forked from rdpeng/RepData_PeerAssessment1
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.Rhistory
161 lines (161 loc) · 6.43 KB
/
.Rhistory
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
install.packages("KernSmooth")
library(KernSmooth)
org.R-project.R force.LANG en_US.UTF-8
org.R-project.R
setwd("~/Desktop/Coursera/Data Science Specialization/Reproducible Research/Assigment 1")
myData <- read.csv("activity.csv")
myData$date <- as.Date(maData$date)
myData$date <- as.Date(myData$date)
head(myDate)
head(myData)
str(myData)
StepsPerDay <- tapply(myData$steps, myData$date, sum, rm.na = T)
head(StepsPerDay)
head(mean(StepsPerDay))
?mean
StepsPerDay <- tapply(myData$steps, myData$date, sum, na.rm = T)
head(StepsPerDay)
head(myData)
StepsPerDay <- tapply(myData$steps, myData$date, sum)
mean(StepsPerDay, na.rm = T)
median(StepsPerDay, na.rm = T)
myData <- read.csv("activity.csv")
StepsPerDay <- tapply(myData$steps, myData$date, sum)
median(StepsPerDay, na.rm = T)
mean(StepsPerDay, na.rm = T)
str(myData)
?read.csv
myData <- read.csv("activity.csv", colClasses = c("int", "Date", "Factor"))
myData <- read.csv("activity.csv", colClasses = c("integer", "Date", "Factor"))
myData <- read.csv("activity.csv", colClasses = c("integer", "Date", "factor"))
str(myData)
head(myData)
StepsPerDay <- tapply(myData$steps, myData$date, sum)
hist(StepsPerDay)
meanSteps
meanSteps <- mean(StepsPerDay, na.rm = T)
meanSteps
roud(meanSteps, 2)
round(meanSteps, 2)
meanSteps
plot(myData$interval, tapply(myData$steps, myData$interval,mean))
levels(myData$interval)
plot(levels(myData$interval), tapply(myData$steps, myData$interval,mean))
tapply(myData$steps, myData$interval,mean)
tapply(myData$steps, myData$interval,mean, na.rm = T)
tapply(myData$steps, myData$interval,mean(na.rm = T))
meanStepsbyIterval <- tapply(myData$steps, myData$interval, mean, na.rm = T)
str(meanStepsbyIterval)
plot(levels(myData$steps), meanStepsbyIterval)
str(levels(myData$steps))
plot(levels(myData$interval), meanStepsbyIterval)
plot(levels(myData$interval), meanStepsbyIterval, type = "l")
?subset
subset(myData, na.rm = T)
with(myData[complete.cases(myData)], plot(interval, tapply(steps, interval, mean)))
myData[complete.cases(myData),]
head(myData[complete.cases(myData),])
with(myData[complete.cases(myData),], plot(interval, tapply(steps, interval, mean)))
with(myData[complete.cases(myData),], plot(levels(interval), tapply(steps, interval, mean)))
with(myData[complete.cases(myData),], plot(levels(interval), tapply(steps, interval, mean), type = "l"))
str(meanStepsbyIterval)
meanStepsbyIterval <- aggregate(x=list(meanSteps=myData$steps), by=list(interval=myData$interval),FUN=mean, na.rm=TRUE)
head(meanStepsbyIterval)
meanStepsbyIterval <- tapply(myData$steps, myData$interval, mean, na.rm = T)
meanStepsbyIterval <- aggregate(meanSteps=myData$steps, interval=myData$interval,FUN=mean, na.rm=TRUE)
meanStepsbyIterval <- aggregate(x=meanSteps=myData$steps, by=interval=myData$interval,FUN=mean, na.rm=TRUE)
meanStepsbyIterval <- aggregate(x=myData$steps, by=myData$interval,FUN=mean, na.rm=TRUE)
meanStepsbyIterval <- aggregate(x=myData$steps, by=list(myData$interval),FUN=mean, na.rm=TRUE)
head(meanStepsbyIterval)
meanStepsbyIterval <- aggregate(x=list(meanSteps=myData$steps), by=list(interval=myData$interval),FUN=mean, na.rm=TRUE)
str(meanStepsbyIterval)
plot(meanStepsbyIterval$interval, meanStepsbyIterval$meanSteps)
plot(meanStepsbyIterval$interval, meanStepsbyIterval$meanSteps, type="l")
plot(meanStepsbyIterval$interval, meanStepsbyIterval$meanSteps, type="l")
ggplot(meanStepsbyIterval, aes(x=interval, y=meanSteps)) +
geom_line() +
xlab("5-minute interval") +
ylab("average number of steps taken")
library(ggplot2)
ggplot(meanStepsbyIterval, aes(x=interval, y=meanSteps)) +
geom_line() +
xlab("5-minute interval") +
ylab("average number of steps taken")
ggplot(meanStepsbyIterval, interval, meanSteps) +
geom_line() +
xlab("5-minute interval") +
ylab("average number of steps taken")
?ggplot
ggplot(data=meanStepsbyIterval, aes(x=interval, y=meanSteps)) +
geom_line() +
xlab("5-minute interval") +
ylab("average number of steps taken")
plot(meanStepsbyIterval$interval, meanStepsbyIterval$meanSteps, type="l")
order(meanStepsbyIterval)
head(meanStepsbyIterval)
str(meanStepsbyIterval)
str(meanStepsbyIterval
meanStepsbyIterval
myData <- read.csv("activity.csv", colClasses = c("integer", "Date", "integer"))
meanStepsbyIterval <- aggregate(x=list(meanSteps=myData$steps), by=list(interval=myData$interval),FUN=mean, na.rm=TRUE)
ggplot(data=meanStepsbyIterval, aes(x=interval, y=meanSteps)) +
geom_line() +
xlab("5-minute interval") +
ylab("average number of steps taken")
plot(meanStepsbyIterval$interval, meanStepsbyIterval$meanSteps, type="l")
meanStepsbyIterval <- aggregate(x=list(steps=myData$steps), by=list(interval=myData$interval),FUN=mean, na.rm=TRUE)
maxStepsInterval <- meanStepsbyIterval$interval[meanStepsbyIterval$steps = max(meanStepsbyIterval$steps)]
maxStepsInterval <- meanStepsbyIterval$interval[meanStepsbyIterval$steps == max(meanStepsbyIterval$steps)]
maxStepsInterval
sum(complete.cases(myData))
sum(!complete.cases(myData))
length(myData)
length(myData$steps)
sum(is.na(myData$steps)
sum(is.na(myData$steps))
head(meanStepsbyIterval)
?impute
fillNAs <- function(interval, steps){
newValue <- NA
if (is.na(steps))
newValue <- as.integer(meanStepsbyIterval$steps[meanStepsbyIterval$interval == interval])
else
newValue <- steps
return(newValue)
}
myNewData <- myData
myNewData$steps <- mapply(FUN=fillNAs, myNewData$interval, myNewData$steps)
head(myNewData)
?qplot
head(weekdays(myData$date))
?weekdays
head(weekdays(myData$date, abbreviate = T))
head(weekdays(myData$date, abbreviate = F))
head(days(myData$date))
head(day(myData$date))
weekdays("Monday")
library("lubridate")
day(myData)
weekday <- function(day){
if (day == "Saturday" | day == "Sunday")
return("weekend")
else
return("weekday")
}
myNewData$day <- sapply(weekdays(myNewData$date), FUN=weekday)
head(myNewData)
str(myNewData)
myNewData$day <- factor(sapply(weekdays(myNewData$date), FUN=weekday))
str(myNewData)
newMeanStepsbyIterval <- aggregate(x=list(steps=myNewData$steps, day = myNewData$day), by=list(interval=myNewData$interval),FUN=mean, na.rm=TRUE)
newMeanStepsbyIterval <- aggregate(x=list(steps=myNewData$steps, day = myNewData$day), by=list(interval=myNewData$interval),FUN=mean)
warnings()
head(newMeanStepsbyInterval)
head(newMeanStepsbyIterval)
?aggregate
newMeanStepsbyInterval <- aggregate(x=list(steps=myNewData$steps), by=list(interval=myNewData$interval, day = myNewData$day),FUN=mean)
head(newMeanStepsbyIterval)
head(newMeanStepsbyInterval)
?ggplot
setwd("~/Desktop/Coursera/Data Science Specialization/Reproducible Research/Assigment1")
?hist