| # extracted from http//www.naturalearthdata.com/download/110m/cultural/ne_110m_admin_0_countries.zip | |
| # under public domain terms | |
| country_bounding_boxes = { | |
| 'AF': ('Afghanistan', (60.5284298033, 29.318572496, 75.1580277851, 38.4862816432)), | |
| 'AO': ('Angola', (11.6400960629, -17.9306364885, 24.0799052263, -4.43802336998)), | |
| 'AL': ('Albania', (19.3044861183, 39.624997667, 21.0200403175, 42.6882473822)), | |
| 'AE': ('United Arab Emirates', (51.5795186705, 22.4969475367, 56.3968473651, 26.055464179)), | |
| 'AR': ('Argentina', (-73.4154357571, -55.25, -53.628348965, -21.8323104794)), | |
| 'AM': ('Armenia', (43.5827458026, 38.7412014837, 46.5057198423, 41.2481285671)), |
| #------------------------------------------------------------ | |
| # REVOLUTION ANALYTICS WEBINAR: INTRODUCTION TO R FOR DATA MINING | |
| # February 14, 2013 | |
| # Joseph B. Rickert | |
| # Technical Marketing Manager | |
| # | |
| # BIG DATA with RevoScaleR | |
| # | |
| # Copyright: Revolution Analytics |
| s0 <- knitr::knit_hooks$get('source') | |
| o0 <- knitr::knit_hooks$get('output') | |
| p0 <- knitr::knit_hooks$get('plot') | |
| knitr::knit_hooks$set( | |
| list( | |
| source=function(x,options){ | |
| if (is.null(options$class)) s0(x, options) |
As far as I know Rstudio does not count words or characters at the moment, which would be useful particularly when writing Rmarkdown.
This is a quick shortcut using word_count and character_count functions from qdap package. See below for two wrapper functions that simplify their use.
library("qdap")
Just select and copy the text to the clipboard and then run in the console:
| c0 <- knitr::knit_hooks$get('chunk') | |
| knitr::knit_hooks$set( | |
| list( | |
| chunk=function(x,options){ | |
| if(is.null(options$class) & is.null(options$fragIndex)){ | |
| c0(x, options) | |
| } else if(is.null(options$fragIndex)) { | |
| classidx <- which(names(options)=="class") |
| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
| import numpy as np | |
| import cPickle as pickle | |
| import gym | |
| # hyperparameters | |
| H = 200 # number of hidden layer neurons | |
| batch_size = 10 # every how many episodes to do a param update? | |
| learning_rate = 1e-4 | |
| gamma = 0.99 # discount factor for reward |
| class MyStreamListener(tweepy.StreamListener): | |
| def __init__(self, api=None): | |
| super(MyStreamListener, self).__init__() | |
| self.num_tweets = 0 | |
| self.file = open("tweets.txt", "w") | |
| def on_status(self, status): | |
| tweet = status._json | |
| self.file.write( json.dumps(tweet) + '\n' ) | |
| self.num_tweets += 1 |
![screenshot][]
In the following we will be using R’s “restarts” feature to implement the state machine that drives generators in languages such as Python. Generators allow lazily generating values on demand: a consumer invokes a generator, and consumes values as they are produced. A new value is only produced once the previous one has been consumed.
| gh_migrate("YOUR_GITHUB_USERNAME", "GITHUB_REPO") | |
| gitea_user <- function(gitea_username, | |
| api_endpoint = Sys.getenv("GITEA_BASE_URL"), | |
| gitea_token = Sys.getenv("GITEA_PAT")) { | |
| require("httr", quietly = TRUE) | |
| require("jsonlite", quietly = TRUE) | |
| httr::GET( |
| library(glue) | |
| vv_transformer <- function(text, envir) { | |
| regex <- "=$" | |
| if (!grepl(regex, text)) { | |
| return(identity_transformer(text, envir)) | |
| } | |
| text <- sub(regex, "", text) | |
| res <- identity_transformer(text, envir) | |
| n <- length(res) |