In antaldaniel/surveyreader: Data cleaning and integration for survey files

knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
library(surveyreader)

df_raw <- readxl::read_xlsx(
  path  = "C:/Users/Daniel Antal/OneDrive - Visegrad Investments/2018 Projektek/surveyreader/data-raw/zeneipari_2017.xlsx",
  sheet = 1,
  skip = 2, col_names = TRUE
  )

metadata <- readxl::read_excel(
  path  = "C:/Users/Daniel Antal/OneDrive - Visegrad Investments/2018 Projektek/surveyreader/data-raw/musician_hu_2017.xlsx",
  sheet = 2, 
  range = "a1:l274"
)

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

df_logical <- df_raw %>%
  purrr::set_names(., metadata$var_name) %>%
  dplyr::select ( dplyr::starts_with ("is_")) %>%
  purrr::map_df (., function(x) str_sub(x, 1, 3) ) %>%
  purrr::map_df (., function(x) chr_logical(x, na_id = "NA"))

summary (df_logical)

Including Plots

You can also embed plots, for example:

df_gender <- df_raw %>%
  set_names(., metadata$var_name) %>%
  select ( which ( metadata$type  == "code_gender") ) %>%
  map_df (., function(x) code_gender(x, na_id = "NA"))

summary (df_gender)

df_scale <- df_raw %>%
  set_names(., metadata$var_name) %>%
  select ( which ( metadata$type == "scale_factor")) %>%
  map_df (., function(x) chr_numeric(x, digits = 1, na_id = "NA")) %>%
  mutate ( difficulty_bills = ifelse ( is.na(difficulty_bills), 
                                       difficulty_bills_abroad,
                                       difficulty_bills)) %>%
  mutate ( subjective_urbanization = 
             ifelse ( is.na(subjective_urbanization), 
           yes = subjective_urbanization_abroad, 
           no = subjective_urbanization))

summary (df_scale)

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

df_outlook <- df_raw %>%
  set_names(., metadata$var_name) %>%
  select ( which ( metadata$type == "better_worse_3")) %>%
  map_df (., function(x) better_worse_3(x,
                          language = "HU", 
                          na_id = "NA")) 

summary (df_outlook)

bla bala

metadata_numeric_3 <- metadata %>% 
  filter ( type == "numeric") %>% 
  filter ( default == "3")

df_numeric_3 <- df_raw %>%
  set_names(., metadata$var_name) %>%
  select ( one_of(metadata_numeric_3$var_name )) %>%
  map_df (., function(x) gsub("több", 999, x)) %>%
  map_df (., function(x) chr_numeric(x, digits = 3, na_id = "NA ")) %>%
  map_df (., function(x) moderate_more (as.vector(x),
                                        moderate = 999) )

summary (df_numeric_3)

metadata_numeric <- metadata %>% 
  filter ( type == "numeric") %>%
  mutate ( default = ifelse(is.na(default), 9, default)) %>%
  filter ( default != "3")

df_numeric <- df_raw %>%
  set_names(., metadata$var_name) %>%
  select ( one_of(metadata_numeric$var_name)) %>%
  map_df (., function(x) gsub("több", 99999, x)) %>%
  map_df (., function(x) chr_numeric(x, digits = NA, na_id = "NA ")) %>%
  map_df (., function(x) moderate_more (as.vector(x), moderate = 99999) )

df_quasi_numeric <- df_numeric %>%
  select ( starts_with("big_five"), starts_with ("cstp_"))

df_numeric <- df_numeric %>%
  select ( -starts_with("big_five"), -starts_with ("cstp_"))

summary (df_numeric)