MarkEdmondson1234

## functions.R 
library(rga) 
library(dygraphs) 
library(zoo) 
library(tidyr) 
library(lubridate) 
library(d3heatmap) 
library(dplyr) 
library(stringr) 
library(DT) 

MarkEdmondson1234

## A script to download and archive Google search analytics
##
## Demo of searchConsoleR R package.
##
## Version 1 - 10th August 2015
##
## Mark Edmondson (http://markedmondson.me)

## load the required libraries 
## (Download them with install.packages("googleAuthR") and install.packages("searchConsoleR" if necessary

MarkEdmondson1234

## assuming you have a folder full of .csv's to merge
## csv's must all have identical column names.

folder <- "./path/to/csv/files"
filenames <- list.files(folder)

all_files <- Reduce(rbind, lapply(filenames, read.csv))

MarkEdmondson1234

library(googleAuthR)

## change the native googleAuthR scopes to the one needed.
options("googleAuthR.scopes.selected" = 
        c("https://www.googleapis.com/auth/urlshortener"))

#' Shortens a url using goo.gl
#'
#' @param url URl to shorten with goo.gl
#' 

MarkEdmondson1234

## in global.R
library(googleAuthR)
options("googleAuthR.scopes.selected" = c("https://www.googleapis.com/auth/urlshortener"))


shorten_url <- function(url){

  body = list(
    longUrl = url
  )

MarkEdmondson1234

install.packages("googleAuthR")

MarkEdmondson1234

library(googleAnalyticsR_public)

gar_auth(new_user=T)

## your profile view Id
id <- "XXXXXX"

## 61607 results
## 30049 unique Ids
## 185 Sku's

MarkEdmondson1234

## want: 30049 x 187 
## userId, product1_view, product2_view, ...., productN_view, productBought
pv <- reshape2::recast(product_views, 
                       dimension1 ~ productSku + variable, 
                       fun.aggregate=sum)

library(dplyr)
## if a user buys more than once, the row will be duplicated
pt <-  product_trans %>% select(productSku, dimension1)

MarkEdmondson1234

library(randomForest)
## warning - can take a long time (30mins)
rf <- randomForest(x = predictors, y = response)

## once model done, we run it using test data and compare results to reality
predictor_test <- test[,which(!names(test) %in% c("dimension1","boughtSku"))]
response_test <- as.factor(test[,"boughtSku"])

## check result on test set
prediction <- predict(rf, predictor_test)

MarkEdmondson1234

## function to get plot data format
getCompareTable <- function (test_data, prediction) {
  require(dplyr)
  
  ## plot real vs model bought Sku
  actual_freq <- table(model_data$boughtSku)
  predicted_freq <- table(prediction)
  
  actual_freq <- actual_freq[order(actual_freq)]
  predicted_freq <- predicted_freq[order(predicted_freq)]