In [1]:

    

import pandas as pd
import statsmodels.formula.api as smf
import matplotlib.pyplot as plt
%matplotlib inline


    

In [29]:

    

df = pd.read_excel('2013_NYC_CD_MedianIncome_Recycle.xlsx')
df


    

    
Out[29]:






  

    

      

      
CD_Name
      
MdHHIncE
      
RecycleRate
    
  
  

    

      
0
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.286771
    
    

      
1
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.264074
    
    

      
2
      
Chinatown & Lower East Side
      
40919
      
0.156485
    
    

      
3
      
Chelsea, Clinton & Midtown Business Distric
      
92583
      
0.235125
    
    

      
4
      
Chelsea, Clinton & Midtown Business Distric
      
92583
      
0.246725
    
    

      
5
      
Murray Hill, Gramercy & Stuyvesant Town
      
101769
      
0.222046
    
    

      
6
      
Upper West Side & West Side
      
96009
      
0.256809
    
    

      
7
      
Upper East Side
      
104602
      
0.253719
    
    

      
8
      
Hamilton Heights, Manhattanville & West Harlem
      
41736
      
0.155888
    
    

      
9
      
Central Harlem
      
36468
      
0.133018
    
    

      
10
      
East Harlem
      
30335
      
0.140438
    
    

      
11
      
Washington Heights, Inwood & Marble Hill
      
37685
      
0.149605
    
    

      
12
      
Hunts Point, Longwood & Melrose
      
21318
      
0.104569
    
    

      
13
      
Hunts Point, Longwood & Melrose
      
21318
      
0.103643
    
    

      
14
      
Belmont, Crotona Park East & East Tremont
      
22343
      
0.119219
    
    

      
15
      
Concourse, Highbridge & Mount Eden
      
25745
      
0.103573
    
    

      
16
      
Morris Heights, Fordham South & Mount Hope
      
24517
      
0.119646
    
    

      
17
      
Belmont, Crotona Park East & East Tremont
      
22343
      
0.110713
    
    

      
18
      
Bedford Park, Fordham North & Norwood
      
30541
      
0.136455
    
    

      
19
      
Riverdale, Fieldston & Kingsbridge
      
56877
      
0.221890
    
    

      
20
      
Castle Hill, Clason Point & Parkchester
      
34779
      
0.105807
    
    

      
21
      
Co-op City, Pelham Bay & Schuylerville
      
54685
      
0.214509
    
    

      
22
      
Pelham Parkway, Morris Park & Laconia
      
43503
      
0.163576
    
    

      
23
      
Wakefield, Williamsbridge & Woodlawn
      
43541
      
0.182580
    
    

      
24
      
Greenpoint & Williamsburg
      
50778
      
0.141621
    
    

      
25
      
Brooklyn Heights & Fort Greene
      
73290
      
0.237205
    
    

      
26
      
Bedford-Stuyvesant
      
36528
      
0.125818
    
    

      
27
      
Bushwick
      
38274
      
0.132463
    
    

      
28
      
East New York & Starrett City
      
33700
      
0.114030
    
    

      
29
      
Park Slope, Carroll Gardens & Red Hook
      
93969
      
0.302798
    
    

      
30
      
Sunset Park & Windsor Terrace
      
43351
      
0.197697
    
    

      
31
      
Crown Heights North & Prospect Heights
      
41075
      
0.156241
    
    

      
32
      
Crown Heights South, Prospect Lefferts & Wingate
      
41095
      
0.115119
    
    

      
33
      
Bay Ridge & Dyker Heights
      
57006
      
0.220855
    
    

      
34
      
Bensonhurst & Bath Beach
      
48252
      
0.183393
    
    

      
35
      
Borough Park, Kensington & Ocean Parkway
      
38215
      
0.156080
    
    

      
36
      
Brighton Beach & Coney Island
      
30159
      
0.134260
    
    

      
37
      
Flatbush & Midwood
      
41681
      
0.145995
    
    

      
38
      
Sheepshead Bay, Gerritsen Beach & Homecrest
      
49392
      
0.193802
    
    

      
39
      
Brownsville & Ocean Hill
      
27772
      
0.091464
    
    

      
40
      
East Flatbush, Farragut & Rugby
      
45954
      
0.134002
    
    

      
41
      
Canarsie & Flatlands
      
63106
      
0.174876
    
    

      
42
      
Astoria & Long Island City
      
50716
      
0.215254
    
    

      
43
      
Sunnyside & Woodside
      
54136
      
0.198388
    
    

      
44
      
Jackson Heights & North Corona
      
47555
      
0.137919
    
    

      
45
      
Elmhurst & South Corona
      
45661
      
0.130604
    
    

      
46
      
Ridgewood, Glendale & Middle Village
      
54924
      
0.214185
    
    

      
47
      
Forest Hills & Rego Park
      
64372
      
0.210247
    
    

      
48
      
Flushing, Murray Hill & Whitestone
      
51251
      
0.192124
    
    

      
49
      
Briarwood, Fresh Meadows & Hillcrest
      
59124
      
0.194293
    
    

      
50
      
Richmond Hill & Woodhaven
      
58578
      
0.187987
    
    

      
51
      
Howard Beach & Ozone Park
      
60828
      
0.183898
    
    

      
52
      
Bayside, Douglaston & Little Neck
      
74960
      
0.253064
    
    

      
53
      
Jamaica, Hollis & St. Albans
      
51251
      
0.157345
    
    

      
54
      
Queens Village, Cambria Heights & Rosedale
      
76002
      
0.196679
    
    

      
55
      
Far Rockaway, Breezy Point & Broad Channel
      
46944
      
0.123351
    
    

      
56
      
Port Richmond, Stapleton & Mariner's Harbor
      
57975
      
0.196748
    
    

      
57
      
New Springville & South Beach
      
71925
      
0.211485
    
    

      
58
      
Tottenville, Great Kills & Annadale
      
84670
      
0.210379
    
  

In [31]:

    

df.plot(kind="scatter", x="MdHHIncE", y="RecycleRate")


    

    
Out[31]:





<matplotlib.axes._subplots.AxesSubplot at 0x109650a58>






    

In [38]:

    

lm = smf.ols(formula="RecycleRate~MdHHIncE",data=df).fit()
lm.params


    

    
Out[38]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [40]:

    

median_income_input = input('Please type down a median income you want to know the recycle rate for:')
if median_income_input:
    output = (float(lm.params['MdHHIncE']) * float(median_income_input)) + (float(lm.params['Intercept']))
    print("The recycle rate of a community district with a median income of", median_income_input, "US-dollar has a recycling rate of approx.", round(output, 2))


    

    




Please type down a median income you want to know the recycle rate for:20000
The recycle rate of a community district with a median income of 20000 US-dollar has a recycling rate of approx. 0.11

In [ ]: