MonkmanMH

---
title: "geom_col vs geom_bar"
author: "Martin Monkman"
date: "2020/04/19"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

MonkmanMH

---
title: "Transform Data"
subtitle: "hands-on examples, with answers"
output: html_notebook
---

<!-- This file by Charlotte Wickham (with some modifications by Martin Monkman) is licensed under a Creative Commons Attribution 4.0 International License, adapted from the orignal work at https://github.com/rstudio/master-the-tidyverse by RStudio and https://github.com/cwickham/data-science-in-tidyverse-solutions. -->

```{r setup}
library(tidyverse)

MonkmanMH

### ---
#
# from @expersso

set.seed(894)  # number of regular season NHL goals Wayne Gretzky scored 
 
x <- replicate(10000, sum(sample(0:1, 20, TRUE, c(0.945, 0.055))))

table(ifelse(x == 0, "Team A win", ifelse(x == 1, "Draw", "Team B win"))) / 100

MonkmanMH

#
# for details see
# http://bayesball.blogspot.ca/2013/06/annotating-select-points-on-x-y-plot.html
#
# load the ggplot2 and grid packages
library(ggplot2)
library(grid)
# read data (note csv files are renamed)
tbl1 = read.csv("FanGraphs_Leaderboard_h.csv")
tbl2 = read.csv("FanGraphs_Leaderboard_d.csv")

MonkmanMH

## make it reproducible

set.seed(8675309)


## two normally distributed variables

X1 <- rnorm(100, mean = 0, sd = 1) 
X2 <- rnorm(100, mean = 0, sd = 1) 

MonkmanMH

# quick example of mutate (in the dplyr R package) to create a dummy variable

# packages (from the tidyverse)
library(tibble)
library(dplyr)

# a little tibble with an ID number and a gender variable (5 Female, 3 Male, 2 Not Stated)
mydata <- tibble(id = 1:10, gender = c("F", "F", "F", "F", "F",
                                       "M", "M", "M", 
                                       "NS", "NS"))

MonkmanMH

library(tidyverse)

datatab <- as.tibble(c(1:10))

# modulo division
datatab$value %% 2

# since we have alternating even and odd value in "value" variable
datatab %>%
  mutate(valueplus = ifelse((value %% 2) == 0, "even", "odd"))

MonkmanMH

# Problem: 
# - row 2 of data file has non-data title that repeats every two columns
# - column 1 / row 1 header label is fine
# - the header in every even-numbered column applies to the next odd-humbered column (eg 2 applies to 3, 4 to 5, etc)
# - the header in those odd-numbered columns (3, 5, 7, etc) is read initially as an NA
# Solution
# - read column names only
# - hard code even and odd suffix
# - copy header value in those even columns to odd columns

MonkmanMH

# load the package and data set "Teams"
install.packages("Lahman")
library("Lahman")
data(Teams)
#
#
# CREATE LEAGUE SUMMARY TABLES
# ============================
#
# select a sub-set of teams from 1901 [the establishment of the American League] forward to 2012

MonkmanMH

#
library(Lahman)
data(Master)
#
# `debut` variable; create new version `debutDate`
Master$debutDate <- (as.Date(Master$debut, "%m/%d/%Y"))
Master$debutDate[is.na(Master$debutDate)] <- 
  as.Date(Master$debut[is.na(Master$debutDate)])
#
# `finalGame` variable; create new version `finalGameDate`