Assigment
Rafael Miranda
9 de enero de 2016
I. Loading and preprocessing the data
rm(list=ls())
activity_raw<-read.csv(choose.files(), stringsAsFactors = FALSE)
# Transform the data
activity_raw$date <- as.POSIXct(activity_raw$date, format="%Y-%m-%d")
# Compute the weekdays from the date attribute
activity_raw <- data.frame(date=activity_raw$date,
weekday=tolower(weekdays(activity_raw$date)),
steps=activity_raw$steps,
interval=activity_raw$interval)
# Compute the day type (weekend or weekday)
activity_raw <- cbind(activity_raw,
daytype=ifelse(activity_raw$weekday == "saturday" |
activity_raw$weekday == "sunday", "weekend",
"weekday"))
# Create the final data.frame
activity <- data.frame(date=activity_raw$date,
weekday=activity_raw$weekday,
daytype=activity_raw$daytype,
interval=activity_raw$interval,
steps=activity_raw$steps)
head (activity)## date weekday daytype interval steps
## 1 2012-10-01 lunes weekday 0 NA
## 2 2012-10-01 lunes weekday 5 NA
## 3 2012-10-01 lunes weekday 10 NA
## 4 2012-10-01 lunes weekday 15 NA
## 5 2012-10-01 lunes weekday 20 NA
## 6 2012-10-01 lunes weekday 25 NA- What is the mean total number of steps taken per day?
# Compute the total number of steps each day (NA values removed)
sum_data <- aggregate(activity$steps, by=list(activity$date), FUN=sum, na.rm=TRUE)
# Rename the attributes
names(sum_data) <- c("date", "total")
head(sum_data)## date total
## 1 2012-10-01 0
## 2 2012-10-02 126
## 3 2012-10-03 11352
## 4 2012-10-04 12116
## 5 2012-10-05 13294
## 6 2012-10-06 15420# Compute the histogram of the total number of steps each day
hist(sum_data$total,
breaks=seq(from=0, to=25000, by=2500),
col="blue",
xlab="Total number of steps",
ylim=c(0, 20),
main="Histogram of the total number of steps taken each day\n(NA removed)")
mean(sum_data$total)## [1] 9354.23median(sum_data$total)## [1] 10395- What is the average daily activity pattern?
# Clear the workspace
rm(sum_data)
# Compute the means of steps accross all days for each interval
mean_data <- aggregate(activity$steps,
by=list(activity$interval),
FUN=mean,
na.rm=TRUE)
mean_data## Group.1 x
## 1 0 1.7169811
## 2 5 0.3396226
## 3 10 0.1320755
## 4 15 0.1509434
## 5 20 0.0754717
## 6 25 2.0943396
## 7 30 0.5283019
## 8 35 0.8679245
## 9 40 0.0000000
## 10 45 1.4716981
## 11 50 0.3018868
## 12 55 0.1320755
## 13 100 0.3207547
## 14 105 0.6792453
## 15 110 0.1509434
## 16 115 0.3396226
## 17 120 0.0000000
## 18 125 1.1132075
## 19 130 1.8301887
## 20 135 0.1698113
## 21 140 0.1698113
## 22 145 0.3773585
## 23 150 0.2641509
## 24 155 0.0000000
## 25 200 0.0000000
## 26 205 0.0000000
## 27 210 1.1320755
## 28 215 0.0000000
## 29 220 0.0000000
## 30 225 0.1320755
## 31 230 0.0000000
## 32 235 0.2264151
## 33 240 0.0000000
## 34 245 0.0000000
## 35 250 1.5471698
## 36 255 0.9433962
## 37 300 0.0000000
## 38 305 0.0000000
## 39 310 0.0000000
## 40 315 0.0000000
## 41 320 0.2075472
## 42 325 0.6226415
## 43 330 1.6226415
## 44 335 0.5849057
## 45 340 0.4905660
## 46 345 0.0754717
## 47 350 0.0000000
## 48 355 0.0000000
## 49 400 1.1886792
## 50 405 0.9433962
## 51 410 2.5660377
## 52 415 0.0000000
## 53 420 0.3396226
## 54 425 0.3584906
## 55 430 4.1132075
## 56 435 0.6603774
## 57 440 3.4905660
## 58 445 0.8301887
## 59 450 3.1132075
## 60 455 1.1132075
## 61 500 0.0000000
## 62 505 1.5660377
## 63 510 3.0000000
## 64 515 2.2452830
## 65 520 3.3207547
## 66 525 2.9622642
## 67 530 2.0943396
## 68 535 6.0566038
## 69 540 16.0188679
## 70 545 18.3396226
## 71 550 39.4528302
## 72 555 44.4905660
## 73 600 31.4905660
## 74 605 49.2641509
## 75 610 53.7735849
## 76 615 63.4528302
## 77 620 49.9622642
## 78 625 47.0754717
## 79 630 52.1509434
## 80 635 39.3396226
## 81 640 44.0188679
## 82 645 44.1698113
## 83 650 37.3584906
## 84 655 49.0377358
## 85 700 43.8113208
## 86 705 44.3773585
## 87 710 50.5094340
## 88 715 54.5094340
## 89 720 49.9245283
## 90 725 50.9811321
## 91 730 55.6792453
## 92 735 44.3207547
## 93 740 52.2641509
## 94 745 69.5471698
## 95 750 57.8490566
## 96 755 56.1509434
## 97 800 73.3773585
## 98 805 68.2075472
## 99 810 129.4339623
## 100 815 157.5283019
## 101 820 171.1509434
## 102 825 155.3962264
## 103 830 177.3018868
## 104 835 206.1698113
## 105 840 195.9245283
## 106 845 179.5660377
## 107 850 183.3962264
## 108 855 167.0188679
## 109 900 143.4528302
## 110 905 124.0377358
## 111 910 109.1132075
## 112 915 108.1132075
## 113 920 103.7169811
## 114 925 95.9622642
## 115 930 66.2075472
## 116 935 45.2264151
## 117 940 24.7924528
## 118 945 38.7547170
## 119 950 34.9811321
## 120 955 21.0566038
## 121 1000 40.5660377
## 122 1005 26.9811321
## 123 1010 42.4150943
## 124 1015 52.6603774
## 125 1020 38.9245283
## 126 1025 50.7924528
## 127 1030 44.2830189
## 128 1035 37.4150943
## 129 1040 34.6981132
## 130 1045 28.3396226
## 131 1050 25.0943396
## 132 1055 31.9433962
## 133 1100 31.3584906
## 134 1105 29.6792453
## 135 1110 21.3207547
## 136 1115 25.5471698
## 137 1120 28.3773585
## 138 1125 26.4716981
## 139 1130 33.4339623
## 140 1135 49.9811321
## 141 1140 42.0377358
## 142 1145 44.6037736
## 143 1150 46.0377358
## 144 1155 59.1886792
## 145 1200 63.8679245
## 146 1205 87.6981132
## 147 1210 94.8490566
## 148 1215 92.7735849
## 149 1220 63.3962264
## 150 1225 50.1698113
## 151 1230 54.4716981
## 152 1235 32.4150943
## 153 1240 26.5283019
## 154 1245 37.7358491
## 155 1250 45.0566038
## 156 1255 67.2830189
## 157 1300 42.3396226
## 158 1305 39.8867925
## 159 1310 43.2641509
## 160 1315 40.9811321
## 161 1320 46.2452830
## 162 1325 56.4339623
## 163 1330 42.7547170
## 164 1335 25.1320755
## 165 1340 39.9622642
## 166 1345 53.5471698
## 167 1350 47.3207547
## 168 1355 60.8113208
## 169 1400 55.7547170
## 170 1405 51.9622642
## 171 1410 43.5849057
## 172 1415 48.6981132
## 173 1420 35.4716981
## 174 1425 37.5471698
## 175 1430 41.8490566
## 176 1435 27.5094340
## 177 1440 17.1132075
## 178 1445 26.0754717
## 179 1450 43.6226415
## 180 1455 43.7735849
## 181 1500 30.0188679
## 182 1505 36.0754717
## 183 1510 35.4905660
## 184 1515 38.8490566
## 185 1520 45.9622642
## 186 1525 47.7547170
## 187 1530 48.1320755
## 188 1535 65.3207547
## 189 1540 82.9056604
## 190 1545 98.6603774
## 191 1550 102.1132075
## 192 1555 83.9622642
## 193 1600 62.1320755
## 194 1605 64.1320755
## 195 1610 74.5471698
## 196 1615 63.1698113
## 197 1620 56.9056604
## 198 1625 59.7735849
## 199 1630 43.8679245
## 200 1635 38.5660377
## 201 1640 44.6603774
## 202 1645 45.4528302
## 203 1650 46.2075472
## 204 1655 43.6792453
## 205 1700 46.6226415
## 206 1705 56.3018868
## 207 1710 50.7169811
## 208 1715 61.2264151
## 209 1720 72.7169811
## 210 1725 78.9433962
## 211 1730 68.9433962
## 212 1735 59.6603774
## 213 1740 75.0943396
## 214 1745 56.5094340
## 215 1750 34.7735849
## 216 1755 37.4528302
## 217 1800 40.6792453
## 218 1805 58.0188679
## 219 1810 74.6981132
## 220 1815 85.3207547
## 221 1820 59.2641509
## 222 1825 67.7735849
## 223 1830 77.6981132
## 224 1835 74.2452830
## 225 1840 85.3396226
## 226 1845 99.4528302
## 227 1850 86.5849057
## 228 1855 85.6037736
## 229 1900 84.8679245
## 230 1905 77.8301887
## 231 1910 58.0377358
## 232 1915 53.3584906
## 233 1920 36.3207547
## 234 1925 20.7169811
## 235 1930 27.3962264
## 236 1935 40.0188679
## 237 1940 30.2075472
## 238 1945 25.5471698
## 239 1950 45.6603774
## 240 1955 33.5283019
## 241 2000 19.6226415
## 242 2005 19.0188679
## 243 2010 19.3396226
## 244 2015 33.3396226
## 245 2020 26.8113208
## 246 2025 21.1698113
## 247 2030 27.3018868
## 248 2035 21.3396226
## 249 2040 19.5471698
## 250 2045 21.3207547
## 251 2050 32.3018868
## 252 2055 20.1509434
## 253 2100 15.9433962
## 254 2105 17.2264151
## 255 2110 23.4528302
## 256 2115 19.2452830
## 257 2120 12.4528302
## 258 2125 8.0188679
## 259 2130 14.6603774
## 260 2135 16.3018868
## 261 2140 8.6792453
## 262 2145 7.7924528
## 263 2150 8.1320755
## 264 2155 2.6226415
## 265 2200 1.4528302
## 266 2205 3.6792453
## 267 2210 4.8113208
## 268 2215 8.5094340
## 269 2220 7.0754717
## 270 2225 8.6981132
## 271 2230 9.7547170
## 272 2235 2.2075472
## 273 2240 0.3207547
## 274 2245 0.1132075
## 275 2250 1.6037736
## 276 2255 4.6037736
## 277 2300 3.3018868
## 278 2305 2.8490566
## 279 2310 0.0000000
## 280 2315 0.8301887
## 281 2320 0.9622642
## 282 2325 1.5849057
## 283 2330 2.6037736
## 284 2335 4.6981132
## 285 2340 3.3018868
## 286 2345 0.6415094
## 287 2350 0.2264151
## 288 2355 1.0754717# Rename the attributes
names(mean_data) <- c("interval", "mean")
head(mean_data)## interval mean
## 1 0 1.7169811
## 2 5 0.3396226
## 3 10 0.1320755
## 4 15 0.1509434
## 5 20 0.0754717
## 6 25 2.0943396#Compute time series graph
plot(mean_data$interval,
mean_data$mean,
type="l",
col="blue",
lwd=2,
xlab="Interval [minutes]",
ylab="Average number of steps",
main="Time-series of the average number of steps per intervals\n(NA removed)")
# We find the position of the maximum mean
max_pos <- which(mean_data$mean == max(mean_data$mean))
max_pos## [1] 104# We lookup the value of interval at this position
max_interval <- mean_data[max_pos, 1]
max_interval## [1] 835# Clear the workspace
rm(max_pos, mean_data)Inputing the missing values
# Clear the workspace
rm(max_interval)
# We use the trick that a TRUE boolean value is equivalent to 1 and a FALSE to 0.
NA_count <- sum(is.na(activity$steps))
# Clear the workspace
rm(NA_count)
# Find the NA positions
na_pos <- which(is.na(activity$steps))
# Create a vector of means
mean_vec <- rep(mean(activity$steps, na.rm=TRUE), times=length(na_pos))
# Replace the NAs by the means
activity[na_pos, "steps"] <- mean_vec
# Clear the workspace
rm(mean_vec, na_pos)
head(activity)## date weekday daytype interval steps
## 1 2012-10-01 lunes weekday 0 37.3826
## 2 2012-10-01 lunes weekday 5 37.3826
## 3 2012-10-01 lunes weekday 10 37.3826
## 4 2012-10-01 lunes weekday 15 37.3826
## 5 2012-10-01 lunes weekday 20 37.3826
## 6 2012-10-01 lunes weekday 25 37.3826# Compute the total number of steps each day (NA values removed)
sum_data <- aggregate(activity$steps, by=list(activity$date), FUN=sum)
# Rename the attributes
names(sum_data) <- c("date", "total")
# Compute the histogram of the total number of steps each day
hist(sum_data$total,
breaks=seq(from=0, to=25000, by=2500),
col="blue",
xlab="Total number of steps",
ylim=c(0, 30),
main="Histogram of the total number of steps taken each day\n(NA replaced by mean value)")
mean(sum_data$total)## [1] 10766.19median(sum_data$total)## [1] 10766.19Are there differences in activity patterns between weekdays and weekends?
# The new factor variable "daytype" was already in the activity data frame
head(activity)## date weekday daytype interval steps
## 1 2012-10-01 lunes weekday 0 37.3826
## 2 2012-10-01 lunes weekday 5 37.3826
## 3 2012-10-01 lunes weekday 10 37.3826
## 4 2012-10-01 lunes weekday 15 37.3826
## 5 2012-10-01 lunes weekday 20 37.3826
## 6 2012-10-01 lunes weekday 25 37.3826# Load the lattice graphical library
require(lattice)## Loading required package: lattice# Compute the average number of steps taken, averaged across all daytype variable
mean_data <- aggregate(activity$steps,
by=list(activity$daytype,
activity$weekday, activity$interval), mean)
# Rename the attributes
names(mean_data) <- c("daytype", "weekday", "interval", "mean")
head(mean_data)## daytype weekday interval mean
## 1 weekday domingo 0 4.672825
## 2 weekday jueves 0 9.375844
## 3 weekday lunes 0 9.418355
## 4 weekday martes 0 0.000000
## 5 weekday miércoles 0 7.931400
## 6 weekday sábado 0 4.672825### The time series plot take the following form:
# Compute the time serie plot
xyplot(mean ~ interval | daytype, mean_data,
type="l",
lwd=1,
xlab="Interval",
ylab="Number of steps",
layout=c(1,2))