Notebook

Example: 2012 Federal Election Commission Database¶

In [3]:

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

In [5]:

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

In [6]:

fec

Out[6]:

	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

In [7]:

fec.ix[123456]

Out[7]:

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

In [8]:

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

Out[8]:

'Obama, Barack'

In [9]:

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'}

In [10]:

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()

Out[10]:

Democrat      593746
Republican    407985
dtype: int64

In [11]:

(fec.contb_receipt_amt > 0).value_counts()

Out[11]:

True     991475
False     10256
dtype: int64

In [12]:

fec = fec[fec.contb_receipt_amt > 0]

In [15]:

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