Leo Lee Leo-Lee15

R to python data wrangling snippets

The dplyr package in R makes data wrangling significantly easier. The beauty of dplyr is that, by design, the options available are limited. Specifically, a set of key verbs form the core of the package. Using these verbs you can solve a wide range of data problems effectively in a shorter timeframe. Whilse transitioning to Python I have greatly missed the ease with which I can think through and solve problems using dplyr in R. The purpose of this document is to demonstrate how to execute the key dplyr verbs when manipulating data using Python (with the pandas package).

dplyr is organised around six key verbs:

#devtools::install_github("r-lib/gh")
library(gh)
#devtools::install_github("romainfrancois/dplyr5000")
library(dplyr5000)
library(tidyverse)
library(grid) 
library(magick)
#> Linking to ImageMagick 6.9.7.4
#> Enabled features: fontconfig, freetype, fftw, lcms, pango, x11

	library(shiny)
	library(htmltools)
	library(rhandsontable)
	library(dplyr)

	rht <- rhandsontable(
	head(mtcars) %>%
	mutate(name = rownames(.)) %>%
	select(name, everything()),
	rowHeaders = NULL

	library(rayrender)

	#Create base scene
	basescene = xz_rect(x=555/2,y=0.1,z=555/2,555,555,
	material = lambertian(color="#bababa", checkercolor = "grey10", checkerperiod = 100)) %>%
	add_object(xz_rect(x=555/2,y=1000,z=555/2,343,332,
	material = lambertian(color="white", lightintensity=40,implicit_sample = TRUE),
	flipped=TRUE))

	#Function for sphere bouncing

	titanic_1tree = h2o.gbm(x = predictors, y = response,
	training_frame = titanicHex,
	ntrees = 1, min_rows = 1, sample_rate = 1, col_sample_rate = 1,
	max_depth = 5,
	# use early stopping once the validation AUC doesn't improve by at least 0.01%
	# for 5 consecutive scoring events
	stopping_rounds = 3, stopping_tolerance = 0.01,
	stopping_metric = "AUC",
	seed = 1)

	Rscript -e 'print("us")' # 执行`print("us")`这一行R代码
	Rscript test_R.R # 执行`test_R.R`脚本

	## library(stringr)
	## xx <- c("we are", "There are", "All are")
	## str_replace_all(xx, pattern = "are", replacement = "是")

	library(fstplyr)
	path <- tempfile()
	dir.create(path)
	fst::write_fst(iris, file.path(path, "iris.fst"))
	fst::write_fst(mtcars, file.path(path, "mtcars.fst"))
	# usage of the file.path() function
	file.path("C:/Users/Lenovo/Documents", "mtcars.xlsx")
	# results: "C:/Users/Lenovo/Documents/mtcars.xlsx"

	# create a big tibble, about 2GB


	# based on a article from here https://dirkschumacher.github.io/ompr/articles/problem-graph-coloring.html

	library(maptools)
	library(dplyr)

	# devtools::install_github("dirkschumacher/ompr@milp")

	# CC by
	map_data <- rgdal::readOGR("https://raw.githubusercontent.com/nvkelso/natural-earth-vector/master/geojson/ne_50m_admin_0_countries.geojson", "OGRGeoJSON")

	################################################################################
	# Loading data

	rm( list=ls() )

	# load libs
	require(neuralnet)
	require(nnet)

	# Load data and set names