sillasgonzaga

cdb <- function(capital, data_aplicacao, data_resgate, di, pct_cdi){
  library(dplyr)
  library(bizdays)  
  
  dias_corridos <- as.numeric(difftime(data_resgate, data_aplicacao, units = "days"))
  
  # computar biz days entre datas
  bizdays::create.calendar("Brazil/ANBIMA",
                           bizdays::holidaysANBIMA,
                           weekdays=c("saturday", "sunday"))

sillasgonzaga

library(BatchGetSymbols)
library(tidyverse)
library(varngc)

x <- GetSP500Stocks()

stocks <- c("AAPL", "GOOG", "MSFT", "AMZN", "ADBE", "EBAY", "FB", "HPQ")

st <- as.Date("2010-01-01")
end <- as.Date("2018-01-01")

sillasgonzaga

plot_rf_tree <- function(final_model, tree_num, shorten_label = TRUE) {
  
  # source: https://shiring.github.io/machine_learning/2017/03/16/rf_plot_ggraph
  
  # get tree by index
  tree <- randomForest::getTree(final_model, 
                                k = tree_num, 
                                labelVar = TRUE) %>%
    tibble::rownames_to_column() %>%
    # make leaf split points to NA, so the 0s won't get plotted

sillasgonzaga

# Criando um Correlation Plot
def visualize_correlation_matrix(data, hurdle = 0.0):
  # fonte: data science academy
    R = np.corrcoef(data, rowvar = 0)
    R[np.where(np.abs(R) < hurdle)] = 0.0
    heatmap = plt.pcolor(R, cmap = mpl.cm.coolwarm, alpha = 0.8)
    heatmap.axes.set_frame_on(False)
    heatmap.axes.set_yticks(np.arange(R.shape[0]) + 0.5, minor = False)
    heatmap.axes.set_xticks(np.arange(R.shape[1]) + 0.5, minor = False)
    heatmap.axes.set_xticklabels(variables, minor = False)

sillasgonzaga

#Code for "A Statistical Curiosity Voyage Through the Emotion of Stranger Things"
#Article and code written by Jordan Dworkin (https://medium.com/@jordandworkin/)


###############################################################################
####### Pull script data (would need to be edited based on data source) #######
###############################################################################

library(rvest)
library(tibble)

sillasgonzaga

library(tidyverse)
library(purrr)
library(forecast)
library(lubridate)

vetor_uf <- c("RJ", "SP", "MG", "ES")

vetor_data <- seq.Date(as.Date("2010-01-01"), by = "month",
                       length.out = 60)

sillasgonzaga

grafico_tfidf <- function(data, n_grams = 1, remover_nomes_proprios,
                          agregar_por_noticia, remover_stop_words = TRUE){
  
  data <- data %>% 
    unnest_tokens(palavra, corpo_noticia, token = "ngrams", n = n_grams, to_lower = FALSE)
  
  if (agregar_por_noticia){
    # remover as duplicatas dentre de uma mesma noticia
    data %<>% distinct(url, palavra, .keep_all = TRUE)
  }

sillasgonzaga

# source: https://gist.github.com/corynissen/5389426

getLongURL.curl <- function(shorturl){
  # uses curl statement to get expanded url from t.co links (or any link)
  # loop through until there's no location attribute... that's the long link.
  newurl <- shorturl
  url <- ""
  while(url != newurl){
    data <- system(paste0("curl -I ", newurl), intern=T)
    if(sum(grepl("location: ", tolower(data))) == 0){

sillasgonzaga

library(stringr)
library(magrittr)
library(lubridate)
library(glue)
library(dplyr)
library(readr)

# exemplo:

extrair_ans_UF <- function(uf, limpar_pasta_temporaria = TRUE) {

sillasgonzaga

# projeto analise de sentimento
library(tidyr)
library(dplyr)
library(magrittr)
library(stringr)
library(lubridate)
library(ggplot2)
library(tm)
library(SnowballC)
library(wordcloud)