MonkmanMH

# ######################
#
# Blog with output and discussion:
# "Fair weather fans? (An R scatter plot matrix)" 2013-07-18
# http://bayesball.blogspot.ca/2013/07/fair-weather-fans-r-scatter-plot-matrix.html
#
# data: pulled from www.harbourcats.com
# saved on Google Drive:
# https://docs.google.com/spreadsheet/ccc?key=0Art4wpcrwqkBdHZvTUFzOUo5U3BzMHFveXdYOTdTWUE&usp=sharing
# File / Download as > Comma Separated Values (CSV)

MonkmanMH

num,date,day,day2,day.night,vs,attend,cloud,sun,temp.c,temp.f,wind,note
1,6/5/2013,Wed,1,1,Kelowna,3026,mainly sunny,4,21,70,,Opening Night
2,6/6/2013,Thu,1,1,Kelowna,1082,mainly sunny,4,18,64,,
3,6/7/2013,Fri,3,1,Kelowna,1542,mainly sunny,4,19,66,windy,
4,6/11/2013,Tue,1,1,Medford,1014,mostly cloudy,2,17,63,,
5,6/12/2013,Wed,1,1,Medford,1003,mostly cloudy,2,16,60,,
6,6/13/2013,Thu,1,1,Medford,1015,partly cloudy,3,19,66,,
7,6/21/2013,Fri,3,1,Bend,1248,sunny,5,18,64,,
8,6/22/2013,Sat,3,1,Bend,1640,sunny,5,21,70,,
9,6/23/2013,Sun,2,0,Bend,1246,cloudy,1,18,64,,

MonkmanMH

Using Google Maps API and R

[source: http://www.r-bloggers.com/using-google-maps-api-and-r/] [address modifications added by MonkmanMH]

This script uses RCurl and RJSONIO to download data from Google's API to get the latitude, longitude, location type, and formatted address

library(RCurl)

MonkmanMH

# PRINT THE INTEGERS 1 THROUGH 10
#
# VERSION 1 -- using while()
# make the initial assignment of variable count_1 to 0 (not necessary)
count_1 <- 0
# the while loop - conditional statement in the first parenthesis, 
# then the repeated steps within the {}
while (count_1 < 10) 
{  count_1 <- count_1 + 1
   print(count_1)

MonkmanMH

# BINOMIAL CONFIDENCE INTERVAL CALCULATOR
#
# the binomial distribuion approximates the Normal distribution
# http://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval
#
# read the data file
bin_data <- read.csv("bin_data.csv")
#
#
# the binomial confidence calculator function

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`

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

# 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

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

# 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"))