Download and Read Data Set

file_url <- "http://downloads.majestic.com/majestic_million.csv"
temp_file <- tempfile(fileext = ".csv")

download.file(file_url, destfile = temp_file)

test_df <- read_csv(temp_file)

Quick Inspection

glimpse(test_df)
## Observations: 1,000,000
## Variables: 12
## $ GlobalRank     <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, ...
## $ TldRank        <int> 1, 2, 3, 4, 5, 6, 1, 7, 8, 9, 2, 10, 3, 11, 12,...
## $ Domain         <chr> "google.com", "facebook.com", "youtube.com", "t...
## $ TLD            <chr> "com", "com", "com", "com", "com", "com", "org"...
## $ RefSubNets     <int> 463232, 451237, 410764, 409068, 303679, 292966,...
## $ RefIPs         <int> 2963708, 3046847, 2444016, 2546940, 1139322, 13...
## $ IDN_Domain     <chr> "google.com", "facebook.com", "youtube.com", "t...
## $ IDN_TLD        <chr> "com", "com", "com", "com", "com", "com", "org"...
## $ PrevGlobalRank <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, ...
## $ PrevTldRank    <int> 1, 2, 3, 4, 5, 6, 1, 7, 8, 9, 2, 10, 3, 11, 12,...
## $ PrevRefSubNets <int> 462861, 451086, 410676, 408692, 303296, 292918,...
## $ PrevRefIPs     <int> 2966284, 3049605, 2447455, 2549623, 1138675, 13...
test_df %>%
  summarise_all(funs(sum(is.na(.)))) %>% # where the NAs at?
  gather(Variable, NAs) %>% 
  kable() %>% 
  kable_styling(full_width = FALSE)

Write the .csv

write_csv(test_df, path)

Small

The “small” .csv consists of the first 100 rows.

(small_df <- test_df %>% 
  slice(1:100))
## # A tibble: 100 x 12
##    GlobalRank TldRank Domain TLD   RefSubNets RefIPs IDN_Domain IDN_TLD
##         <int>   <int> <chr>  <chr>      <int>  <int> <chr>      <chr>  
##  1          1       1 googl~ com       463232 2.96e6 google.com com    
##  2          2       2 faceb~ com       451237 3.05e6 facebook.~ com    
##  3          3       3 youtu~ com       410764 2.44e6 youtube.c~ com    
##  4          4       4 twitt~ com       409068 2.55e6 twitter.c~ com    
##  5          5       5 micro~ com       303679 1.14e6 microsoft~ com    
##  6          6       6 linke~ com       292966 1.35e6 linkedin.~ com    
##  7          7       1 wikip~ org       287420 1.24e6 wikipedia~ org    
##  8          8       7 plus.~ com       284103 1.46e6 plus.goog~ com    
##  9          9       8 insta~ com       277145 1.37e6 instagram~ com    
## 10         10       9 apple~ com       276152 1.05e6 apple.com  com    
## # ... with 90 more rows, and 4 more variables: PrevGlobalRank <int>,
## #   PrevTldRank <int>, PrevRefSubNets <int>, PrevRefIPs <int>
(small_rows <- nrow(small_df)) %>% comma() %>% cat("rows")
## 100 rows
path_small_csv <- "test-data/small_csv.csv"
write_csv(small_df, path_small_csv)

Medium

The “medium” .csv consists of the first 5,000 rows.

(medium_df <- test_df %>% 
  slice(1:5000))
## # A tibble: 5,000 x 12
##    GlobalRank TldRank Domain TLD   RefSubNets RefIPs IDN_Domain IDN_TLD
##         <int>   <int> <chr>  <chr>      <int>  <int> <chr>      <chr>  
##  1          1       1 googl~ com       463232 2.96e6 google.com com    
##  2          2       2 faceb~ com       451237 3.05e6 facebook.~ com    
##  3          3       3 youtu~ com       410764 2.44e6 youtube.c~ com    
##  4          4       4 twitt~ com       409068 2.55e6 twitter.c~ com    
##  5          5       5 micro~ com       303679 1.14e6 microsoft~ com    
##  6          6       6 linke~ com       292966 1.35e6 linkedin.~ com    
##  7          7       1 wikip~ org       287420 1.24e6 wikipedia~ org    
##  8          8       7 plus.~ com       284103 1.46e6 plus.goog~ com    
##  9          9       8 insta~ com       277145 1.37e6 instagram~ com    
## 10         10       9 apple~ com       276152 1.05e6 apple.com  com    
## # ... with 4,990 more rows, and 4 more variables: PrevGlobalRank <int>,
## #   PrevTldRank <int>, PrevRefSubNets <int>, PrevRefIPs <int>
(med_rows <- nrow(medium_df)) %>% comma() %>% cat("rows")
## 5,000 rows
path_medium_csv <- "test-data/medium_csv.csv"
write_csv(medium_df, path_medium_csv)

Big

The “big” .csv stacks all 1,000,000 rows five times, creating a 5,000,000 row .csv.

(big_df <- test_df %>% 
  rerun(.n = 5) %>% 
  bind_rows())
## # A tibble: 5,000,000 x 12
##    GlobalRank TldRank Domain TLD   RefSubNets RefIPs IDN_Domain IDN_TLD
##         <int>   <int> <chr>  <chr>      <int>  <int> <chr>      <chr>  
##  1          1       1 googl~ com       463232 2.96e6 google.com com    
##  2          2       2 faceb~ com       451237 3.05e6 facebook.~ com    
##  3          3       3 youtu~ com       410764 2.44e6 youtube.c~ com    
##  4          4       4 twitt~ com       409068 2.55e6 twitter.c~ com    
##  5          5       5 micro~ com       303679 1.14e6 microsoft~ com    
##  6          6       6 linke~ com       292966 1.35e6 linkedin.~ com    
##  7          7       1 wikip~ org       287420 1.24e6 wikipedia~ org    
##  8          8       7 plus.~ com       284103 1.46e6 plus.goog~ com    
##  9          9       8 insta~ com       277145 1.37e6 instagram~ com    
## 10         10       9 apple~ com       276152 1.05e6 apple.com  com    
## # ... with 4,999,990 more rows, and 4 more variables:
## #   PrevGlobalRank <int>, PrevTldRank <int>, PrevRefSubNets <int>,
## #   PrevRefIPs <int>
(big_rows <- nrow(big_df)) %>% comma() %>% cat("rows")
## 5,000,000 rows
path_big_csv <- "test-data/big_csv.csv"
write_csv(big_df, path_big_csv)

R

base_col_specs <- c("double", "double", "character",
                    "character", "double", "double",
                    "character", "character", "double",
                    "double", "double", "double")

base_test <- function(path) {
  df <- read.csv(file = path, colClasses = base_col_specs)
  
  return(df)
}

c("r/base_test_small.R", "r/base_test_med.R", "r/base_test_big.R") %>% 
  walk(inspect_script)

# r/base_test_small.R ===========================================================
path_small_csv <- "test-data/small_csv.csv" 
 
base_col_specs <- c("double", "double", "character", 
                    "character", "double", "double", 
                    "character", "character", "double", 
                    "double", "double", "double") 
 
df <- read.csv(file = path_small_csv, colClasses = base_col_specs) 

# r/base_test_med.R =============================================================
path_medium_csv <- "test-data/medium_csv.csv" 
 
base_col_specs <- c("double", "double", "character", 
                    "character", "double", "double", 
                    "character", "character", "double", 
                    "double", "double", "double") 
 
df <- read.csv(file = path_medium_csv, colClasses = base_col_specs) 

# r/base_test_big.R =============================================================
path_big_csv <- "test-data/big_csv.csv" 
 
base_col_specs <- c("double", "double", "character", 
                    "character", "double", "double", 
                    "character", "character", "double", 
                    "double", "double", "double") 
 
df <- read.csv(file = path_big_csv, colClasses = base_col_specs) 

library(readr)

readr_col_specs <- list(col_double(), col_double(), col_character(),
                        col_character(), col_double(), col_double(),
                        col_character(), col_character(), col_double(),
                        col_double(), col_double(), col_double())

readr_test <- function(path) {
  df <- read_csv(file = path, col_types = readr_col_specs)
  
  return(df)
}

c("r/readr_test_small.R", "r/readr_test_med.R", "r/readr_test_big.R") %>% 
  walk(inspect_script)

# r/readr_test_small.R ==========================================================
library(readr) 
 
path_small_csv <- "test-data/small_csv.csv" 
 
readr_col_specs <- list(col_double(), col_double(), col_character(), 
                        col_character(), col_double(), col_double(), 
                        col_character(), col_character(), col_double(), 
                        col_double(), col_double(), col_double()) 
 
df <- read_csv(file = path_small_csv, col_types = readr_col_specs) 

# r/readr_test_med.R ============================================================
library(readr) 
 
path_medium_csv <- "test-data/medium_csv.csv" 
 
readr_col_specs <- list(col_double(), col_double(), col_character(), 
                        col_character(), col_double(), col_double(), 
                        col_character(), col_character(), col_double(), 
                        col_double(), col_double(), col_double()) 
 
df <- read_csv(file = path_medium_csv, col_types = readr_col_specs) 

# r/readr_test_big.R ============================================================
library(readr) 
 
path_big_csv <- "test-data/big_csv.csv" 
 
readr_col_specs <- list(col_double(), col_double(), col_character(), 
                        col_character(), col_double(), col_double(), 
                        col_character(), col_character(), col_double(), 
                        col_double(), col_double(), col_double()) 
 
df <- read_csv(file = path_big_csv, col_types = readr_col_specs) 

library(data.table)

datatable_col_specs <- c("double", "double", "character",
                         "character", "double", "double",
                         "character", "character", "double",
                         "double", "double", "double")

datatable_test <- function(path) {
  df <- fread(file = path, colClasses = datatable_col_specs)
  
  return(df)
}

c("r/datatable_test_small.R", "r/datatable_test_med.R", "r/datatable_test_big.R") %>% 
  walk(inspect_script)

# r/datatable_test_small.R ======================================================
library(data.table) 
 
path_small_csv <- "test-data/small_csv.csv" 
 
datatable_col_specs <- c("double", "double", "character", 
                         "character", "double", "double", 
                         "character", "character", "double", 
                         "double", "double", "double") 
 
df <- fread(file = path_small_csv, colClasses = datatable_col_specs) 

# r/datatable_test_med.R ========================================================
library(data.table) 
 
path_medium_csv <- "test-data/medium_csv.csv" 
 
datatable_col_specs <- c("double", "double", "character", 
                         "character", "double", "double", 
                         "character", "character", "double", 
                         "double", "double", "double") 
 
df <- fread(file = path_medium_csv, colClasses = datatable_col_specs) 

# r/datatable_test_big.R ========================================================
library(data.table) 
 
path_big_csv <- "test-data/big_csv.csv" 
 
datatable_col_specs <- c("double", "double", "character", 
                         "character", "double", "double", 
                         "character", "character", "double", 
                         "double", "double", "double") 
 
df <- fread(file = path_big_csv, colClasses = datatable_col_specs) 

Python

import pandas
path_small_csv = 'test-data/small_csv.csv'
path_medium_csv = 'test-data/medium_csv.csv'
path_big_csv = 'test-data/big_csv.csv'
pandas_col_specs = {
  'GlobalRank':float, 'TldRank':float, 'Domain':str,
  'TLD':str, 'RefSubNets':float, 'RefIPs':float,
  'IDN_Domain':str, 'IDN_TLD':str, 'PrevGlobalRank':float,
  'PrevTldRank':float, 'PrevRefSubNets':float, 'PrevRefIPs':float
  }
def pandas_test_small():
  df = pandas.read_csv(filepath_or_buffer = path_small_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)
  
def pandas_test_medium():
  df = pandas.read_csv(filepath_or_buffer = path_medium_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)
  
def pandas_test_big():
  df = pandas.read_csv(filepath_or_buffer = path_big_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)

c("py/pandas_test_small.py", "py/pandas_test_med.py", "py/pandas_test_big.py") %>% 
  walk(inspect_script)

# py/pandas_test_small.py =======================================================
import pandas 
 
path_small_csv = 'test-data/small_csv.csv' 
   
pandas_col_specs = { 
  'GlobalRank':float, 'TldRank':float, 'Domain':str, 
  'TLD':str, 'RefSubNets':float, 'RefIPs':float, 
  'IDN_Domain':str, 'IDN_TLD':str, 'PrevGlobalRank':float, 
  'PrevTldRank':float, 'PrevRefSubNets':float, 'PrevRefIPs':float 
  } 
 
df = pandas.read_csv(filepath_or_buffer = path_small_csv, 
                     dtype = pandas_col_specs, low_memory = False) 

# py/pandas_test_med.py =========================================================
import pandas 
 
path_medium_csv = 'test-data/medium_csv.csv' 
 
pandas_col_specs = { 
  'GlobalRank':float, 'TldRank':float, 'Domain':str, 
  'TLD':str, 'RefSubNets':float, 'RefIPs':float, 
  'IDN_Domain':str, 'IDN_TLD':str, 'PrevGlobalRank':float, 
  'PrevTldRank':float, 'PrevRefSubNets':float, 'PrevRefIPs':float 
  } 
 
df = pandas.read_csv(filepath_or_buffer = path_medium_csv, 
                     dtype = pandas_col_specs, low_memory = False) 

# py/pandas_test_big.py =========================================================
import pandas 
 
path_big_csv = 'test-data/big_csv.csv' 
 
pandas_col_specs = { 
  'GlobalRank':float, 'TldRank':float, 'Domain':str, 
  'TLD':str, 'RefSubNets':float, 'RefIPs':float, 
  'IDN_Domain':str, 'IDN_TLD':str, 'PrevGlobalRank':float, 
  'PrevTldRank':float, 'PrevRefSubNets':float, 'PrevRefIPs':float 
  } 
 
df = pandas.read_csv(filepath_or_buffer = path_big_csv, 
                     dtype = pandas_col_specs, low_memory = False) 

py_run_string(
"
import pandas

path_small_csv = 'test-data/small_csv.csv'
path_medium_csv = 'test-data/medium_csv.csv'
path_big_csv = 'test-data/big_csv.csv'

pandas_col_specs = {
  'GlobalRank':float, 'TldRank':float, 'Domain':str,
  'TLD':str, 'RefSubNets':float, 'RefIPs':float,
  'IDN_Domain':str, 'IDN_TLD':str, 'PrevGlobalRank':float,
  'PrevTldRank':float, 'PrevRefSubNets':float, 'PrevRefIPs':float
  }

def retic_pandas_test_small():
  df = pandas.read_csv(filepath_or_buffer = path_small_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)

def retic_pandas_test_medium():
  df = pandas.read_csv(filepath_or_buffer = path_medium_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)

def retic_pandas_test_big():
  df = pandas.read_csv(filepath_or_buffer = path_big_csv,
                dtype = pandas_col_specs, low_memory = False)
  return(df)

", convert = FALSE
)

Dependencies Only

c("r/test_load_readr.R", "r/test_load_datatable.R", "py/test_load_pandas.py") %>% 
  walk(inspect_script)

File available at https://github.com/syknapptic/syknapptic/tree/master/content/post/r/test_load_readr.R

# r/test_load_readr.R ===========================================================
library(readr) 

File available at https://github.com/syknapptic/syknapptic/tree/master/content/post/r/test_load_datatable.R

# r/test_load_datatable.R =======================================================
library(data.table) 

File available at https://github.com/syknapptic/syknapptic/tree/master/content/post/py/test_load_pandas.py

# py/test_load_pandas.py ========================================================
def square(x): 
  return x**2 
 
def evens(x): 
  y = [] 
  for i in x: 
    if i // 2 == 0: 
      y.append(i) 
  return(y) 
 
 
def ceci_nest_pas_une_pipe(args, *funs): 
  for arg in args: 
    for fun in funs: 
      arg = fun(arg) 
  return arg 
 
ceci_nest_pas_une_pipe([1, 2, 3, 4], even) 

Initial Carpentry

package_results_df <- package_results %>% 
  unnest() %>% 
  mutate(package = case_when(
    str_detect(expression, "datatable") ~ "data.table",
    str_detect(expression, "readr") ~ "readr",
    str_detect(expression, "pandas") ~ "pandas"
  )) %>% 
  mutate(call = case_when(
    package == "data.table" ~ "library(data.table)",
    package == "readr" ~ "library(readr)",
    package == "pandas" ~ "import pandas"
  ))

package_medians_df <- package_results_df %>% 
  rename(median_package = median, min_package = min, max_package = max) %>%
  distinct(package, median_package, min_package, max_package) %>% 
  add_row(median_package = bench_time(0), package = "utils")
all_exprs <- results$expression
system_calls <- all_exprs %>% str_subset("^system\\(")
local_r_fun_calls <- all_exprs %>% str_subset("^(base|readr|datatable)_test\\(")
python_eng_calls <- all_exprs %>% str_subset("^py\\$")
reticulate_calls <- all_exprs %>% str_subset("py_run")
knitr_calls <- c(local_r_fun_calls, python_eng_calls, reticulate_calls)

results_df <- results %>%
  unnest() %>%
  mutate(package = case_when(
    str_detect(expression, "datatable") ~ "data.table",
    str_detect(expression, "readr") ~ "readr",
    str_detect(expression, "pandas") ~ "pandas",
    TRUE ~ "utils"
  )) %>% 
  mutate(call = case_when(
    str_detect(expression, "base") ~ "utils::read.csv()",
    str_detect(expression, "readr") ~ "readr::read_csv()",
    str_detect(expression, "datatable") ~ "data.table::fread()",
    str_detect(expression, "py_run_string") ~ "reticulate::py_run_string()",
    str_detect(expression, "py_run_file") ~ "reticulate::py_run_file()",
    str_detect(expression, "pandas") ~ "pandas.read_csv()"
      ) %>%
      str_pad(max(nchar(.)), side = "right") # enforce left alignment in plots
    ) %>%
  mutate(execution_type = case_when(
    expression %in% system_calls ~ "Sourced Script",
    expression %in% knitr_calls ~ "knitr Engine"
    )) %>%
  mutate(dependency_status = case_when(
    expression %in% system_calls ~ "Dependencies Loaded on Execution (Sourced Script)",
    expression %in% knitr_calls ~ "Dependencies Pre-Loaded")) %>% 
  mutate(lang = if_else(str_detect(expression, "pandas"), "Python", "R")) %>%
  mutate(file_size = str_extract(expression, "small|med|big")) %>%
  mutate(rows = case_when(
    file_size == "small" ~ small_rows,
    file_size == "med" ~ med_rows,
    file_size == "big" ~ big_rows
    )) %>% 
  left_join(package_medians_df, by = "package")

gg_df <- results_df %>%
  mutate(n_rows = rows) %>% 
  arrange(rows) %>%
  mutate(rows = rows %>%
           comma() %>%
           paste("Rows") %>%
           as_factor()
        ) %>%
  group_by(expression) %>% 
  mutate(med_time = as.numeric(median(time))) %>% 
  ungroup() %>% 
  arrange(desc(med_time)) %>%
  mutate(call = as_factor(call)) %>%
  arrange(desc(lang)) %>%
  mutate(lang = as_factor(lang))

Execution Times

At 100 rows, R is faster, with base R’s utils::read.csv() finishing first.

gg_df %>%
  filter(file_size == "small") %>% 
  plot_times(facet = dependency_status)

At 5,000 rows, R is still faster. In the sourced scripts, pandas.read_csv() has nearly caught up with utils::read.csv(), but data.table::fread() has pulled away.

gg_df %>%
  filter(file_size == "med") %>% 
  plot_times(facet = dependency_status)

At 5,000,000 million rows, we’ve reached the size where time differences would actually be noticeable.

The advantage ofutils::read.csv()’s lack of dependencies has run its course and pandas.read_csv() is faster in nearly every case.

That said, readr::read_csv() is still faster than pandas.read_csv() and, like most R users would expect, data.table::fread() is by far the fastest.

gg_df %>%
  filter(file_size == "big") %>% 
  plot_times(facet = dependency_status)

Dependency Load Times

package_results_df %>%
  mutate(lang = if_else(str_detect(expression, "pandas"), "Python", "R")) %>% 
  arrange(desc(lang)) %>%
  mutate(lang = as_factor(lang)) %>% 
  plot_times()

gg_df %>% 
  filter(dependency_status == "Dependencies Loaded on Execution (Sourced Script)") %>%  
  filter(file_size == "big") %>% 
  mutate(adjusted_time = if_else(lang == "Python", time - max_package, NA_real_))  %>% 
  rename(original_time = time) %>% 
  gather(time_type, time, original_time, adjusted_time) %>% 
  drop_na(time) %>% 
  mutate(descrip = case_when(
    lang == "R" ~ "Original R Time",
    lang == "Python" & time_type == "original_time" ~ "Original Python Time",
    lang == "Python" & time_type == "adjusted_time" ~ "Adjusted Python Time"
    )) %>% 
  arrange(desc(descrip)) %>% 
  mutate(descrip = as_factor(descrip)) %>% 
  ggplot(aes(call, time, fill = descrip)) +
  stat_ydensity(width = 1, size = 0, color = "transparent", scale = "width", bw = 0.01,
                trim = FALSE) +
  scale_fill_manual(values = c("#165CAA", "#ffde57", "#ff9051"), 
                    labels = c(t_R, t_Python, t_import_pandas)) +
  guides(fill = guide_legend(nrow = 3, label.hjust = 0)) +
  coord_flip() +
  theme_simple() +
  labs(x = NULL, y = "Execution Time",
       title = "Comparing Sourced Scripts with Adjusted Python Times",
       caption = str_glue("CSV to Data Frame: {comma(big_rows)} Rows")
      )

Summary Tables

results_df %>%
  select(rows, lang, execution_type, call, mean, median, `itr/sec`, n_gc, mem_alloc) %>% 
  distinct() %>% 
  arrange(rows, desc(lang)) %>%
  mutate(rows = comma(rows), 
         `itr/sec` = round(`itr/sec`, 2),
         n_gc = ifelse(execution_type == "Sourced Script", "unknown", n_gc),
         mem_alloc = ifelse(execution_type == "Sourced Script", "unknown", mem_alloc)) %>% 
  mutate_at(vars(-c(rows, lang)), 
            funs(cell_spec(., background = ifelse(lang == "R", "#f2f2f2", "#edf9ff"),
                              color = ifelse(lang == "R", "#002963", "#809100"))
                )) %>% 
  mutate(lang = lang %>% cell_spec(background = ifelse(lang == "R", "#f2f2f2", "#edf9ff"),
                                   color = ifelse(lang == "R", "#002647", "#809100"))) %>% 
  mutate(n_gc = if_else(str_detect(n_gc, "unknown"), "unknown", n_gc),
         mem_alloc = if_else(str_detect(mem_alloc, "unknown"), "unknown", mem_alloc)) %>%
  rename(garbage_collections = n_gc, language = lang, memory_allocated = mem_alloc) %>%
  rename_all(funs(str_to_title(str_replace(., "_", " ")))) %>%
  kable(caption = "CSV to Data Frame Times", escape = FALSE, digits = 2) %>%
  kable_styling(bootstrap_options = "condensed", font_size = 12) %>% 
  collapse_rows(columns = 1:3, valign = "top")

package_results_df %>% 
  mutate(lang = if_else(str_detect(expression, "\\.py"), "Python", "R"),
         `itr/sec` = round(`itr/sec`, 2)) %>% 
  select(lang, call, min, mean, median, max, `itr/sec`) %>% 
  distinct() %>% 
  mutate_at(vars(-lang), 
            funs(cell_spec(., background = ifelse(lang == "R", "#f2f2f2", "#edf9ff"),
                              color = ifelse(lang == "R", "#002963", "#809100"))
            )) %>% 
  mutate(lang = lang %>% cell_spec(background = ifelse(lang == "R", "#f2f2f2", "#edf9ff"),
                                   color = ifelse(lang == "R", "#002647", "#809100"))) %>% 
  rename(language = lang) %>% 
  rename_all(str_to_title) %>% 
  kable(caption = "Dependency Load Times", escape = FALSE, digits = 2) %>%
  kable_styling(bootstrap_options = "condensed", font_size = 12) %>% 
  collapse_rows(columns = 1, valign = "top")

IDE

rstudio_info <- rstudioapi::versionInfo() # obtain in interactive session
write_rds(rstudio_info, "test-data/rstudio_info.rds")
read_rds("test-data/rstudio_info.rds") %>% 
  as_tibble() %>% 
  mutate(IDE = "RStudio") %>% 
  select(IDE, mode, version) %>% 
  mutate(version = as.character(version)) %>% 
  kable() %>% 
  kable_styling(full_width = FALSE)

R

sessionInfo()
## R version 3.5.1 (2018-07-02)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 17134)
## 
## Matrix products: default
## 
## locale:
## [1] LC_COLLATE=English_United States.1252 
## [2] LC_CTYPE=English_United States.1252   
## [3] LC_MONETARY=English_United States.1252
## [4] LC_NUMERIC=C                          
## [5] LC_TIME=English_United States.1252    
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] data.table_1.11.5     bindrcpp_0.2.2        forcats_0.3.0        
##  [4] stringr_1.3.1         dplyr_0.7.6           purrr_0.2.5          
##  [7] readr_1.1.1           tidyr_0.8.1           tibble_1.4.2.9004    
## [10] ggplot2_3.0.0.9000    tidyverse_1.2.1.9000  scales_0.5.0.9000    
## [13] reticulate_1.9.0.9001 kableExtra_0.9.0      bench_1.0.1          
## 
## loaded via a namespace (and not attached):
##  [1] Rcpp_0.12.17      lubridate_1.7.4   lattice_0.20-35  
##  [4] utf8_1.1.4        assertthat_0.2.0  digest_0.6.15    
##  [7] psych_1.8.4       R6_2.2.2          cellranger_1.1.0 
## [10] plyr_1.8.4        evaluate_0.10.1   highr_0.7        
## [13] httr_1.3.1        blogdown_0.7.1    pillar_1.3.0.9000
## [16] rlang_0.2.1       lazyeval_0.2.1    readxl_1.1.0     
## [19] rstudioapi_0.7    Matrix_1.2-14     rmarkdown_1.10.7 
## [22] selectr_0.4-1     foreign_0.8-70    munsell_0.5.0    
## [25] broom_0.4.5       compiler_3.5.1    modelr_0.1.2     
## [28] xfun_0.3          pkgconfig_2.0.1   mnormt_1.5-5     
## [31] htmltools_0.3.6   tidyselect_0.2.4  bookdown_0.7     
## [34] fansi_0.2.3       viridisLite_0.3.0 crayon_1.3.4     
## [37] withr_2.1.2       grid_3.5.1        nlme_3.1-137     
## [40] jsonlite_1.5      gtable_0.2.0      magrittr_1.5     
## [43] cli_1.0.0         stringi_1.2.3     profmem_0.5.0    
## [46] reshape2_1.4.3    xml2_1.2.0        htmldeps_0.1.0   
## [49] tools_3.5.1       glue_1.2.0        hms_0.4.2        
## [52] parallel_3.5.1    yaml_2.1.19       colorspace_1.3-2 
## [55] rvest_0.3.2       knitr_1.20.8      bindr_0.1.1      
## [58] haven_1.1.2

Python

import sys
import numpy
import pandas
print(sys.version)
## 3.6.6 |Anaconda, Inc.| (default, Jun 28 2018, 11:27:44) [MSC v.1900 64 bit (AMD64)]
print(numpy.__version__)
## 1.14.5
print(pandas.__version__)
## 0.23.1

System

cat("CPU:\n", system("wmic cpu get name", intern = TRUE)[[2]])
## CPU:
##  Intel(R) Core(TM) i7-6700HQ CPU @ 2.60GHz  

ram_df <- system("wmic MEMORYCHIP get BankLabel, Capacity, Speed", intern = TRUE) %>% 
  str_trim() %>% 
  as_tibble() %>% 
  slice(2:3) %>% 
  separate(value, into = c("BankLabel", "Capacity", "Speed"), sep = "\\s{2,}")

ram_df %>% 
  rename_all(str_replace, "L", " L") %>% 
  kable() %>% 
  kable_styling(full_width = FALSE)

ram_df %>% 
  mutate(Capacity = as.numeric(Capacity) / 1e9,
         Speed = as.numeric(Speed)) %>% 
  summarise(`Capacity in GB` = sum(Capacity),
            `Speed in MHz` = unique(Speed)) %>% 
  kable() %>% 
  kable_styling(full_width = FALSE)

cat("SSD:\n", system("wmic diskdrive get Model", intern = TRUE)[[2]])
## SSD:
##  PM951 NVMe SAMSUNG 512GB