Linear Regression (Service Level) 3

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as seabornInstance

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

#from sklearn.feature_selection import SelectFromModel

from sklearn import metrics

from sklearn.metrics import classification_report

from sklearn.metrics import confusion_matrix

import statsmodels.api as sm

ServiceLevel = pd.read_csv("Service Level.csv")

print(ServiceLevel.head())

y = ServiceLevel['SL'].values # Create arrays for the feature variable

X = ServiceLevel.drop(['SL','Date'], axis=1).values # Create arrays for the response variables

# We do the regression

reg = sm.OLS(y, X).fit()

# And here we can see the results in a very nice looking table

print('SUMMARY -------------------------------------------')

print((reg.summary()))

# We can only take a look at the parameter values though

print('PARAMETERS ----------------------------------------')

print((reg.params))

# We can also extract the residuals

# print('RESIDUALS -----------------------------------------')

# print((reg.resid))

# This line is just to prevent the output from vanishing when you

# run the program by double-clicking

# input('Done - Hit any key to finish.')

SUMMARY -------------------------------------------

OLS Regression Results

=======================================================================================

Dep. Variable: y R-squared (uncentered): 0.979

Model: OLS Adj. R-squared (uncentered): 0.978

Method: Least Squares F-statistic: 6357.

Date: Sat, 16 May 2020 Prob (F-statistic): 0.00

Time: 19:09:41 Log-Likelihood: 554.37

No. Observations: 699 AIC: -1099.

Df Residuals: 694 BIC: -1076.

Df Model: 5

Covariance Type: nonrobust

==============================================================================

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

------------------------------------------------------------------------------

x1 -0.0017 6.67e-05 -24.976 0.000 -0.002 -0.002

x2 0.0016 7.11e-05 23.039 0.000 0.001 0.002

x3 0.0030 0.000 13.994 0.000 0.003 0.003

x4 -6.06e-05 9.08e-05 -0.667 0.505 -0.000 0.000

x5 0.0006 8.65e-05 6.670 0.000 0.000 0.001

==============================================================================

Omnibus: 102.645 Durbin-Watson: 0.825

Prob(Omnibus): 0.000 Jarque-Bera (JB): 190.404

Skew: -0.879 Prob(JB): 4.51e-42

Kurtosis: 4.857 Cond. No. 98.6

==============================================================================

Warnings:

[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

PARAMETERS ----------------------------------------

[-1.66514205e-03 1.63764578e-03 2.95806398e-03 -6.05955892e-05

5.76872815e-04]