setwd("D:/R/Udacity/EDA_Course_Materials/lesson3")
library(rmarkdown)
library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionInvestigation of my friends’ distribution birth months and days
My aim in this project is to answer the folowing questions:
Which month contains the most number of birthdays?
How many birthdays are in each month?
Which day of the year has the most number of birthdays?
Do I have at least 365 friends that have birthdays on everyday of the year?
csvdata <- read.csv('FBbd.csv')
#convert vector into necessary time format
bdates <- strptime(csvdata$Start, "%d/%m/%Y %H:%M")
names(unclass(bdates))## [1] "sec" "min" "hour" "mday" "mon" "year" "wday"
## [8] "yday" "isdst" "zone" "gmtoff"#extract days and months
days <- bdates$mday
mon <- as.numeric(bdates$mon) + 1
yday <- as.numeric(bdates$yday) + 1
#creat dataframes
df <- data.frame(days, mon, yday, count = 1)Which month contains the most number of birthdays?
Histogram shows that mostly my friends have birthdays in the range from March to July and most of them were born in March.
qplot(df$mon, binwidth = 1,
main = 'Birthdays per month',
xlab = 'Months',
ylab = 'Number of birthdays in month',
color = I('black'), fill = I('#A41470')) +
scale_x_continuous(breaks = seq(1,12,1), lim = c(1,13)) +
scale_y_continuous(breaks = seq(0,30,2), lim = c(0,30))
ggsave('BD_num.png')## Saving 7 x 5 in imageHow many birthdays are in each month?
by_mon<-group_by(df, mon)
summarise(by_mon, sum(count))## Source: local data frame [12 x 2]
##
## mon sum(count)
## 1 1 20
## 2 2 15
## 3 3 29
## 4 4 25
## 5 5 27
## 6 6 26
## 7 7 25
## 8 8 20
## 9 9 14
## 10 10 14
## 11 11 21
## 12 12 16Which day of the year has the most number of birthdays?
Among my friends the most number of birthdays is on 1 of May.
# convert day of year into "day-month format
by_yday<-group_by(df, yday)
df_yday<-summarise(by_yday, total = sum(count))
df_yday$yday <- format(strptime(df_yday$yday, format="%j"), format="%d-%m")
ordered <- df_yday[order(-df_yday$total),]Do I have at least 365 friends that have birthdays on everyday of the year?
I sorted days of birth of my friends. Final table shows that I have 252 observations so it already means that my friends’ birthdays are not every day of the year.
bd <- select(df, days, mon)
bd_ordered <- bd[order(as.numeric(bd$mon), as.numeric(bd$days)),]
row.names(bd_ordered) <- c(1:252)
bd_ordered## days mon
## 1 1 1
## 2 1 1
## 3 1 1
## 4 1 1
## 5 6 1
## 6 6 1
## 7 11 1
## 8 11 1
## 9 16 1
## 10 17 1
## 11 19 1
## 12 22 1
## 13 22 1
## 14 23 1
## 15 23 1
## 16 24 1
## 17 27 1
## 18 29 1
## 19 30 1
## 20 31 1
## 21 2 2
## 22 5 2
## 23 8 2
## 24 10 2
## 25 15 2
## 26 19 2
## 27 19 2
## 28 19 2
## 29 19 2
## 30 20 2
## 31 20 2
## 32 21 2
## 33 22 2
## 34 22 2
## 35 24 2
## 36 2 3
## 37 5 3
## 38 5 3
## 39 6 3
## 40 7 3
## 41 8 3
## 42 9 3
## 43 10 3
## 44 11 3
## 45 11 3
## 46 11 3
## 47 12 3
## 48 13 3
## 49 15 3
## 50 15 3
## 51 15 3
## 52 17 3
## 53 17 3
## 54 17 3
## 55 18 3
## 56 20 3
## 57 21 3
## 58 21 3
## 59 23 3
## 60 24 3
## 61 24 3
## 62 27 3
## 63 28 3
## 64 29 3
## 65 1 4
## 66 2 4
## 67 4 4
## 68 4 4
## 69 7 4
## 70 8 4
## 71 12 4
## 72 12 4
## 73 15 4
## 74 16 4
## 75 16 4
## 76 16 4
## 77 16 4
## 78 18 4
## 79 19 4
## 80 21 4
## 81 21 4
## 82 22 4
## 83 22 4
## 84 23 4
## 85 24 4
## 86 26 4
## 87 29 4
## 88 29 4
## 89 29 4
## 90 1 5
## 91 1 5
## 92 1 5
## 93 1 5
## 94 1 5
## 95 2 5
## 96 2 5
## 97 8 5
## 98 8 5
## 99 8 5
## 100 9 5
## 101 9 5
## 102 10 5
## 103 11 5
## 104 11 5
## 105 17 5
## 106 19 5
## 107 19 5
## 108 20 5
## 109 20 5
## 110 22 5
## 111 24 5
## 112 25 5
## 113 25 5
## 114 25 5
## 115 31 5
## 116 31 5
## 117 1 6
## 118 1 6
## 119 2 6
## 120 2 6
## 121 3 6
## 122 3 6
## 123 4 6
## 124 5 6
## 125 7 6
## 126 12 6
## 127 12 6
## 128 13 6
## 129 13 6
## 130 13 6
## 131 14 6
## 132 15 6
## 133 16 6
## 134 21 6
## 135 22 6
## 136 24 6
## 137 25 6
## 138 25 6
## 139 26 6
## 140 27 6
## 141 29 6
## 142 29 6
## 143 3 7
## 144 3 7
## 145 5 7
## 146 6 7
## 147 7 7
## 148 8 7
## 149 10 7
## 150 11 7
## 151 12 7
## 152 15 7
## 153 16 7
## 154 16 7
## 155 17 7
## 156 17 7
## 157 17 7
## 158 19 7
## 159 20 7
## 160 20 7
## 161 22 7
## 162 23 7
## 163 24 7
## 164 26 7
## 165 28 7
## 166 28 7
## 167 30 7
## 168 1 8
## 169 4 8
## 170 5 8
## 171 6 8
## 172 8 8
## 173 10 8
## 174 10 8
## 175 11 8
## 176 17 8
## 177 18 8
## 178 18 8
## 179 18 8
## 180 19 8
## 181 23 8
## 182 24 8
## 183 26 8
## 184 28 8
## 185 28 8
## 186 28 8
## 187 31 8
## 188 10 9
## 189 12 9
## 190 15 9
## 191 17 9
## 192 17 9
## 193 19 9
## 194 20 9
## 195 20 9
## 196 20 9
## 197 22 9
## 198 23 9
## 199 25 9
## 200 26 9
## 201 27 9
## 202 2 10
## 203 4 10
## 204 5 10
## 205 9 10
## 206 9 10
## 207 12 10
## 208 13 10
## 209 15 10
## 210 15 10
## 211 17 10
## 212 17 10
## 213 18 10
## 214 18 10
## 215 21 10
## 216 3 11
## 217 3 11
## 218 4 11
## 219 4 11
## 220 5 11
## 221 5 11
## 222 5 11
## 223 5 11
## 224 6 11
## 225 7 11
## 226 10 11
## 227 11 11
## 228 12 11
## 229 13 11
## 230 13 11
## 231 17 11
## 232 20 11
## 233 22 11
## 234 28 11
## 235 28 11
## 236 30 11
## 237 6 12
## 238 6 12
## 239 8 12
## 240 10 12
## 241 13 12
## 242 15 12
## 243 17 12
## 244 21 12
## 245 21 12
## 246 23 12
## 247 23 12
## 248 25 12
## 249 27 12
## 250 28 12
## 251 29 12
## 252 31 12qplot(data = by_yday, x = yday, binwidth = 1,
main = 'Birthdays during one year',
xlab = 'Days of year',
ylab = 'Number of birthday in that day',
fill = I('#A41470')) +
scale_x_continuous(breaks = seq(0,365,30), lim = c(1,366))