Ver https://rstudio.github.io/reticulate/.
library(reticulate)
py_install("openpyxl") # para instalar pacoteimport pandas as pd
# precisei instalar openpyxl (para xlsx) e xlrd (para xls)
df = pd.read_excel (r'D:\Documentos\disciplinas\econometria\laboratorio_Python\primeiro_projeto\gujarati 5ed p236 frangos tabela7_9.xlsx', sheet_name='dados')
print (df[["lny" , "lnx2" , "lnx3" , "lnx4" , "lnx5"]])## lny lnx2 lnx3 lnx4 lnx5
## 0 3.325036 5.985195 3.742420 3.925926 4.360548
## 1 3.397858 6.024174 3.640214 3.951244 4.371976
## 2 3.394508 6.084955 3.696351 3.988984 4.371976
## 3 3.427515 6.130574 3.676301 4.012773 4.371976
## 4 3.440418 6.200306 3.618993 4.001864 4.348987
## 5 3.505557 6.270232 3.640214 4.154185 4.384524
## 6 3.572346 6.328472 3.671225 4.245634 4.387014
## 7 3.594569 6.437111 3.632309 4.188138 4.429626
## 8 3.602777 6.501890 3.648057 4.166665 4.448516
## 9 3.648057 6.576191 3.691376 4.248495 4.540098
## 10 3.698830 6.644050 3.653252 4.293195 4.664382
## 11 3.696351 6.737323 3.683867 4.216562 4.652054
## 12 3.732896 6.815201 3.681351 4.370713 4.736198
## 13 3.698830 6.836367 3.953165 4.558079 4.821088
## 14 3.706228 6.929027 3.889777 4.545420 4.848900
## 15 3.691376 7.061249 4.065602 4.816241 4.962145
## 16 3.754199 7.207564 4.058717 4.866765 4.967032
## 17 3.786460 7.278905 4.034241 4.767289 4.935912
## 18 3.843744 7.362328 4.154185 4.874434 5.108971
## 19 3.923952 7.472558 4.120662 4.865995 5.314683
## 20 3.914021 7.597998 4.075841 4.852030 5.391808
## 21 3.945458 7.722279 4.195697 4.948760 5.400874
## 22 3.968403 7.815490 4.254193 5.125154 5.449320import numpy as np
from sklearn.linear_model import LinearRegression
import statsmodels.formula.api as smimport statsmodels.formula.api as sm
result = sm.ols(formula="lny ~ lnx2 + lnx3 + lnx4 + lnx5", data=df).fit()print(result.summary())
# comparar com https://rpubs.com/amrofi/exercicio_gujarati_7_19## OLS Regression Results
## ==============================================================================
## Dep. Variable: lny R-squared: 0.982
## Model: OLS Adj. R-squared: 0.978
## Method: Least Squares F-statistic: 249.9
## Date: Wed, 04 Aug 2021 Prob (F-statistic): 1.67e-15
## Time: 21:02:54 Log-Likelihood: 52.759
## No. Observations: 23 AIC: -95.52
## Df Residuals: 18 BIC: -89.84
## Df Model: 4
## Covariance Type: nonrobust
## ==============================================================================
## coef std err t P>|t| [0.025 0.975]
## ------------------------------------------------------------------------------
## Intercept 2.1898 0.156 14.063 0.000 1.863 2.517
## lnx2 0.3426 0.083 4.114 0.001 0.168 0.517
## lnx3 -0.5046 0.111 -4.550 0.000 -0.738 -0.272
## lnx4 0.1485 0.100 1.490 0.153 -0.061 0.358
## lnx5 0.0911 0.101 0.905 0.378 -0.120 0.303
## ==============================================================================
## Omnibus: 1.145 Durbin-Watson: 1.826
## Prob(Omnibus): 0.564 Jarque-Bera (JB): 1.078
## Skew: 0.427 Prob(JB): 0.583
## Kurtosis: 2.370 Cond. No. 388.
## ==============================================================================
##
## Notes:
## [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.