patternproject

## anti-join vs setdiff
# The main idea comes from this post:
# http://zevross.com/blog/2014/08/05/using-the-r-function-anti_join-to-find-unmatched-records/

# Setting up
df.1 <- data.frame(
  state = rep(1:3, each=2),
  country = rep(c("A","B"),3),
  vals = rnorm(6)
)

## different_iteration.r
# Helper Function
fn_downloadZip <- function(URL) {

  myzip <- unz(URL, filename=basename(URL))
  c.zip.name = "test.zip"
  c.file.path = file.path(c.home.dir,c.data.dir,c.zip.name)
  c.data.folder = file.path(c.home.dir,c.data.dir)
  download.file(URL, destfile=c.file.path)
  f.name = unzip(c.file.path, exdir=c.data.folder)


## gist:0a7ade8fa3d85453076d9bafc2087127
Hi,

-----------------------------------
PROBLEM STATEMENT
-----------------------------------
I want to generate URLS for each month for each year as follows:

[...]
https://s3.amazonaws.com/data/201611.csv.zip
https://s3.amazonaws.com/data/201612.csv.zip

## sessionizationInR.r
## `````````````````````````````````````````````
#### Read Me ####
## `````````````````````````````````````````````
## Trying to implement "sessionization" in R
## Details here:
## https://www.dataiku.com/learn/guide/code/reshaping_data/sessionization.html
## `````````````````````````````````````````````

## `````````````````````````````````````````````
#### Load Libraries ####

## .block
license: mit

## Secrets of Success.csv

          
            Social Strata
            Reason
            Rate

            
              Rich people
              good education, high qualification
              28%

            
              Middle class
              good education, high qualification
              33%

            
              Poor
              good education, high qualification
              18%

            
              Rich people
              cunning, cheating
              11%

            
              Middle class
              cunning, cheating
              21%

            
              Poor
              cunning, cheating
              32%

            
              Rich people
              abilities, talents
              13%

            
              Middle class
              abilities, talents
              8%

            
              Poor
              abilities, talents
              7%

## pmap-v1.r
# -------------------
# HELPER FUNCTION
# -------------------
# fn to search rank
# INPUT: year (integer)
# OUTPUT: rank (integer)
# SRC:
# http://adv-r.had.co.nz/Functions.html
# https://cran.r-project.org/web/packages/ArgumentCheck/vignettes/ArgumentChecking.html

## saveListOfDfAsCsv.r
# list of all data frames
s.df = names(which(sapply(.GlobalEnv, is.data.frame)))

# list of data frames with .p. in their names
s.df.p = s.df[str_detect(s.df,regex("\\.p\\.",ignore_case = FALSE))]

# creating path
paths <- paste0(s.df.p,".1", ".csv")

# helper function

## glitchulate.py
from __future__ import print_function

import sys
import random

from collections import deque

from PIL import Image

# THIS IS THE MAGIC VALUE THAT MAKES EVERYTHING GLITCHED

## expand in ggplot2
#### Load Data ####
df.winners = read.csv(
  "winnersWithMean.csv",
  header = TRUE,
  stringsAsFactors = FALSE,
  na.strings = c("", "NA")
)

# dput for df.winners
# at the end of the code