notebook.community

Edit and run



In [1]:

    
import pandas as pd









    



/Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages/matplotlib/__init__.py:1035: UserWarning: Duplicate key in file "/Users/mercybenzaquen/.matplotlib/matplotlibrc", line #2
  (fname, cnt))



In [2]:

    
!pip install pandas









    



Requirement already satisfied (use --upgrade to upgrade): pandas in /Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages
Requirement already satisfied (use --upgrade to upgrade): numpy>=1.7.0 in /Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages (from pandas)
Requirement already satisfied (use --upgrade to upgrade): pytz>=2011k in /Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages (from pandas)
Requirement already satisfied (use --upgrade to upgrade): python-dateutil>=2 in /Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages (from pandas)
Requirement already satisfied (use --upgrade to upgrade): six>=1.5 in /Users/mercybenzaquen/.virtualenvs/Homework7/lib/python3.5/site-packages (from python-dateutil>=2->pandas)



In [3]:

    
import pandas as pd



In [8]:

    
df = pd.read_csv("congress.csv", error_bad_lines=False) 
#I got an error saying CParserError: Error tokenizing data pandas
#so I added error_bad_lines=False.









    



b'Skipping line 7054: expected 13 fields, saw 14\nSkipping line 7581: expected 13 fields, saw 14\nSkipping line 8088: expected 13 fields, saw 14\nSkipping line 9719: expected 13 fields, saw 15\nSkipping line 10019: expected 13 fields, saw 15\nSkipping line 10235: expected 13 fields, saw 15\nSkipping line 10550: expected 13 fields, saw 15\nSkipping line 10641: expected 13 fields, saw 14\nSkipping line 10764: expected 13 fields, saw 15\nSkipping line 11075: expected 13 fields, saw 15\nSkipping line 11168: expected 13 fields, saw 14\nSkipping line 11290: expected 13 fields, saw 15\nSkipping line 11606: expected 13 fields, saw 15\nSkipping line 11697: expected 13 fields, saw 14\nSkipping line 12141: expected 13 fields, saw 15\nSkipping line 12230: expected 13 fields, saw 14\nSkipping line 12664: expected 13 fields, saw 15\nSkipping line 12738: expected 13 fields, saw 14\n'



In [10]:

    
df.head()









    Out[10]:






  
    
      
      congress
      chamber
      bioguide
      firstname
      middlename
      lastname
      suffix
      birthday
      state
      party
      incumbent
      termstart
      age
    
  
  
    
      0
      80
      house
      M000112
      Joseph
      Jefferson
      Mansfield
      NaN
      1861-02-09
      TX
      D
      Yes
      1947-01-03
      85.9
    
    
      1
      80
      house
      D000448
      Robert
      Lee
      Doughton
      NaN
      1863-11-07
      NC
      D
      Yes
      1947-01-03
      83.2
    
    
      2
      80
      house
      S000001
      Adolph
      Joachim
      Sabath
      NaN
      1866-04-04
      IL
      D
      Yes
      1947-01-03
      80.7
    
    
      3
      80
      house
      E000023
      Charles
      Aubrey
      Eaton
      NaN
      1868-03-29
      NJ
      R
      Yes
      1947-01-03
      78.8
    
    
      4
      80
      house
      L000296
      William
      NaN
      Lewis
      NaN
      1868-09-22
      KY
      R
      No
      1947-01-03
      78.3



In [ ]:

	congress	chamber	bioguide	firstname	middlename	lastname	suffix	birthday	state	party	incumbent	termstart	age
0	80	house	M000112	Joseph	Jefferson	Mansfield	NaN	1861-02-09	TX	D	Yes	1947-01-03	85.9
1	80	house	D000448	Robert	Lee	Doughton	NaN	1863-11-07	NC	D	Yes	1947-01-03	83.2
2	80	house	S000001	Adolph	Joachim	Sabath	NaN	1866-04-04	IL	D	Yes	1947-01-03	80.7
3	80	house	E000023	Charles	Aubrey	Eaton	NaN	1868-03-29	NJ	R	Yes	1947-01-03	78.8
4	80	house	L000296	William	NaN	Lewis	NaN	1868-09-22	KY	R	No	1947-01-03	78.3