fernandobarbalho

library(tabulizer)
library(dplyr)

setwd("~/GitHub/oleogate/data")

#Extrai tabelas do arquivo pdf. 
#Esse arquivo foi baixado do seguinte link 
# https://politica.estadao.com.br/blogs/estadao-verifica/wp-content/uploads/sites/690/2019/10/Ibama.pdf
#A tabela é extraída para um arquivo csv de forma a poder trabalhar melhor questões de encoding
tabulizer::extract_tables("ibama.pdf", output = "csv",outdir = getwd())

fernandobarbalho

# install.packages("devtools")
devtools::install_github("tchiluanda/rsiconfi")

library(rsiconfi)
library(dplyr)
library(tidyr)

###########Trabalhando as despesas

#Monta um vetor com todos os códigos de UFs do Brasil

sergiospagnuolo

# Força o encoding para UTF-8, default do banco de dados
# Colaboração de Sérgio Spagnuolo ([email protected])
# Programa acessar a API do Atlas da Notícia (https://www.atlas.jor.br/)
# É necessário antes se cadastrar, veja como aqui: https://www.atlas.jor.br/plataforma/utilizarAPI/

library(httr)
library(jsonlite)

# Puxa os dados da sua credencial
token = content(

fernandobarbalho

library(readr)
library(dplyr)
PENSIONISTAS_112019 <- read_delim("Data/PENSIONISTAS_112019.csv", 
                      ";", escape_double = FALSE, locale = locale(decimal_mark = ",", 
                                                                  grouping_mark = ".", encoding = "LATIN1"), 
                      trim_ws = TRUE)

PENSIONISTAS_122019 <- read_delim("Data/PENSIONISTAS_122019.csv", 
                                  ";", escape_double = FALSE, locale = locale(decimal_mark = ",", 

fernandobarbalho

#based on this method: https://github.com/k-sys/covid-19/blob/master/Realtime%20R0.ipynb
# In fact it is a translation from python to R of some parts of the code explained in the link above.

get_last_covid_rt<- function(df_days_case){ #this dataset must have a structre with a collumn no_cases (accumulated number of cases on a given sequence day)
  
  
  #smooth the data
  
  x <- 1:NROW(df_days_case)
  y<-df_days_case$no_cases 

lgelape

### STOPWORDS IN PORTUGUESE

## Create a unique dataset from several datasets with stopwords in Portuguese

# Lucas Gelape

# Packages
library(dplyr)
library(stringi)
library(readr)

fernandobarbalho

library(readxl)
library(ckanr)
library(purrr)

ckanr::package_search()

package<- ckanr::package_show(id= "22d13d17-bf69-4a1a-add2-25cc1e25f2d7", 
                              url= "https://www.tesourotransparente.gov.br/ckan") #busca todos os dados do dataset que se refere aos dados de COFOG

jlomako

#####################################################
# Use GPT-3 in R with the OpenAI API. You need to install the reticulate package.
# Additionally, an API key is required that must be saved in a separate file, called .openaikey 
# Get your API key here: https://openai.com/api/
#####################################################

# install.packages("reticulate") # run only once
library(reticulate)

# create python env

turicas