡献者

近期动态

搜索帮助

大象乔布斯/pydata-book