-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrun_analysis.R
268 lines (222 loc) · 9.13 KB
/
run_analysis.R
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
## run_analysis.R
##
## getting and cleaning data course project
## david saint ruby
## September 2014
##
##
## note - this script should be run from a directory which contains the
## UCR HAR Dataset folder and related subfolders
##
##
## date changes
## ----------- ---------------------
## 09202014 initial
##
##
## plyr library
library(plyr)
## advise our working directory
print(paste("Working directory: ",getwd()))
## read in our X_train and X_test data sets
## X_train
if (!file.exists(".\\UCI HAR Dataset\\train\\X_train.txt")) stop("File does not exist - X_train.txt")
X_train <- read.table(".\\UCI HAR Dataset\\train\\X_train.txt", sep = "" , header = F)
## X_test
if (!file.exists(".\\UCI HAR Dataset\\test\\X_test.txt")) stop("File does not exist - X_test.txt")
X_test <- read.table(".\\UCI HAR Dataset\\test\\X_test.txt", sep = "" , header = F)
## pull in our subject files - align on position
## subject_train
if (!file.exists(".\\UCI HAR Dataset\\train\\subject_train.txt")) stop("File does not exist - subject_train.txt")
subject_train <- read.table(".\\UCI HAR Dataset\\train\\subject_train.txt", sep = "" , header = F)
## subject_test
if (!file.exists(".\\UCI HAR Dataset\\test\\subject_test.txt")) stop("File does not exist - subject_test.txt")
subject_test <- read.table(".\\UCI HAR Dataset\\test\\subject_test.txt", sep = "" , header = F)
## load up the y files
## y_train
if (!file.exists(".\\UCI HAR Dataset\\train\\y_train.txt")) stop("File does not exist - y_train.txt")
y_train <- read.table(".\\UCI HAR Dataset\\train\\y_train.txt", sep = "" , header = F)
## y_test
if (!file.exists(".\\UCI HAR Dataset\\test\\y_test.txt")) stop("File does not exist - y_test.txt")
y_test <- read.table(".\\UCI HAR Dataset\\test\\y_test.txt", sep = "" , header = F)
## pull in a couple more utility files for later
## features.txt
if (!file.exists(".\\UCI HAR Dataset\\features.txt")) stop("File does not exist - features.txt")
features <- read.table(".\\UCI HAR Dataset\\features.txt", sep = "" , header = F)
## activity_labels.txt
if (!file.exists(".\\UCI HAR Dataset\\activity_labels.txt")) stop("File does not exist - activity_labels.txt")
activity_labels <- read.table(".\\UCI HAR Dataset\\activity_labels.txt", sep = "" , header = F)
## rename our columns for subject
names(subject_train)[1] <- "subject"
names(subject_test)[1] <- "subject"
## rename our X sets to feature names
names(X_train) <- features[,2]
names(X_test) <- features[,2]
## rename our columns for activity
names(y_train)[1] <- "activity"
names(y_test)[1] <- "activity"
## rename our columns for activity labels
names(activity_labels)[1] <- "activity"
names(activity_labels)[2] <- "activity_label"
## bind our columns to the left side for test and train
train <- cbind(subject_train, y_train, X_train)
test <- cbind(subject_test, y_test, X_test)
## join up all into one
trainandtest <- rbind(train, test)
## only use the columns we want
trainandtest <- trainandtest[,grep("subject|activity|std\\(\\)|mean\\(\\)", colnames(trainandtest))]
## merge up with activity labels
trainandtestlabeled <- merge(trainandtest,activity_labels,by="activity")
## reorder the set to bring the activity label near the front
trainandtestlabeled <- trainandtestlabeled[c(
"subject",
"activity",
"activity_label",
"tBodyAcc-mean()-X",
"tBodyAcc-mean()-Y",
"tBodyAcc-mean()-Z",
"tBodyAcc-std()-X",
"tBodyAcc-std()-Y",
"tBodyAcc-std()-Z",
"tGravityAcc-mean()-X",
"tGravityAcc-mean()-Y",
"tGravityAcc-mean()-Z",
"tGravityAcc-std()-X",
"tGravityAcc-std()-Y",
"tGravityAcc-std()-Z",
"tBodyAccJerk-mean()-X",
"tBodyAccJerk-mean()-Y",
"tBodyAccJerk-mean()-Z",
"tBodyAccJerk-std()-X",
"tBodyAccJerk-std()-Y",
"tBodyAccJerk-std()-Z",
"tBodyGyro-mean()-X",
"tBodyGyro-mean()-Y",
"tBodyGyro-mean()-Z",
"tBodyGyro-std()-X",
"tBodyGyro-std()-Y",
"tBodyGyro-std()-Z",
"tBodyGyroJerk-mean()-X",
"tBodyGyroJerk-mean()-Y",
"tBodyGyroJerk-mean()-Z",
"tBodyGyroJerk-std()-X",
"tBodyGyroJerk-std()-Y",
"tBodyGyroJerk-std()-Z",
"tBodyAccMag-mean()",
"tBodyAccMag-std()",
"tGravityAccMag-mean()",
"tGravityAccMag-std()",
"tBodyAccJerkMag-mean()",
"tBodyAccJerkMag-std()",
"tBodyGyroMag-mean()",
"tBodyGyroMag-std()",
"tBodyGyroJerkMag-mean()",
"tBodyGyroJerkMag-std()",
"fBodyAcc-mean()-X",
"fBodyAcc-mean()-Y",
"fBodyAcc-mean()-Z",
"fBodyAcc-std()-X",
"fBodyAcc-std()-Y",
"fBodyAcc-std()-Z",
"fBodyAccJerk-mean()-X",
"fBodyAccJerk-mean()-Y",
"fBodyAccJerk-mean()-Z",
"fBodyAccJerk-std()-X",
"fBodyAccJerk-std()-Y",
"fBodyAccJerk-std()-Z",
"fBodyGyro-mean()-X",
"fBodyGyro-mean()-Y",
"fBodyGyro-mean()-Z",
"fBodyGyro-std()-X",
"fBodyGyro-std()-Y",
"fBodyGyro-std()-Z",
"fBodyAccMag-mean()",
"fBodyAccMag-std()",
"fBodyBodyAccJerkMag-mean()",
"fBodyBodyAccJerkMag-std()",
"fBodyBodyGyroMag-mean()",
"fBodyBodyGyroMag-std()",
"fBodyBodyGyroJerkMag-mean()",
"fBodyBodyGyroJerkMag-std()"
)]
## sort by subject and activity
trainandtestlabeled <- trainandtestlabeled[order(trainandtestlabeled$subject,
trainandtestlabeled$activity),]
## rename to TIDY names :>
trainandtestlabeled <- rename(trainandtestlabeled,
c("subject"="subject",
"activity"="activity",
"activity_label"="activity_label",
"tBodyAcc-mean()-X"="timeBodyAccMeanForX",
"tBodyAcc-mean()-Y"="timeBodyAccMeanForY",
"tBodyAcc-mean()-Z"="timeBodyAccMeanForZ",
"tBodyAcc-std()-X"="timeBodyAccStdForX",
"tBodyAcc-std()-Y"="timeBodyAccStdForY",
"tBodyAcc-std()-Z"="timeBodyAccStdForZ",
"tGravityAcc-mean()-X"="timeGravityAccMeanForX",
"tGravityAcc-mean()-Y"="timeGravityAccMeanForY",
"tGravityAcc-mean()-Z"="timeGravityAccMeanForZ",
"tGravityAcc-std()-X"="timeGravityAccStdForX",
"tGravityAcc-std()-Y"="timeGravityAccStdForY",
"tGravityAcc-std()-Z"="timeGravityAccStdForZ",
"tBodyAccJerk-mean()-X"="timeBodyAccJerkMeanForX",
"tBodyAccJerk-mean()-Y"="timeBodyAccJerkMeanForY",
"tBodyAccJerk-mean()-Z"="timeBodyAccJerkMeanForZ",
"tBodyAccJerk-std()-X"="timeBodyAccJerkStdForX",
"tBodyAccJerk-std()-Y"="timeBodyAccJerkStdForY",
"tBodyAccJerk-std()-Z"="timeBodyAccJerkStdForZ",
"tBodyGyro-mean()-X"="timeBodyGyroMeanForX",
"tBodyGyro-mean()-Y"="timeBodyGyroMeanForY",
"tBodyGyro-mean()-Z"="timeBodyGyroMeanForZ",
"tBodyGyro-std()-X"="timeBodyGyroStdForX",
"tBodyGyro-std()-Y"="timeBodyGyroStdForY",
"tBodyGyro-std()-Z"="timeBodyGyroStdForZ",
"tBodyGyroJerk-mean()-X"="timeBodyGyroJerkMeanForX",
"tBodyGyroJerk-mean()-Y"="timeBodyGyroJerkMeanForY",
"tBodyGyroJerk-mean()-Z"="timeBodyGyroJerkMeanForZ",
"tBodyGyroJerk-std()-X"="timeBodyGyroJerkStdForX",
"tBodyGyroJerk-std()-Y"="timeBodyGyroJerkStdForY",
"tBodyGyroJerk-std()-Z"="timeBodyGyroJerkStdForZ",
"tBodyAccMag-mean()"="timeBodyAccMagMean",
"tBodyAccMag-std()"="timeBodyAccMagStd",
"tGravityAccMag-mean()"="timeGravityAccMagMean",
"tGravityAccMag-std()"="timeGravityAccMagStd",
"tBodyAccJerkMag-mean()"="timeBodyAccJerkMagMean",
"tBodyAccJerkMag-std()"="timeBodyAccJerkMagStd",
"tBodyGyroMag-mean()"="timeBodyGyroMagMean",
"tBodyGyroMag-std()"="timeBodyGyroMagStd",
"tBodyGyroJerkMag-mean()"="timeBodyGyroJerkMagMean",
"tBodyGyroJerkMag-std()"="timeBodyGyroJerkMagStd",
"fBodyAcc-mean()-X"="freqBodyAccMeanForX",
"fBodyAcc-mean()-Y"="freqBodyAccMeanForY",
"fBodyAcc-mean()-Z"="freqBodyAccMeanForZ",
"fBodyAcc-std()-X"="freqBodyAccStdForX",
"fBodyAcc-std()-Y"="freqBodyAccStdForY",
"fBodyAcc-std()-Z"="freqBodyAccStdForZ",
"fBodyAccJerk-mean()-X"="freqBodyAccJerkMeanForX",
"fBodyAccJerk-mean()-Y"="freqBodyAccJerkMeanForY",
"fBodyAccJerk-mean()-Z"="freqBodyAccJerkMeanForZ",
"fBodyAccJerk-std()-X"="freqBodyAccJerkStdForX",
"fBodyAccJerk-std()-Y"="freqBodyAccJerkStdForY",
"fBodyAccJerk-std()-Z"="freqBodyAccJerkStdForZ",
"fBodyGyro-mean()-X"="freqBodyGyroMeanForX",
"fBodyGyro-mean()-Y"="freqBodyGyroMeanForY",
"fBodyGyro-mean()-Z"="freqBodyGyroMeanForZ",
"fBodyGyro-std()-X"="freqBodyGyroStdForX",
"fBodyGyro-std()-Y"="freqBodyGyroStdForY",
"fBodyGyro-std()-Z"="freqBodyGyroStdForZ",
"fBodyAccMag-mean()"="freqBodyAccMagMean",
"fBodyAccMag-std()"="freqBodyAccMagStd",
"fBodyBodyAccJerkMag-mean()"="freqBodyAccJerkMagMean",
"fBodyBodyAccJerkMag-std()"="freqBodyAccJerkMagStd",
"fBodyBodyGyroMag-mean()"="freqBodyGyroMagMean",
"fBodyBodyGyroMag-std()"="freqBodyGyroMagStd",
"fBodyBodyGyroJerkMag-mean()"="freqBodyGyroJerkMagMean",
"fBodyBodyGyroJerkMag-std()"="freqBodyGyroJerkMagStd"))
## export out the tidy file
write.table(trainandtestlabeled, file = "UCIHARconsolidated.txt",row.name=FALSE)
## generate our means
trainandtestlabeledMeans <-ddply(trainandtestlabeled, .(subject, activity, activity_label), numcolwise(mean))
## export out the tidy file
write.table(trainandtestlabeledMeans, file = "UCIHARconsolidatedMeans.txt",row.name=FALSE)
## end of script