szilard

library(yaml)
library(RJSONIO)
library(httr)

event_id <- 132296372
n_max <- 20

api_key <- yaml.load_file("meetup_api_key.yml")$api_key
  ## get your api key from  http://www.meetup.com/meetup_api/key/  while logged in 

szilard

library(Matrix)

rm(list=ls())

set.seed(123)


## parameters

n <- 1e6

szilard

library(RJSONIO)
library(httr)
library(ggplot2)

api_key <- scan("~/.meetup.apikey", character(), quiet = TRUE)
group_id <- 1414043   ## LA R meetup

req_url <- paste0("http://www.meetup.com/2/events?key=", api_key, 
                  "&group_id=",group_id,"&status=past")
events_data <- fromJSON(rawToChar(GET(req_url)$content))$results

szilard

---
runtime: shiny
output: html_document
---


```{r, echo=FALSE}
inputPanel(
  selectInput("n", label = "n:", choices = c(10,50)),
  submitButton("Update")

szilard

library(dplyr)

read.csv("members_export.csv") %>%
  mutate(pcrnk = percent_rank(CONFIRM_TIME), wdbl = ifelse(LinkedIn!="",2,1),
      w = (3-2*pcrnk)*wdbl) %>%
  sample_n(30, weight = w) %>% 
  mutate(name = paste(First.Name,Last.Name)) %>% select(name)

szilard

## Minimal example of R's data.table vs pandas aggregation and join benchmark
## ( more detailed but still basic benchmark here:
##   http://datascience.la/dplyr-and-a-very-basic-benchmark/ )

## Just copy paste into R and Ipython, respectively
## Timings on a decent server with data.table 1.9.4 & pandas 0.15.1 (Nov 2014)

szilard

abbr <- input$inp_abbr
dbGetQuery(con, paste0("select * from states where abbr = '",abbr,"'"))

szilard

abbr <- validinp_character(input$inp_abbr)
## or:
abbr <- validinp_character(input$inp_abbr, pattern="^((CA)|(NY))$")

szilard

library(randomForest)
library(parallel)

genr_data <- function(n,p) { 
  X <- matrix(rnorm(n*p),n,p)
  y <- as.factor(apply(X,1, function(x) 
    ifelse(sum(x^2)>qchisq(0.5,p),"+","-")))
    ## Hastie etal 10.2
  data.frame(X,y)

szilard

import numpy as np
from scipy.stats import chi2
from sklearn.ensemble import RandomForestClassifier

n = 1000
p = 100

def genr_data(n,p):
  X = np.random.randn(n,p)
  y = np.zeros(n)