In [1]:

    

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


    

In [3]:

    

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


    

In [4]:

    

df.head()


    

    
Out[4]:






  

    

      

      
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
    
  

In [5]:

    

df['MdHHIncE'].describe()


    

    
Out[5]:





count        59.000000
mean      53895.932203
std       24371.741796
min       21318.000000
25%       37950.000000
50%       48252.000000
75%       61967.000000
max      119596.000000
Name: MdHHIncE, dtype: float64

In [12]:

    

df['MdHHIncE'].median()


    

    
Out[12]:





48252.0

In [14]:

    

df['MdHHIncE'].mode()


    

    
Out[14]:





0     21318
1     22343
2     51251
3     92583
4    119596
dtype: int64

In [23]:

    

range=df['MdHHIncE'].max()-df['MdHHIncE'].min()
range


    

    
Out[23]:





98278

In [15]:

    

df['MdHHIncE'].quantile(q=0.75)


    

    
Out[15]:





61967.0

In [17]:

    

df['MdHHIncE'].quantile(q=0.25)


    

    
Out[17]:





37950.0

In [16]:

    

df['MdHHIncE'].quantile(q=0.5) #is the same as median


    

    
Out[16]:





48252.0

In [19]:

    

Inter_quartile_Range=df['MdHHIncE'].quantile(q=0.75) - df['MdHHIncE'].quantile(q=0.25)
Inter_quartile_Range


    

    
Out[19]:





24017.0

In [21]:

    

Identification_of_outlier=1.5*Inter_quartile_Range
Identification_of_outlier


    

    
Out[21]:





36025.5

In [7]:

    

df['RecycleRate'].describe()


    

    
Out[7]:





count    59.000000
mean      0.175569
std       0.051499
min       0.091464
25%       0.133510
50%       0.174876
75%       0.212835
max       0.302798
Name: RecycleRate, dtype: float64

In [10]:

    

df.plot(kind='scatter', x='MdHHIncE', y='RecycleRate')
plt.xlabel('Median Income')
plt.ylabel('Recycling Rate')


    

    
Out[10]:





<matplotlib.text.Text at 0x11163dc88>






    

In [11]:

    

df.corr()


    

    
Out[11]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [ ]: