In [21]:

    

import numpy as np
from sklearn.preprocessing import normalize
from sklearn.preprocessing import StandardScaler
import pandas as pd
import matplotlib.pyplot as plt
import scipy.stats as stats
%matplotlib inline
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.model_selection import train_test_split
import statsmodels.formula.api as smf
from statsmodels.compat import lzip
from sklearn import feature_selection
import statsmodels.regression.linear_model as sm
from statsmodels.stats.outliers_influence import variance_inflation_factor
from statsmodels.stats.diagnostic import het_breuschpagan


    

    




/home/55018335734/.conda/envs/datascience/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
  from pandas.core import datetools

In [11]:

    

df = pd.read_csv('servidor.csv')
df.head()
df.info()
df.describe()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 29 entries, 0 to 28
Data columns (total 4 columns):
Duracao_media_ms    29 non-null int64
Perc_medio_CPU      29 non-null float64
Load_avg_minute     29 non-null float64
Requests_média      29 non-null int64
dtypes: float64(2), int64(2)
memory usage: 1008.0 bytes






    
Out[11]:







  

    

      

      
Duracao_media_ms
      
Perc_medio_CPU
      
Load_avg_minute
      
Requests_média
    
  
  

    

      
count
      
29.000000
      
29.000000
      
29.000000
      
29.000000
    
    

      
mean
      
811.586207
      
47.975050
      
3.927406
      
631.793103
    
    

      
std
      
672.159129
      
43.282833
      
3.379525
      
391.095657
    
    

      
min
      
140.000000
      
6.866574
      
0.498327
      
56.000000
    
    

      
25%
      
150.000000
      
10.581583
      
0.650421
      
230.000000
    
    

      
50%
      
520.000000
      
20.151097
      
2.333277
      
720.000000
    
    

      
75%
      
1500.000000
      
98.170972
      
7.317686
      
890.000000
    
    

      
max
      
1950.000000
      
121.235760
      
9.580188
      
1535.000000
    
  

In [14]:

    

results = smf.ols('Duracao_media_ms ~ Perc_medio_CPU + Load_avg_minute + Requests_média', data=df).fit()
results.summary()


    

    
Out[14]:





OLS Regression Results

  
Dep. Variable:
    
Duracao_media_ms
 
  R-squared:         
 
   1.000
 


  
Model:
                   
OLS
       
  Adj. R-squared:    
 
   0.999
 


  
Method:
             
Least Squares
  
  F-statistic:       
 
1.755e+04


  
Date:
             
Fri, 10 Nov 2017
 
  Prob (F-statistic):
 
1.17e-41
 


  
Time:
                 
14:11:46
     
  Log-Likelihood:    
 
 -118.48
 


  
No. Observations:
      
    29
      
  AIC:               
 
   245.0
 


  
Df Residuals:
          
    25
      
  BIC:               
 
   250.4
 


  
Df Model:
              
     3
      
                     
     
 
    


  
Covariance Type:
      
nonrobust
    
                     
     
 
    




         
            
coef
     
std err
      
t
      
P>|t|
  
[0.025
    
0.975]
  


  
Intercept
       
   20.7948
 
    6.316
 
    3.292
 
 0.003
 
    7.786
 
   33.803


  
Perc_medio_CPU
  
    0.2873
 
    0.285
 
    1.009
 
 0.323
 
   -0.299
 
    0.874


  
Load_avg_minute
 
  194.4347
 
    3.828
 
   50.799
 
 0.000
 
  186.552
 
  202.318


  
Requests_média
  
    0.0212
 
    0.010
 
    2.206
 
 0.037
 
    0.001
 
    0.041




  
Omnibus:
       
 0.521
 
  Durbin-Watson:     
 
   2.480


  
Prob(Omnibus):
 
 0.771
 
  Jarque-Bera (JB):  
 
   0.611


  
Skew:
          
-0.081
 
  Prob(JB):          
 
   0.737


  
Kurtosis:
      
 2.308
 
  Cond. No.          
 
1.67e+03

In [18]:

    

X = df.drop('Duracao_media_ms',axis=1)
Xe = sm.add_constant(X,prepend=True)
vif = [variance_inflation_factor(Xe.values, i) for i in range(Xe.shape[1])]
vif_s =pd.Series(vif, index =Xe.columns)
print(vif_s)


    

    




const               4.817213
Perc_medio_CPU     17.701874
Load_avg_minute    19.506190
Requests_média      1.645110
dtype: float64

In [29]:

    

name = ['Lagrange multiplier statistic', 'p-value', 
        'f-value', 'f p-value']
testeH = het_breuschpagan(results.resid, results.model.exog)
lzip(name, testeH)


    

    
Out[29]:





[('Lagrange multiplier statistic', 3.6684353081331946),
 ('p-value', 0.29956464547347383),
 ('f-value', 1.2068063937739497),
 ('f p-value', 0.32771840796145069)]

In [ ]: