-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathCilantro Figures 2 and 3 NSample.Rmd
339 lines (252 loc) · 10.3 KB
/
Cilantro Figures 2 and 3 NSample.Rmd
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
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
---
title: "Untitled"
output: html_document
date: "2022-11-28"
---
```{r}
library(tidyverse)
library(reshape2)
library(readr)
```
```{r}
Unc_Conts<-read_csv("Data/Water_Testing_Analysis_R4.csv")
```
```{r}
Unc_Conts<-Unc_Conts %>%
select(-...1) %>%
mutate(N10Lsamples= as.factor(N10Lsamples)) %>%
group_by(N10Lsamples, Conts) %>%
summarise(median = median(PDetect), q05 = quantile(PDetect, 0.05), q95 = quantile(PDetect, 0.95))
```
Unc_Conts %>%
ggplot(aes(x = Conts, y = median, shape =N10Lsamples, linetype =N10Lsamples, color =N10Lsamples,ymin=q05, ymax=q95, fill = N10Lsamples))+
geom_point(alpha = 0.5)+
geom_line()+
geom_ribbon(alpha= 0.3)+
labs(x = "Contamination Levels Bulk Water: Oocyst/L", y = "Probability of Detection: 10L Sample(s)", fill = "No. 10L Samples", color= "No. 10L Samples", shape = "No. 10L Samples", linetype ="No. 10L Samples" )
ggsave("Contamination vs Method- R2.jpeg", width = 15, height = 10, units = "cm", dpi = 600)
```{r}
Unc_Conts %>%
filter(Conts <=1.6) %>%
ggplot(aes(x = Conts, y = median, shape =N10Lsamples, linetype =N10Lsamples, color =N10Lsamples,ymin=q05, ymax=q95, fill = N10Lsamples))+
geom_point(size= 1.3, alpha = 0.6)+
geom_line()+
geom_ribbon(alpha= 0.3)+
labs(x = "Contamination Levels Bulk Water: Oocyst/L", y = "Probability of Detection: 10L Sample(s)", fill = "No. 10L Samples", color= "No. 10L Samples", shape = "No. 10L Samples", linetype ="No. 10L Samples" )+
scale_x_continuous(limits = c(0,1.6), breaks = c(0,0.5,1,1.5,1.6))+
theme_bw()+
theme(axis.text.x=element_text(size =12), axis.text.y=element_text(size =12),axis.title = element_text(size = 12))+
theme(legend.position=c(0.75, 0.3))
ggsave("Contamination vs Method-R4.jpeg", width = 15, height = 10, units = "cm", dpi = 600)
```
```{r}
Conts_WT = Unc_Conts[1:201,2]
WT_1<-Unc_Conts %>%
filter(N10Lsamples==1)
WT_2<-Unc_Conts %>%
filter(N10Lsamples==2)
WT_4<-Unc_Conts %>%
filter(N10Lsamples==4)
WT_8<-Unc_Conts %>%
filter(N10Lsamples==8)
WT_16<-Unc_Conts %>%
filter(N10Lsamples==16)
WT_32<-Unc_Conts %>%
filter(N10Lsamples==32)
Conts_WT$`1`<-WT_1$median-WT_1$median
Conts_WT$`2`<-WT_2$median-WT_1$median
Conts_WT$`4`<-WT_4$median-WT_1$median
Conts_WT$`8`<-WT_8$median-WT_1$median
Conts_WT$`16`<-WT_16$median-WT_1$median
Conts_WT$`32`<-WT_32$median-WT_1$median
Conts_WT %>%
melt(id = "Conts") %>%
filter(Conts<=1.6) %>%
ggplot(aes(x = Conts, y = value, color = variable,shape =variable, fill = variable))+
geom_point(size= 1.3, alpha = 0.6)+
scale_x_continuous(limits = c(0,1.6), breaks = c(0,0.5,1,1.5,1.6))+
geom_line()+
theme_bw()+
labs(x = "Contamination Levels Bulk Water: Oocyst/L", y = "Difference in median probability of detection\n n number of samples vs. 1 10L Sample", color = "No. 10L Samples", shape = "No. 10L Samples", fill = "No. 10L Samples")+
theme(axis.text.x=element_text(size =12), axis.text.y=element_text(size =12),axis.title = element_text(size = 12))+
theme(legend.position=c(0.75, 0.7))
ggsave("Contamination vs Method Differences Water-R4.jpeg", width = 15, height = 10, units = "cm", dpi = 600)
```
```{r}
Unc_Conts<-read_csv("Data/Product_Testing_Analysis_R4.csv")
#Unc_Conts$Conts<- log10(Unc_Conts$Conts)
```
```{r}
# #LOG
# Unc_Conts<-Unc_Conts %>%
# mutate(log_CFU_g_conts = log10(10^Conts/(454*22000))) %>%
# select(-...1) %>%
# mutate(N25gsamples= as.factor(N25gsamples)) %>%
# group_by(N25gsamples, log_CFU_g_conts) %>%
# summarise(median = median(PDetect), q05 = quantile(PDetect, 0.05), q95 = quantile(PDetect, 0.95))
#NON LOG
Unc_Conts<-Unc_Conts %>%
mutate(Conts = Conts/(454*22000)) %>%
select(-...1) %>%
mutate(N25gsamples= as.factor(N25gsamples)) %>%
group_by(N25gsamples, Conts) %>%
summarise(median = median(PDetect), q05 = quantile(PDetect, 0.05), q95 = quantile(PDetect, 0.95))
#non log
Unc_Conts %>%
filter(Conts<= 1.6) %>%
ggplot(aes(x = Conts, y = median, color =N25gsamples, shape =N25gsamples, linetype =N25gsamples, ymin=q05, ymax=q95, fill = N25gsamples))+
geom_point(size= 1.3, alpha = 0.6)+
geom_line()+
geom_ribbon(alpha= 0.3)+
theme_bw()+
scale_x_continuous(limits = c(0,1.6), breaks = c(0,0.5,1,1.5,1.6))+
theme(legend.position="top")+
labs(x = "Contamination Levels in Field:Oocysts/g ", y = "Probability of Detection: 25g sample(s)", fill = "No. 25 g Samples", color= "No. 25 g Samples", linetype = "No. 25 g Samples", shape = "No. 25 g Samples")+
theme(axis.text.x=element_text(size =12), axis.text.y=element_text(size =12),axis.title = element_text(size = 12))+
theme(legend.position=c(0.75, 0.3))
# #log
# Unc_Conts %>%
# ggplot(aes(x = log_CFU_g_conts, y = median, color =N25gsamples, shape =N25gsamples, linetype =N25gsamples, ymin=q05, ymax=q95, fill = N25gsamples))+
# geom_point(alpha = 0.5, size = 2.5)+
# geom_line()+
# geom_ribbon(alpha= 0.3)+
# theme_bw()+
# theme(legend.position="top")+
# labs(x = "Contamination Levels in Field: log (Oocysts/g) ", y = "Probability of Detection: 25g sample(s)", fill = "No. 25 g Samples", color= "No. 25 g Samples", linetype = "No. 25 g Samples", shape = "No. 25 g Samples")
ggsave("Figures/Contamination vs Field Contam-R4.jpeg", width = 15, height = 10, units = "cm", dpi = 600)
```
```{r}
Conts_PD = Unc_Conts[1:170,2]
as.data.frame(Conts_PD)
PD_1<-Unc_Conts %>%
filter(N25gsamples==1)
PD_2<-Unc_Conts %>%
filter(N25gsamples==2)
PD_4<-Unc_Conts %>%
filter(N25gsamples==4)
PD_8<-Unc_Conts %>%
filter(N25gsamples==8)
PD_16<-Unc_Conts %>%
filter(N25gsamples==16)
PD_32<-Unc_Conts %>%
filter(N25gsamples==32)
Conts_PD$`1`<-PD_1$median-PD_1$median
Conts_PD$`2`<-PD_2$median-PD_1$median
Conts_PD$`4`<-PD_4$median-PD_1$median
Conts_PD$`8`<-PD_8$median-PD_1$median
Conts_PD$`16`<-PD_16$median-PD_1$median
Conts_PD$`32`<-PD_32$median-PD_1$median
#non log
Conts_PD %>%
melt(id = "Conts") %>%
filter(Conts<1.6) %>%
ggplot(aes(x = Conts, y = value, color = variable,shape =variable, fill = variable))+
geom_point(size= 1.3, alpha = 0.6)+
geom_line()+
scale_x_continuous(limits = c(0,1.6), breaks = c(0,0.5,1,1.5,1.6))+
theme_bw()+
theme(legend.position="top")+
labs(x = "Contamination Levels in Field: Oocysts/g", y = "Difference in median probability of detection\n n number of samples vs. 1 25g Sample", color = "No. 25g Samples", shape = "No. 25g Samples", fill = "No. 25g Samples")+
theme(axis.text.x=element_text(size =12), axis.text.y=element_text(size =12),axis.title = element_text(size = 12))+
theme(legend.position=c(0.75, 0.70))
# #log version
# Conts_PD %>%
# melt(id = "log_CFU_g_conts") %>%
# #filter(log_CFU_g_conts<2) %>%
# ggplot(aes(x = log_CFU_g_conts, y = value, color = variable,shape =variable, fill = variable))+
# geom_point(size= 2.5)+
# geom_line()+
# theme_bw()+
# theme(legend.position="top")+
# labs(x = "Contamination Levels in Field: log (Oocysts/g)", y = "Difference in median probability of detection\n n number of samples vs. 1 25g Sample", color = "No. 25g Samples", shape = "No. 25g Samples", fill = "No. 25g Samples")
ggsave("Figures/Contamination vs Method Differences Contam-R4.jpeg", width = 15, height = 10, units = "cm", dpi = 600)
```
Area Under the curve for water sampling
```{r}
library(pracma)
AUC2 = trapz(Conts_WT$Conts, y = Conts_WT$`2`)
AUC4 = trapz(Conts_WT$Conts, y = Conts_WT$`4`)
AUC8 = trapz(Conts_WT$Conts, y = Conts_WT$`8`)
AUC16 = trapz(Conts_WT$Conts, y = Conts_WT$`16`)
AUC32 = trapz(Conts_WT$Conts, y = Conts_WT$`32`)
AUC2/1
AUC4/AUC2
AUC8/AUC4
AUC16/AUC8
AUC32/AUC16
AUC32-AUC16
AUC16-AUC8
AUC8-AUC4
AUC4-AUC2
AUC2
```
```{r}
meds<-read_csv("Data_Cilantro_Outputs/Product_Testing_Meds.csv")
meds %>%
ggplot(aes(x= Conts/(22000*454), y = PDetect))+
geom_point()+
labs(y = "median p detect", x= "Contamination CFU/g")
```
```{r}
meds_w<-read_csv("Data_Cilantro_Outputs/Water_Testing_Meds.csv")
meds_w %>%
ggplot(aes(x= Conts, y = PDetect))+
geom_point()+
labs(y = "median p detect", x= "Contamination oocyst/L")
```
```{r}
#AUC
#Areas under the curve
integrate(approxfun(Conts_PD$log_CFU_g_conts, y = Conts_PD$`2`),-3.9994785337, 0.4005214663)
library(pracma)
AUC2 = trapz(Conts_PD$log_CFU_g_conts, y = Conts_PD$`2`)
AUC4 = trapz(Conts_PD$log_CFU_g_conts, y = Conts_PD$`4`)
AUC8 = trapz(Conts_PD$log_CFU_g_conts, y = Conts_PD$`8`)
AUC16 = trapz(Conts_PD$log_CFU_g_conts, y = Conts_PD$`16`)
AUC32 = trapz(Conts_PD$log_CFU_g_conts, y = Conts_PD$`32`)
AUC2/AUC4
AUC4/AUC8
AUC8/AUC16
AUC16/AUC32
AUC32-AUC16
AUC16-AUC8
AUC8-AUC4
AUC4-AUC2
seq(0,1.5, 0.01)*22000*454
```
```{r}
Unc_Conts %>%
filter(Conts<5.0e+06) %>%
ggplot(aes(x = Conts, y = median, color =N25gsamples,ymin=q05, ymax=q95, fill = N25gsamples))+
geom_point(alpha = 0.5)+
geom_line()+
geom_ribbon(alpha= 0.3)+
labs(x = "Contamiantion levels total Oocysts in Field", y = "Probability of Detection", fill = "No. 25g Samples", color= "No. 25g Samples")
```
### Logistic Fits
```{r}
#product Testing
PT_Qpcr_Results<-read_csv("Data/qPCR_Fit_Product_Testing.csv")
PT_Qpcr_Probs<-read_csv("Data/qPCR_Fit_Product_Testing_Probs.csv")
ggplot()+
geom_hline(aes(yintercept = .313),color = "orange")+
geom_hline(aes(yintercept = .80),color = "red")+
geom_vline(aes(xintercept = 5),color = "orange")+
geom_vline(aes(xintercept = 10),color = "red")+
geom_line(aes(x = Cont, y = `Prob Detect`), data = PT_Qpcr_Probs)+
geom_point(aes(x = Cont, y = Results), data = PT_Qpcr_Results,position = position_jitter(height = 0.01, width = 1),shape= 21, fill = "skyblue")+
labs(x= "Oocyst/ 25 g Sample", y = "Predicted Detection Rate", title = "Logistic Fit: Product Testing")+
theme_bw()
ggsave(filename="Figures/Product Testing Fit.png",width = 10, height = 10, units = "cm", dpi = 600)
#Water Testing
WT_Qpcr_Results<-read_csv("Data/qPCR_Fit_Water_Testing.csv")
WT_Qpcr_Probs<-read_csv("Data/qPCR_Fit_Water_Testing_Probs.csv")
ggplot()+
geom_hline(aes(yintercept = .66),color = "red")+
geom_vline(aes(xintercept = 6),color = "red")+
geom_line(aes(x = Cont, y = `Prob Detect`), data = WT_Qpcr_Probs)+
geom_point(aes(x = Cont, y = Results), data = WT_Qpcr_Results,position = position_jitter(height = 0.01, width = 1),shape= 21, fill = "skyblue")+
labs(x= "Oocyst/ 10L Sample", y = "Predicted Detection Rate", title = "Logistic Fit: Agricultural Water Testing")+
theme_bw()
ggsave(filename="Figures/Water Testing Fit.png",width = 10, height = 10, units = "cm", dpi = 600)
```