inst/scripts/testing_codes.R

In credoinc/credoc: Credo Consulting Convenience Functions

library(credobb3)
starting_year <- 2013
ending_year <- 2017
dat <- credobb_loadraw(reload = TRUE)
verbatims <- c()
for(year in starting_year:ending_year){
  df <- dat[[paste0("y",year)]]
  first <- as.character(df$q6.1)
  others <- c(as.character(df$q6b.1),
              as.character(df$q6b.2),
              as.character(df$q6b.3),
              as.character(df$q6b.4),
              as.character(df$q6b.5),
              as.character(df$q6b.6),
              as.character(df$q6b.7),
              as.character(df$q6b.8))
  verbatims <- c(verbatims,first,others)
}
m <- verbatims
trim <- function (x) gsub("^\\s+|\\s+$", "", x)
m <- as.character(verbatims)
m <- tolower(m)
m <- trim(m)


m[which(m =="")] <- NA # Drop blanks
m[grep("aeg",m)] <- NA
m[grep("agf",m)] <- NA
m[grep("aim",m)] <- NA
m[grep("aic",m)] <- NA
m[grep("alta",m)] <- NA
m[grep("altra",m)] <- NA
m[grep("arrow",m)] <- NA
m[grep("acuity",m)] <- NA
m[grep("acut",m)] <- NA
m[grep("aston",m)] <- NA
m[grep("b2b",m)] <- NA
m[grep("b to b",m)] <- NA
m[grep("bmo etfs",m)] <- NA
m[grep("bmo",m)] <- NA
m[grep("bullion",m)] <- NA
m[grep("beut",m)] <- NA
m[grep("buet",m)] <- NA
m[grep("brande",m)] <- NA
m[grep("bridge",m)] <- NA
m[grep("bridgehouse",m)] <- NA
m[grep("^cam$",m)] <- NA
m[grep("canoe",m)] <- NA
m[grep("canada life",m,fixed=TRUE)] <- NA
m[grep("canada vie",m,fixed=TRUE)] <- NA
m[grep("cibc",m)] <- NA
m[grep("ci$",m)] <- NA
m[grep("^ci",m)] <- NA
m[grep("c.i",m,fixed=TRUE)] <- NA
m[grep("c i",m,fixed=TRUE)] <- NA
m[grep("ci investments",m,fixed=TRUE)] <- NA
m[grep("ci funds",m,fixed=TRUE)] <- NA
m[grep("clarin",m)] <- NA
m[grep("counsel",m)] <- NA
m[grep("consel",m)] <- NA
m[grep("dimen",m)] <- NA
m[grep("desjar",m)] <- NA
m[grep("dominion",m)] <- NA
m[grep("dfa",m)] <- NA
m[grep("dy",m)]  <- NA
m[grep("edge",m)] <- NA
m[grep("empire",m)] <- NA
m[grep("ethical",m)] <- NA
m[grep("excel",m)] <- NA
m[grep("equity asso",m)] <- NA
m[grep("equitable",m)] <- NA
m[grep("fid",m)] <- NA
m[grep("fiera",m)] <- NA
m[grep("first",m)] <- NA
m[grep("frankli",m)] <- NA
m[grep("front",m)] <- NA
m[grep("ggof",m)] <- NA
m[grep("growthwork",m)] <- NA
m[grep("great",m)] <- NA
m[grep("guardian",m)] <- NA
m[grep("harvest",m)] <- NA
m[grep("horizon",m)] <- NA
m[grep("^ia$",m)] <- NA
m[grep("ia clar",m,fixed=TRUE)] <- NA
m[grep("industrial",m)] <- NA
m[grep("industrielle alliance",m)] <- NA
m[grep("industri",m)] <- NA
m[grep("invesc",m)] <- NA
m[grep("investco",m)] <- NA
m[grep("investors",m)] <- NA
m[grep("ishares",m)] <- NA
m[grep("shares",m)] <- NA
m[grep("jov",m)] <- NA
m[grep("kenzie",m)] <- NA
m[grep("lysand",m)] <- NA
m[grep("mack",m)] <- NA
m[grep("manu",m)] <- NA
m[grep("matrix",m)] <- NA
m[grep("mawer",m)] <- NA
m[grep("merit",m)] <- NA
m[grep("middlefield",m)] <- NA
m[grep("natix",m)] <- NA
m[grep("national",m)] <- NA
m[grep("nbc",m)] <- NA
m[grep("^nei",m)] <- NA
m[grep("nex",m)] <- NA
m[grep("northwest",m)] <- NA
m[grep("norre",m)] <- NA
m[grep("o'leary",m,fixed=TRUE)] <- NA
m[grep("pimc",m)] <- NA
m[grep("^picton",m)] <- NA
m[grep("phillips",m,fixed=TRUE)] <- NA
m[grep("ph&n",m,fixed=TRUE)] <- NA
m[grep("ph & n",m,fixed=TRUE)] <- NA
m[grep("phn",m)] <- NA
m[grep("primerica",m)] <- NA
m[grep("quadrus",m)] <- NA
m[grep("queensbur",m)] <- NA
m[grep("^roi",m)] <- NA
m[grep("rbc",m)] <- NA
m[grep("reni",m)] <- NA
m[grep("renn",m)] <- NA
m[grep("russ",m)] <- NA
m[grep("royal",m)] <- NA
m[grep("scotia",m)] <- NA
m[grep("^sei",m)] <- NA
m[grep("sance",m)] <- NA
m[grep("sentry",m)] <- NA
m[grep("standar",m)] <- NA
m[grep("stone",m)] <- NA
m[grep("sprott",m)] <- NA
m[grep("sun",m)] <- NA
m[grep("ssq",m)] <- NA
m[grep("^td",m)] <- NA
m[grep("t.d.",m,fixed=TRUE)] <- NA
m[grep("td$",m)] <- NA
m[grep("temple",m)] <- NA
m[grep("tempel",m)] <- NA
m[grep("templ",m)] <- NA
m[grep("transamerica",m)] <- NA
m[grep("trima",m)] <- NA
m[grep("vanguard",m)] <- NA
m[grep("value",m)] <- NA
m[grep("vpi",m)] <- NA
m[grep("rena",m)] <- NA

# AGF Investments
# Invesco Trimark
# BMOMutual Funds
# Bridgehouse
# CI Investments
# First Asset[ETF]
# 
# Desjardins Financial
# Dynamic Funds
# NEI (Northwest - Ethical)
# Fidelity Investments
# Franklin Templeton Investments
# Horizons ETFs[ETF]
# Sun Life Global Investments
# IA Clarington
# iShares[ETF]
# Mackenzie Financial
# Manulife Investments
# National Bank 
# Phillips Hager & North
# RBC Mutual Funds
# Renaissance (CIBC)
# Scotia Mutual Funds
# Sentry Investments
# TD Mutual Funds
# PIMCO
# BMO ETFs [ETF]
# Sprott Asset Management
# Mawer
# Russell Investments
# EdgePoint
# 
# Vanguard ETFs [ETF]
# Canoe Financial
# RBC ETFs [ETF]
# PowerShares [ETF]
# Natixis Global Asset Management
# First Trust ETFs [ETF]
# Purpose Investments (ETFs) [ETF]


m[grep("blackrock",m)] <- NA
m[grep("world financial",m)] <- NA
m[grep("c. i.",m,fixed=TRUE)] <- NA
m[grep("hesperian",m)] <- NA
m[grep("edward jones",m)] <- NA
m[grep("ashton",m)] <- NA
m[grep("connor",m)] <- NA
m[grep("^canada",m)] <- NA
m[grep("london life",m)] <- NA
m[grep("dundee",m)] <- NA
m[grep("morning",m)] <- NA
m[grep("atb",m)] <- NA
m[grep("compass",m)] <- NA
m[grep("pfsl",m)] <- NA
m[grep("macq",m)] <- NA
m[grep("fieli",m)] <- NA
m[grep("^wis",m)] <- NA
m[grep("freedom 55",m)] <- NA
m[grep("gwl",m)] <- NA
no_na <- as.data.frame(na.omit(m))
no_na %>% group_by(`na.omit(m)`) %>% count() %>% arrange(-n) %>% View()
#m <- unique(m)
#write.csv(x = m,file = "names.txt",row.names = FALSE)