In [6]:
import pandas as pa
#Données reliant un nombre de ventes et l’investissement dans différents médias. 
#Le modèle de régression multiple a une variable dépendante y mesurant le nombre de ventes 
#et 3 variables indépendantes mesurant les investissements en terme de publicité par média.
data = pa.read_csv('advertising.csv')
data.head()
Out[6]:
TV Radio Newspaper Sales
0 230.1 37.8 69.2 22.1
1 44.5 39.3 45.1 10.4
2 17.2 45.9 69.3 9.3
3 151.5 41.3 58.5 18.5
4 180.8 10.8 58.4 12.9
In [7]:
X = data[['TV', 'Radio', 'Newspaper']]
y = data['Sales']
In [8]:
from statsmodels.regression.linear_model import OLS
model = OLS(y,X)
results = model.fit()
report = results.summary()
report
Out[8]:
OLS Regression Results
Dep. Variable: Sales R-squared (uncentered): 0.979
Model: OLS Adj. R-squared (uncentered): 0.979
Method: Least Squares F-statistic: 3091.
Date: Fri, 22 Sep 2023 Prob (F-statistic): 2.40e-165
Time: 07:52:32 Log-Likelihood: -437.56
No. Observations: 200 AIC: 881.1
Df Residuals: 197 BIC: 891.0
Df Model: 3
Covariance Type: nonrobust
coef std err t P>|t| [0.025 0.975]
TV 0.0531 0.001 37.422 0.000 0.050 0.056
Radio 0.2296 0.010 22.877 0.000 0.210 0.249
Newspaper 0.0158 0.007 2.206 0.029 0.002 0.030
Omnibus: 24.277 Durbin-Watson: 2.053
Prob(Omnibus): 0.000 Jarque-Bera (JB): 83.215
Skew: 0.371 Prob(JB): 8.51e-19
Kurtosis: 6.072 Cond. No. 12.5


Notes:
[1] R² is computed without centering (uncentered) since the model does not contain a constant.
[2] Standard Errors assume that the covariance matrix of the errors is correctly specified.
In [ ]: