verajosemanuel

require(tibble)

# if nrow is numerical

df <- rownames_to_column(df, var = "id")


# if nrow is not numerical

df$id <- seq.int(nrow(df))

verajosemanuel

source('py_logging.R') 

# Set up logging
logger.setup(debugLog = "debug.log", infoLog = "info.log", errorLog = "error.log")

# Silence other warning messages
options(warn = -1) # -1=ignore, 0=save/print, 1=print, 2=error

err_msg <- geterrmessage()
logger.error('Error on running some scripts: %s')

verajosemanuel

df <- read.csv("data.csv", sep = ";", stringsAsFactors = FALSE)
library("FFTrees")


## Recoding 

pdf$recoded <- pdf$original
pdf$recoded[pdf$TIPO == "no"] <- "0"
pdf$recoded[pdf$TIPO == "yes"] <- "1"
pdf$recoded <- as.numeric(pdf$recoded)

verajosemanuel

mb <- microbenchmark(function_1(df), function_2(df), function_3(df), function_4(df))

library(ggplot2)

autoplot(mb)

verajosemanuel

x <- c("m", "f", "u", "f", "f", "m", "m")

lookup <- c(m = "Male", f = "Female", u = NA)

lookup[x]

unname(lookup[x])

verajosemanuel

grades <- c(1, 2, 2, 3, 1)

info <- data.frame(
  grade = 3:1,
  desc = c("Excellent", "Good", "Poor"),
  fail = c(F, F, T)
)

# info  table with grades 

verajosemanuel

df <- data.frame(x = c(2, 4, 1), y = c(9, 11, 6), n = c(3, 5, 1))

rep(1:nrow(df), df$n)

df[rep(1:nrow(df), df$n), ]

verajosemanuel

# discard columns

df[setdiff(names(df), "y")] 

(x <- c(sort(sample(1:20, 9)), NA))
(y <- c(sort(sample(3:23, 7)), NA))

union(x, y)

intersect(x, y)

verajosemanuel

for (i in 1:4) {
  assign(paste("df_name",i,sep = ""), read.csv(paste0("df",i,".csv"), sep = ";", stringsAsFactors = FALSE)) 
}

verajosemanuel

library(janitor)

df <- remove_empty_rows(df)
df <- remove_empty_cols(df)

# clean names

names(df) <- names(clean_names(df))