Introduction



In [2]:

    
%matplotlib inline 
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt



In [5]:

    
df = pd.read_excel('2011_Current_Table1.xlsx')



In [6]:

    
df.shape









    Out[6]:





(15003, 16)



In [7]:

    
df.head()









    Out[7]:






  
    
      
      tbl
      Year
      quarter
      citymarketid_1
      citymarketid_2
      city1
      city2
      nsmiles
      passengers
      fare
      carrier_lg
      large_ms
      fare_lg
      carrier_low
      lf_ms
      fare_low
    
  
  
    
      0
      Table 1
      2011
      1
      30135
      31454
      Allentown/Bethlehem/Easton, PA
      Orlando, FL
      906
      291.777778
      119.161005
      FL
      0.687738
      112.950000
      G4
      0.119573
      84.792994
    
    
      1
      Table 1
      2011
      1
      30140
      30194
      Albuquerque, NM
      Dallas/Fort Worth, TX
      580
      532.333333
      189.705197
      WN
      0.612607
      189.172266
      WN
      0.612607
      189.172266
    
    
      2
      Table 1
      2011
      1
      30140
      30325
      Albuquerque, NM
      Denver, CO
      349
      521.777778
      114.180473
      WN
      0.449744
      111.501610
      F9
      0.319208
      104.576584
    
    
      3
      Table 1
      2011
      1
      30140
      30423
      Albuquerque, NM
      Austin, TX
      619
      151.777778
      201.043704
      WN
      0.718887
      202.160998
      AA
      0.180088
      201.397967
    
    
      4
      Table 1
      2011
      1
      30140
      30436
      Albuquerque, NM
      Tucson, AZ
      321
      155.666667
      115.909707
      WN
      0.927909
      114.270308
      WN
      0.927909
      114.270308



In [8]:

    
airports = pd.concat([df['citymarketid_1'], df['citymarketid_2']])



In [9]:

    
len(np.unique(airports))









    Out[9]:





141



In [18]:

    
len(np.unique(df.citymarketid_1))









    Out[18]:





123



In [10]:

    
from_nyc = df[df['city1'].str.contains('NY')]



In [11]:

    
from_nyc_to_or = from_nyc[from_nyc['city2'].str.contains('OR')]



In [16]:

    
from_nyc_to_or.plot(kind='bar', x='Year', y='fare', color='k');



In [17]:

    
df.to_csv('domenstic-flights.csv')



In [ ]:

	tbl	Year	quarter	citymarketid_1	citymarketid_2	city1	city2	nsmiles	passengers	fare	carrier_lg	large_ms	fare_lg	carrier_low	lf_ms	fare_low
0	Table 1	2011	1	30135	31454	Allentown/Bethlehem/Easton, PA	Orlando, FL	906	291.777778	119.161005	FL	0.687738	112.950000	G4	0.119573	84.792994
1	Table 1	2011	1	30140	30194	Albuquerque, NM	Dallas/Fort Worth, TX	580	532.333333	189.705197	WN	0.612607	189.172266	WN	0.612607	189.172266
2	Table 1	2011	1	30140	30325	Albuquerque, NM	Denver, CO	349	521.777778	114.180473	WN	0.449744	111.501610	F9	0.319208	104.576584
3	Table 1	2011	1	30140	30423	Albuquerque, NM	Austin, TX	619	151.777778	201.043704	WN	0.718887	202.160998	AA	0.180088	201.397967
4	Table 1	2011	1	30140	30436	Albuquerque, NM	Tucson, AZ	321	155.666667	115.909707	WN	0.927909	114.270308	WN	0.927909	114.270308