In [1]:

    

import pandas as pd
import statsmodels.formula.api as sm
import numpy as np
import ggplot as gg


    

In [9]:

    

! pip install ggplot


    

    




Requirement already satisfied: ggplot in c:\users\dell\anaconda3\lib\site-packages
Requirement already satisfied: matplotlib in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: scipy in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: brewer2mpl in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: patsy>=0.4 in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: six in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: statsmodels in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: pandas in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: cycler in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: numpy in c:\users\dell\anaconda3\lib\site-packages (from ggplot)
Requirement already satisfied: python-dateutil in c:\users\dell\anaconda3\lib\site-packages (from matplotlib->ggplot)
Requirement already satisfied: pytz in c:\users\dell\anaconda3\lib\site-packages (from matplotlib->ggplot)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,>=1.5.6 in c:\users\dell\anaconda3\lib\site-packages (from matplotlib->ggplot)

In [2]:

    

anscombe=pd.read_csv("https://vincentarelbundock.github.io/Rdatasets/csv/datasets/anscombe.csv")


    

In [5]:

    

anscombe=anscombe.drop("Unnamed: 0",1)


    

In [6]:

    

anscombe


    

    
Out[6]:






  

    

      

      
x1
      
x2
      
x3
      
x4
      
y1
      
y2
      
y3
      
y4
    
  
  

    

      
0
      
10
      
10
      
10
      
8
      
8.04
      
9.14
      
7.46
      
6.58
    
    

      
1
      
8
      
8
      
8
      
8
      
6.95
      
8.14
      
6.77
      
5.76
    
    

      
2
      
13
      
13
      
13
      
8
      
7.58
      
8.74
      
12.74
      
7.71
    
    

      
3
      
9
      
9
      
9
      
8
      
8.81
      
8.77
      
7.11
      
8.84
    
    

      
4
      
11
      
11
      
11
      
8
      
8.33
      
9.26
      
7.81
      
8.47
    
    

      
5
      
14
      
14
      
14
      
8
      
9.96
      
8.10
      
8.84
      
7.04
    
    

      
6
      
6
      
6
      
6
      
8
      
7.24
      
6.13
      
6.08
      
5.25
    
    

      
7
      
4
      
4
      
4
      
19
      
4.26
      
3.10
      
5.39
      
12.50
    
    

      
8
      
12
      
12
      
12
      
8
      
10.84
      
9.13
      
8.15
      
5.56
    
    

      
9
      
7
      
7
      
7
      
8
      
4.82
      
7.26
      
6.42
      
7.91
    
    

      
10
      
5
      
5
      
5
      
8
      
5.68
      
4.74
      
5.73
      
6.89
    
  

In [7]:

    

np.mean(anscombe)


    

    
Out[7]:





x1    9.000000
x2    9.000000
x3    9.000000
x4    9.000000
y1    7.500909
y2    7.500909
y3    7.500000
y4    7.500909
dtype: float64

In [8]:

    

np.std(anscombe)


    

    
Out[8]:





x1    3.162278
x2    3.162278
x3    3.162278
x4    3.162278
y1    1.937024
y2    1.937109
y3    1.935933
y4    1.936081
dtype: float64

In [10]:

    

result1 = sm.ols(formula="y1 ~ x1 ", data=anscombe).fit()
result2 = sm.ols(formula="y2 ~ x2 ", data=anscombe).fit()
result3 = sm.ols(formula="y3 ~ x3 ", data=anscombe).fit()
result4 = sm.ols(formula="y4 ~ x4 ", data=anscombe).fit()


    

In [12]:

    

result1.summary()


    

    




C:\Users\Dell\Anaconda3\lib\site-packages\scipy\stats\stats.py:1327: UserWarning: kurtosistest only valid for n>=20 ... continuing anyway, n=11
  "anyway, n=%i" % int(n))






    
Out[12]:





OLS Regression Results

  
Dep. Variable:
           
y1
        
  R-squared:         
 
   0.667


  
Model:
                   
OLS
       
  Adj. R-squared:    
 
   0.629


  
Method:
             
Least Squares
  
  F-statistic:       
 
   17.99


  
Date:
             
Tue, 18 Apr 2017
 
  Prob (F-statistic):
  
0.00217


  
Time:
                 
20:21:59
     
  Log-Likelihood:    
 
 -16.841


  
No. Observations:
      
    11
      
  AIC:               
 
   37.68


  
Df Residuals:
          
     9
      
  BIC:               
 
   38.48


  
Df Model:
              
     1
      
                     
     
 
   


  
Covariance Type:
      
nonrobust
    
                     
     
 
   




      
         
coef
     
std err
      
t
      
P>|t|
 
[95.0% Conf. Int.]
 


  
Intercept
 
    3.0001
 
    1.125
 
    2.667
 
 0.026
 
    0.456     5.544


  
x1
        
    0.5001
 
    0.118
 
    4.241
 
 0.002
 
    0.233     0.767




  
Omnibus:
       
 0.082
 
  Durbin-Watson:     
 
   3.212


  
Prob(Omnibus):
 
 0.960
 
  Jarque-Bera (JB):  
 
   0.289


  
Skew:
          
-0.122
 
  Prob(JB):          
 
   0.865


  
Kurtosis:
      
 2.244
 
  Cond. No.          
 
    29.1

In [13]:

    

print(result1.params)
print(result2.params)
print(result3.params)
print(result4.params)


    

    




Intercept    3.000091
x1           0.500091
dtype: float64
Intercept    3.000909
x2           0.500000
dtype: float64
Intercept    3.002455
x3           0.499727
dtype: float64
Intercept    3.001727
x4           0.499909
dtype: float64

In [ ]:

    

print(result1.rsquared)
print(result2.rsquared)
print(result3.rsquared)
print(result4.rsquared)


    

In [14]:

    

%matplotlib inline


    

In [15]:

    

p = gg.ggplot(gg.aes(x='x1', y='y1'), data=anscombe)


    

In [16]:

    

p + gg.geom_point()


    

    













    
Out[16]:





<ggplot: (12797788)>

In [17]:

    

p2 = gg.ggplot(gg.aes(x='x2', y='y2'), data=anscombe)
p2 + gg.geom_point()


    

    













    
Out[17]:





<ggplot: (12841764)>

In [18]:

    

p3 = gg.ggplot(gg.aes(x='x3', y='y3'), data=anscombe)
p3 + gg.geom_point()


    

    













    
Out[18]:





<ggplot: (-9223372036841546566)>

In [19]:

    

p4= gg.ggplot(gg.aes(x='x4', y='y4'), data=anscombe)
p4 + gg.geom_point()


    

    













    
Out[19]:





<ggplot: (-9223372036841149899)>

In [ ]: