-
Notifications
You must be signed in to change notification settings - Fork 2
/
StreamAnalysisV2.R
284 lines (263 loc) · 14.8 KB
/
StreamAnalysisV2.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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
library("plyr")
library(dplyr)
library("ggplot2")
library(lubridate)
library("ape")
library("vegan")
library("microbiome")
library(data.table)
library(tidyr)
setwd("~/Desktop/SCCWRP")
#Read in site data containing biological counts, water chemistry, and land usage
#values. Generate a merged data set.
#GISBiochemData <- read.table("GISBiochemData.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
#If you need to aggregate site data please proceed here.
#Read in algae data from SMC sites.
algaeDataSMCRaw <- read.table("AlgaeTax_dnaSites_SMC.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
#Subset only replicate 1
algaeDataSMC <- filter(algaeDataSMCRaw, Replicate==1)
#Subset columns of interest for the SMC sites.
algaeDataSMC <- algaeDataSMCRaw[,c(2,3,43,44,40)]
#Determine the algal totals count column and make it a temporary dataframe.
tmp1 <- as.data.frame(xtabs(BAResult ~ StationCode,algaeDataSMC))
colnames(tmp1) <- c("StationCode","ActualOrganismCount")
#Determine the algal volumes column and make it a temporary dataframe.
tmp2 <- as.data.frame(xtabs(Result ~ StationCode,algaeDataSMC))
colnames(tmp2) <- c("StationCode","ActualOrganismVolume")
#Add algal totals count column to algae dataframe.
algaeDataSMC <- merge(algaeDataSMC,tmp1,"StationCode")
algaeDataSMC <- merge(algaeDataSMC,tmp2,"StationCode")
#Temporarily split data frame into soft-bodied and benthic algae sets.
#Determine each algal sets relative abundances and then merge data frames back.
tmp1 <- filter(algaeDataSMC,BAResult!="NA")
#Calculate the relative abundance of benthic algae data.
tmp1$Measurement <- with(tmp1,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
tmp1$MeasurementType <- with(tmp1,"Benthic algal relative abundance")
tmp2 <- filter(algaeDataSMC, Result!="NA")
#Calculate the relative abundance of soft-bodied algae data.
tmp2$Measurement <- with(tmp2,Result/ActualOrganismVolume)
#Add organism type for later use in merged data sets.
tmp2$MeasurementType <- with(tmp2,"Soft-bodied algal relative abundance")
algaeDataSMC <- rbind(tmp1,tmp2)
#Force a uniform date format
algaeDataSMC$SampleDate <- mdy(algaeDataSMC$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
algaeDataSMC$UniqueID <- with(algaeDataSMC,paste(algaeDataSMC$StationCode,"SMC",algaeDataSMC$SampleDate))
#Find sampling year.
algaeDataSMC$Year <- year(algaeDataSMC$SampleDate)
#Read in algae data from CEDEN sites.
algaeDataCEDENRaw <- read.table("AlgaeTax_dnaSites_CEDEN.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
#Subset only replicate 1
algaeDataCEDEN <- filter(algaeDataCEDENRaw, CollectionReplicate==1)
#Subset columns of interest for the CEDEN sites.
algaeDataCEDEN <- algaeDataCEDENRaw[,c(6,11,36,35,26)]
names(algaeDataCEDEN)[names(algaeDataCEDEN)=="Counts"]<-"Result"
#Determine the algal totals count column and make it a temporary dataframe.
tmp1 <- as.data.frame(xtabs(BAResult ~ StationCode,algaeDataCEDEN))
colnames(tmp1) <- c("StationCode","ActualOrganismCount")
#Determine the algal volumes column and make it a temporary dataframe.
tmp2 <- as.data.frame(xtabs(Result ~ StationCode,algaeDataCEDEN))
colnames(tmp2) <- c("StationCode","ActualOrganismVolume")
#Add algal totals count column to algae dataframe.
algaeDataCEDEN <- merge(algaeDataCEDEN,tmp1,"StationCode")
algaeDataCEDEN <- merge(algaeDataCEDEN,tmp2,"StationCode")
#Temporarily split data frame into soft-bodied and benthic algae sets.
#Determine each algal sets relative abundances and then merge data frames back.
tmp1 <- filter(algaeDataCEDEN,BAResult!="NA")
#Calculate the relative abundance of benthic algae data.
tmp1$Measurement <- with(tmp1,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
tmp1$MeasurementType <- with(tmp1,"Benthic algal relative abundance")
tmp2 <- filter(algaeDataCEDEN, Result!="NA")
#Calculate the relative abundance of soft-bodied algae data.
tmp2$Measurement <- with(tmp2,Result/ActualOrganismVolume)
#Add organism type for later use in merged data sets.
tmp2$MeasurementType <- with(tmp2,"Soft-bodied algal relative abundance")
algaeDataCEDEN <- rbind(tmp1,tmp2)
#Force a uniform date format
algaeDataCEDEN$SampleDate <- ymd(algaeDataCEDEN$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
algaeDataCEDEN$UniqueID <- with(algaeDataCEDEN,paste(algaeDataCEDEN$StationCode,"CEDEN",algaeDataCEDEN$SampleDate))
#Find sampling year.
algaeDataCEDEN$Year <- year(algaeDataCEDEN$SampleDate)
#The SWAMP data file is in a somewhat irregular format and this is accounted for
#when being read in.
algaeDataSWAMPRaw <- read.table("AlgaeTaxonomy_dnaSamples_SWAMP.csv", fill=TRUE,header=TRUE, sep=",",as.is=T,check.names=FALSE)
#Subset only replicate 1
algaeDataSWAMP <- filter(algaeDataSWAMPRaw, Replicate==1)
algaeDataSWAMP <- algaeDataSWAMPRaw[,c(6,8,97,99,90)]
#Determine the algal totals count column and make it a temporary dataframe.
tmp1 <- as.data.frame(xtabs(BAResult ~ StationCode,algaeDataSWAMP))
colnames(tmp1) <- c("StationCode","ActualOrganismCount")
#Determine the algal volumes column and make it a temporary dataframe.
tmp2 <- as.data.frame(xtabs(Result ~ StationCode,algaeDataSWAMP))
colnames(tmp2) <- c("StationCode","ActualOrganismVolume")
#Add algal totals count column to algae dataframe.
algaeDataSWAMP <- merge(algaeDataSWAMP,tmp1,"StationCode")
algaeDataSWAMP <- merge(algaeDataSWAMP,tmp2,"StationCode")
#Temporarily split data frame into soft-bodied and benthic algae sets.
#Determine each algal sets relative abundances and then merge data frames back.
tmp1 <- filter(algaeDataSWAMP,BAResult!="NA")
#Calculate the relative abundance of benthic algae data.
tmp1$Measurement <- with(tmp1,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
tmp1$MeasurementType <- with(tmp1,"Benthic algal relative abundance")
tmp2 <- filter(algaeDataSWAMP, Result!="NA")
#Calculate the relative abundance of soft-bodied algae data.
tmp2$Measurement <- with(tmp2,Result/ActualOrganismVolume)
#Add organism type for later use in merged data sets.
tmp2$MeasurementType <- with(tmp2,"Soft-bodied algal relative abundance")
algaeDataSWAMP <- rbind(tmp1,tmp2)
#Force a uniform date format
algaeDataSWAMP$SampleDate <- mdy(algaeDataSWAMP$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
algaeDataSWAMP$UniqueID <- with(algaeDataSWAMP,paste(algaeDataSWAMP$StationCode,"SWAMP",algaeDataSWAMP$SampleDate))
#Find sampling year.
algaeDataSWAMP$Year <- year(algaeDataSWAMP$SampleDate)
#Create merged algae data set.
algaeData <- do.call("rbind",list(algaeDataSMC,algaeDataSWAMP,algaeDataCEDEN))
#Remove raw count data.
algaeData <- within(algaeData,rm("BAResult","Result","ActualOrganismCount","ActualOrganismVolume"))
#Reorder columns prior to merger.
algaeData <- algaeData[c("StationCode","SampleDate","FinalID","Measurement","MeasurementType","UniqueID","Year")]
#Read in insect data from SMC sites.
insectDataSMCRAW <- read.csv("BugTax_dnaSites_SMC.csv")
#Subset only replicate 1
insectDataSMC <- filter(insectDataSMCRAW, FieldReplicate==1)
#Subset columns of interest.
insectDataSMC <- insectDataSMC[,c("StationCode","SampleDate","FinalID","BAResult")]
tmp<-data.table(insectDataSMC)
#Sum insect counts for matching IDs, but with different life stages.
insectDataSMC<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate,FinalID)]
#Determine the insect totals count column by StationCode and SampleDate and make it a temporary dataframe.
tmp<-data.table(insectDataSMC)
tmp<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate)]
colnames(tmp) <- c("StationCode","SampleDate","ActualOrganismCount")
#Merge in the total insect count column.
insectDataSMC<-join(insectDataSMC,tmp,by=c("StationCode","SampleDate"))
#Calculate the relative abundance of insect data.
insectDataSMC$Measurement <- with(insectDataSMC,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
insectDataSMC$MeasurementType <- with(insectDataSMC,"Invertebrate relative abundances")
#Force a uniform date format
insectDataSMC$SampleDate <- mdy(insectDataSMC$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
insectDataSMC$UniqueID <- with(insectDataSMC,paste(insectDataSMC$StationCode,"SMC",insectDataSMC$SampleDate))
#Find sampling year.
insectDataSMC$Year <- year(insectDataSMC$SampleDate)
#Read in insect data from CEDEN sites.
insectDataCEDENRAW <- read.table("BugTax_dnaSites_CEDEN.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
#Subset only replicate 1
insectDataCEDEN <- filter(insectDataCEDENRAW, CollectionReplicate==1)
#Subset columns of interest.
insectDataCEDEN <- insectDataCEDENRAW[,c("StationCode","SampleDate","FinalID","BAResult")]
tmp<-data.table(insectDataCEDEN)
#Sum insect counts for matching IDs, but with different life stages.
insectDataCEDEN<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate,FinalID)]
#Determine the insect totals count column by StationCode and SampleDate and make it a temporary dataframe.
tmp<-data.table(insectDataCEDEN)
tmp<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate)]
colnames(tmp) <- c("StationCode","SampleDate","ActualOrganismCount")
#Merge in the total insect count column.
insectDataCEDEN<-join(insectDataCEDEN,tmp,by=c("StationCode","SampleDate"))
#Calculate the relative abundance of insect data.
insectDataCEDEN$Measurement <- with(insectDataCEDEN,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
insectDataCEDEN$MeasurementType <- with(insectDataCEDEN,"Invertebrate relative abundance")
#Force a uniform date format
insectDataCEDEN$SampleDate <- ymd(insectDataCEDEN$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
insectDataCEDEN$UniqueID <- with(insectDataCEDEN,paste(insectDataCEDEN$StationCode,"CEDEN",insectDataCEDEN$SampleDate))
#Find sampling year.
insectDataCEDEN$Year <- year(insectDataCEDEN$SampleDate)
#Read in insect data from SWAMP sites.
insectDataSWAMPRAW <- read.table("BugTaxonomy_dnaSamples_SWAMP.csv", header=TRUE, sep=",",as.is=T,skip=0,fill=TRUE,check.names=FALSE)
#Subset only replicate 1
insectDataSWAMP <- filter(insectDataSWAMPRAW, Replicate==1)
#Subset columns of interest.
insectDataSWAMP <- insectDataSWAMPRAW[,c("StationCode","SampleDate","FinalID","BAResult")]
#Sum insect counts for matching IDs, but with different life stages.
tmp<-data.table(insectDataSWAMP)
#Sum insect counts for matching IDs, but with different life stages.
insectDataSWAMP<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate,FinalID)]
#Determine the insect totals count column by StationCode and SampleDate and make it a temporary dataframe.
tmp<-data.table(insectDataSWAMP)
tmp<-tmp[,.(BAResult=sum(BAResult)),by=.(StationCode,SampleDate)]
colnames(tmp) <- c("StationCode","SampleDate","ActualOrganismCount")
#Merge in the total insect count column.
insectDataSWAMP<-join(insectDataSWAMP,tmp,by=c("StationCode","SampleDate"))
#Calculate the relative abundance of insect data.
insectDataSWAMP$Measurement <- with(insectDataSWAMP,BAResult/ActualOrganismCount)
#Add organism type for later use in merged data sets.
insectDataSWAMP$MeasurementType <- with(insectDataSWAMP,"Invertebrate relative abundance")
insectDataSWAMP <- subset(insectDataSWAMP,insectDataSWAMP$BAResult!='NA')
#Force a uniform date format
insectDataSWAMP$SampleDate <- mdy(insectDataSWAMP$SampleDate)
#Create unique ID combining the sample station ID and sampling date.
insectDataSWAMP$UniqueID <- with(insectDataSWAMP,paste(insectDataSWAMP$StationCode,"SWAMP",insectDataSWAMP$SampleDate))
#Find sampling year.
insectDataSWAMP$Year <- year(insectDataSWAMP$SampleDate)
#Create merged insect data set.
insectData <- do.call("rbind",list(insectDataSMC,insectDataSWAMP,insectDataCEDEN))
#Remove raw count data.
insectData <- within(insectData,rm("BAResult","ActualOrganismCount"))
#Reorder columns prior to merger.
insectData <- insectData[,c("StationCode","SampleDate","FinalID","Measurement","MeasurementType","UniqueID","Year")]
#Merge insect and algae data.
bioData <- do.call("rbind",list(insectData,algaeData))
bioData <- bioData[!duplicated(bioData),]
#Reorder columns post merger.
bioData <- bioData[,c("StationCode","SampleDate","FinalID","Measurement","MeasurementType","UniqueID","Year")]
#Read in geospatial data.
GISDataRAW <- read.table("GIS_dnaSites.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
#Subset columns of interest. StationID, location, and land usage.
GISData <- GISDataRAW[,c(2,6:7,94,97,100)]
names(GISData)[names(GISData)=="New_Lat"]<-"Latitude"
names(GISData)[names(GISData)=="New_Long"]<-"Longitude"
#Merge geospatial data with biological observations.
GISBioData <- join(bioData,GISData,by="StationCode")
#Sort merged data set by year then measurement name.
GISBioData <- as.data.frame(GISBioData[order(as.numeric(GISBioData$Year),as.character(GISBioData$FinalID)),])
#Filter out duplicate rows.
GISBioData <- GISBioData[!duplicated(GISBioData),]
#Calculate land usage index based on 5km catchment zone values from 2011.
GISBioData$LU_2011_5K <- with(GISBioData,Ag_2011_5K+CODE_21_2011_5K+URBAN_2011_5K)
#Incorporate CSCI data.
csciData1 <- read.csv("CSCI_dnaSites.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
csciData1 <- filter(csciData1,CSCI!="NA")
#csciData1 <- subset(csciData1,select=-c(StationCode))
#Fix date format.
csciData1$SampleDate <- mdy(csciData1$SampleDate)
#Create Year column.
csciData1$Year <- year(csciData1$SampleDate)
#Insert Unique ID
csciData1$UniqueID <- with(csciData1,paste(csciData1$StationCode,"SWAMP",csciData1$SampleDate))
#Subset UniqueID and CSCI.
csciData1 <- csciData1[,c("UniqueID","StationCode","SampleDate","CSCI")]
#Incorporate CSCI data.
csciData2 <- read.csv("csci_scored_sites_tbl.csv", header=TRUE, sep=",",as.is=T,check.names=FALSE)
csciData2 <- filter(csciData2,CSCI!="NA")
#names(csciData2)[names(csciData2)=="StationCode"]<-"SampleStationID"
#Fix date format.
csciData2$SampleDate <- mdy(csciData2$SAMPLEDATE)
#Create Year column.
csciData2$Year <- year(csciData2$SampleDate)
#Insert Unique ID
csciData2$UniqueID <- with(csciData2,paste(csciData2$StationCode,"SWAMP",csciData2$SampleDate))
#Subset UniqueID and CSCI.
csciData2 <- csciData2[,c("UniqueID","StationCode","SampleDate","CSCI")]
#Merge into a single CSCI dataframe.
csciData <- rbind(csciData1,csciData2)
csciData <- csciData[,c("StationCode","SampleDate","CSCI")]
csciData <- csciData[!duplicated(csciData),]
#Merge CSCI data by StationCode and SampleDate.
GISBioData <- join(GISBioData,csciData,by=c("StationCode","SampleDate"))
GISBioData <- GISBioData[!duplicated(GISBioData),]
#Run if you want to filter out data without a land usage index.
GISBioData <- subset(GISBioData,LU_2011_5K!="NA")
#Run if you want to filter out data without a CSCI value.
GISBioData <- subset(GISBioData,CSCI!="NA")
#Write out merged data set to read back in the future as opposed to
#generating it each time from component data files.
write.csv(GISBioData,file="GISBioData.csv",row.names=FALSE)