R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

plot(cars)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

#ALL CODE FOR ASSIGNMENT 2

install.packages(c("tidyverse", "pwr"))

Error in install.packages : Updating loaded packages

library(tidyverse)
library(lubridate)

#NEW CODE FOR GLM INFORMATION
images <- read_csv("images.csv")

# Confirm exact species names
images %>%
  count(common_name, sort = TRUE)

# Filter focal species and count detections per deployment
species_counts <- images %>%
  filter(common_name %in% c(
    "Harvey's Duiker",
    "Suni",
    "Bushbuck",
    "Blue Duiker"
  )) %>%
  count(deployment_id, common_name, name = "occurences")

#keep values only with TZA-001 to match
library(dplyr)
dat_names_cleaned <- species_counts %>%
  filter(grepl("^TZA-001", deployment_id, ignore.case = TRUE))

library(tidyverse)
library(lubridate)

species_wide <- dat_names_cleaned %>%
  tidyr::pivot_wider(
    names_from  = common_name,
    values_from = occurences,
    values_fill = 0
  ) %>%
  rename(
    harveys_duiker = `Harvey's Duiker`,
    suni           = `Suni`,
    bushbuck       = `Bushbuck`,
    blue_duiker    = `Blue Duiker`
  )

glimpse(species_wide)

Rows: 92
Columns: 5
$ deployment_id  <chr> "TZA-001-D0005", "TZA-001-D0010", "TZA-001-D0019", "TZA-001-D0025", "TZA-001-D0031", "T…
$ harveys_duiker <int> 10, 5, 26, 9, 4, 4, 1, 0, 21, 2, 5, 8, 1, 0, 3, 0, 0, 1, 1, 2, 0, 1, 1, 1, 3, 2, 0, 0, …
$ suni           <int> 4, 0, 4, 4, 0, 1, 0, 0, 1, 0, 4, 6, 0, 0, 0, 2, 0, 0, 0, 0, 1, 0, 1, 0, 2, 0, 2, 3, 1, …
$ blue_duiker    <int> 0, 0, 0, 0, 0, 4, 1, 1, 0, 0, 0, 0, 1, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
$ bushbuck       <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …

#GLM CALCULATIONS

m_suni <- glm(
  suni ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

m_bushbuck <- glm(
  bushbuck ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

m_blue <- glm(
  blue_duiker ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

summary(m_suni)

Call:
glm(formula = suni ~ harveys_duiker, family = poisson, data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)     0.46900    0.09551   4.910  9.1e-07 ***
harveys_duiker  0.02527    0.01576   1.603    0.109    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 295.54  on 91  degrees of freedom
Residual deviance: 293.24  on 90  degrees of freedom
AIC: 431.62

Number of Fisher Scoring iterations: 6

summary(m_bushbuck)

Call:
glm(formula = bushbuck ~ harveys_duiker, family = poisson, data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)    -0.96421    0.20673  -4.664  3.1e-06 ***
harveys_duiker -0.01139    0.04361  -0.261    0.794    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 171.34  on 91  degrees of freedom
Residual deviance: 171.27  on 90  degrees of freedom
AIC: 203.38

Number of Fisher Scoring iterations: 7

summary(m_blue)

Call:
glm(formula = blue_duiker ~ harveys_duiker, family = poisson, 
    data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)    -1.75239    0.34171  -5.128 2.92e-07 ***
harveys_duiker -0.09051    0.10812  -0.837    0.402    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 67.513  on 91  degrees of freedom
Residual deviance: 66.542  on 90  degrees of freedom
AIC: 89.035

Number of Fisher Scoring iterations: 6

#GLM CALCULATIONS

m_suni <- glm(
  suni ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

m_bushbuck <- glm(
  bushbuck ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

m_blue <- glm(
  blue_duiker ~ harveys_duiker,
  family = poisson,
  data = species_wide
)

summary(m_suni)

Call:
glm(formula = suni ~ harveys_duiker, family = poisson, data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)     0.46900    0.09551   4.910  9.1e-07 ***
harveys_duiker  0.02527    0.01576   1.603    0.109    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 295.54  on 91  degrees of freedom
Residual deviance: 293.24  on 90  degrees of freedom
AIC: 431.62

Number of Fisher Scoring iterations: 6

summary(m_bushbuck)

Call:
glm(formula = bushbuck ~ harveys_duiker, family = poisson, data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)    -0.96421    0.20673  -4.664  3.1e-06 ***
harveys_duiker -0.01139    0.04361  -0.261    0.794    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 171.34  on 91  degrees of freedom
Residual deviance: 171.27  on 90  degrees of freedom
AIC: 203.38

Number of Fisher Scoring iterations: 7

summary(m_blue)

Call:
glm(formula = blue_duiker ~ harveys_duiker, family = poisson, 
    data = species_wide)

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)    -1.75239    0.34171  -5.128 2.92e-07 ***
harveys_duiker -0.09051    0.10812  -0.837    0.402    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 67.513  on 91  degrees of freedom
Residual deviance: 66.542  on 90  degrees of freedom
AIC: 89.035

Number of Fisher Scoring iterations: 6

#CODE TO CREATE ANTELOPE DENSITY COMPARISON GRAPH
#stuff from original code
install.packages(c("tidyverse", "pwr"))

Error in install.packages : Updating loaded packages

library(tidyverse)
install.packages(c("tidyverse", "pwr"))

WARNING: Rtools is required to build R packages but is not currently installed. Please download and install the appropriate version of Rtools before proceeding:

https://cran.rstudio.com/bin/windows/Rtools/

Warning in install.packages :
  package ‘tidyverse’ is in use and will not be installed

trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.5/pwr_1.3-0.zip'
Content type 'application/zip' length 161960 bytes (158 KB)
downloaded 158 KB

package ‘pwr’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\tyl25njr\AppData\Local\Temp\Rtmpa2MJe9\downloaded_packages

library(lubridate)

#dataset load
dataset <- read_csv("images.csv")
head(dataset)

glimpse(dataset)

Rows: 5,017
Columns: 30
$ project_id              <dbl> 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 200350…
$ deployment_id           <chr> "dfdb6f1c-9d8d-4d1f-86aa-7692f9c3d51a", "TZA-001-D0169", "e221a522-0668-4c7f-b…
$ image_id                <chr> "514a68e6-776e-455f-8848-9f8f3a51071c", "478f8b7a-d1c1-4bad-9d6c-c8978a4d4915"…
$ sequence_id             <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ filename                <chr> "TZA-001-D0001-I000027", "TZA-001-D0169-I003880", "TZA-001-D0039-I001538", "TZ…
$ location                <chr> "https://app.wildlifeinsights.org/download/2016630/project/2003500/data-files/…
$ is_blank                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ identified_by           <chr> "F. Rovero - Batch Upload", "F. Rovero - Batch Upload", "F. Rovero - Batch Upl…
$ wi_taxon_id             <chr> "7b40cf9f-0dae-431d-a541-7d465845ff97", "1bec402e-f98b-440c-bdf3-9ac196403fbb"…
$ class                   <chr> "Mammalia", "Mammalia", "Mammalia", "Mammalia", NA, "Mammalia", "Mammalia", "M…
$ order                   <chr> "Cetartiodactyla", "Cetartiodactyla", "Cetartiodactyla", "Cetartiodactyla", NA…
$ family                  <chr> "Bovidae", "Bovidae", "Bovidae", "Bovidae", NA, "Bovidae", "Bovidae", "Bovidae…
$ genus                   <chr> "Nesotragus", "Cephalophus", "Nesotragus", "Cephalophus", NA, "Nesotragus", "C…
$ species                 <chr> "moschatus", "harveyi", "moschatus", "harveyi", NA, "moschatus", "harveyi", "h…
$ common_name             <chr> "Suni", "Harvey's Duiker", "Suni", "Harvey's Duiker", "Animal", "Suni", "Harve…
$ uncertainty             <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ timestamp               <dttm> 2003-12-23 07:19:00, 2006-11-15 08:23:00, 2005-02-13 13:46:00, 2004-11-22 10:…
$ age                     <chr> "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "…
$ sex                     <chr> "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "…
$ animal_recognizable     <lgl> TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, …
$ individual_id           <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ number_of_objects       <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ individual_animal_notes <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ behavior                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ highlighted             <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, F…
$ markings                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ cv_confidence           <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ license                 <chr> "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY…
$ fuzzed                  <lgl> TRUE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, F…
$ deployment_fuzzed       <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, F…

names(dataset)

 [1] "project_id"              "deployment_id"           "image_id"                "sequence_id"            
 [5] "filename"                "location"                "is_blank"                "identified_by"          
 [9] "wi_taxon_id"             "class"                   "order"                   "family"                 
[13] "genus"                   "species"                 "common_name"             "uncertainty"            
[17] "timestamp"               "age"                     "sex"                     "animal_recognizable"    
[21] "individual_id"           "number_of_objects"       "individual_animal_notes" "behavior"               
[25] "highlighted"             "markings"                "cv_confidence"           "license"                
[29] "fuzzed"                  "deployment_fuzzed"      

dim(dataset)

[1] 5017   30

glimpse(dataset)

Rows: 5,017
Columns: 30
$ project_id              <dbl> 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 2003500, 200350…
$ deployment_id           <chr> "dfdb6f1c-9d8d-4d1f-86aa-7692f9c3d51a", "TZA-001-D0169", "e221a522-0668-4c7f-b…
$ image_id                <chr> "514a68e6-776e-455f-8848-9f8f3a51071c", "478f8b7a-d1c1-4bad-9d6c-c8978a4d4915"…
$ sequence_id             <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ filename                <chr> "TZA-001-D0001-I000027", "TZA-001-D0169-I003880", "TZA-001-D0039-I001538", "TZ…
$ location                <chr> "https://app.wildlifeinsights.org/download/2016630/project/2003500/data-files/…
$ is_blank                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ identified_by           <chr> "F. Rovero - Batch Upload", "F. Rovero - Batch Upload", "F. Rovero - Batch Upl…
$ wi_taxon_id             <chr> "7b40cf9f-0dae-431d-a541-7d465845ff97", "1bec402e-f98b-440c-bdf3-9ac196403fbb"…
$ class                   <chr> "Mammalia", "Mammalia", "Mammalia", "Mammalia", NA, "Mammalia", "Mammalia", "M…
$ order                   <chr> "Cetartiodactyla", "Cetartiodactyla", "Cetartiodactyla", "Cetartiodactyla", NA…
$ family                  <chr> "Bovidae", "Bovidae", "Bovidae", "Bovidae", NA, "Bovidae", "Bovidae", "Bovidae…
$ genus                   <chr> "Nesotragus", "Cephalophus", "Nesotragus", "Cephalophus", NA, "Nesotragus", "C…
$ species                 <chr> "moschatus", "harveyi", "moschatus", "harveyi", NA, "moschatus", "harveyi", "h…
$ common_name             <chr> "Suni", "Harvey's Duiker", "Suni", "Harvey's Duiker", "Animal", "Suni", "Harve…
$ uncertainty             <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ timestamp               <dttm> 2003-12-23 07:19:00, 2006-11-15 08:23:00, 2005-02-13 13:46:00, 2004-11-22 10:…
$ age                     <chr> "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "…
$ sex                     <chr> "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "…
$ animal_recognizable     <lgl> TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, …
$ individual_id           <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ number_of_objects       <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ individual_animal_notes <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ behavior                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ highlighted             <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, F…
$ markings                <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ cv_confidence           <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ license                 <chr> "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY", "CC-BY…
$ fuzzed                  <lgl> TRUE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, F…
$ deployment_fuzzed       <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, F…

colSums(is.na(dataset))

             project_id           deployment_id                image_id             sequence_id 
                      0                       0                      16                    5017 
               filename                location                is_blank           identified_by 
                      0                      16                    5017                       0 
            wi_taxon_id                   class                   order                  family 
                      0                      28                      52                     126 
                  genus                 species             common_name             uncertainty 
                    137                     167                       6                    5017 
              timestamp                     age                     sex     animal_recognizable 
                      0                       0                       0                       0 
          individual_id       number_of_objects individual_animal_notes                behavior 
                   5017                       0                    5017                    5017 
            highlighted                markings           cv_confidence                 license 
                      0                    5017                    5017                       0 
                 fuzzed       deployment_fuzzed 
                      0                       0 

#dataset 2 deployments
dataset2 <- read_csv("deployments.csv")

#selecting columns
dat_names <- dataset %>% select(filename, deployment_id, common_name, timestamp)

#selecting columns from dataset2
dat_names2 <- dataset2 %>% select(deployment_id, longitude, latitude)

#rows in dataset
nrow(dataset)

[1] 5017

summary(dataset)

   project_id      deployment_id        image_id         sequence_id      filename           location        
 Min.   :2003500   Length:5017        Length:5017        Mode:logical   Length:5017        Length:5017       
 1st Qu.:2003500   Class :character   Class :character   NA's:5017      Class :character   Class :character  
 Median :2003500   Mode  :character   Mode  :character                  Mode  :character   Mode  :character  
 Mean   :2003500                                                                                             
 3rd Qu.:2003500                                                                                             
 Max.   :2003500                                                                                             
 is_blank       identified_by      wi_taxon_id           class              order              family         
 Mode:logical   Length:5017        Length:5017        Length:5017        Length:5017        Length:5017       
 NA's:5017      Class :character   Class :character   Class :character   Class :character   Class :character  
                Mode  :character   Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                                                              
                                                                                                              
                                                                                                              
    genus             species          common_name        uncertainty      timestamp                  
 Length:5017        Length:5017        Length:5017        Mode:logical   Min.   :2003-12-15 07:05:00  
 Class :character   Class :character   Class :character   NA's:5017      1st Qu.:2004-11-23 00:00:00  
 Mode  :character   Mode  :character   Mode  :character                  Median :2005-12-22 03:41:00  
                                                                         Mean   :2006-06-18 13:08:16  
                                                                         3rd Qu.:2007-07-26 18:40:00  
                                                                         Max.   :2009-11-23 10:53:00  
     age                sex            animal_recognizable individual_id  number_of_objects
 Length:5017        Length:5017        Mode:logical        Mode:logical   Min.   : 1.000   
 Class :character   Class :character   TRUE:5017           NA's:5017      1st Qu.: 1.000   
 Mode  :character   Mode  :character                                      Median : 1.000   
                                                                          Mean   : 1.037   
                                                                          3rd Qu.: 1.000   
                                                                          Max.   :10.000   
 individual_animal_notes behavior       highlighted     markings       cv_confidence    license         
 Mode:logical            Mode:logical   Mode :logical   Mode:logical   Mode:logical   Length:5017       
 NA's:5017               NA's:5017      FALSE:5017      NA's:5017      NA's:5017      Class :character  
                                                                                      Mode  :character  
                                                                                                        
                                                                                                        
                                                                                                        
   fuzzed        deployment_fuzzed
 Mode :logical   Mode :logical    
 FALSE:2173      FALSE:5017       
 TRUE :2844                       
                                  
                                  
                                  

#removing void longitude
deployments <- dat_names2%>%filter(longitude != 38)
dat_names3 <- dat_names%>%filter(deployment_id != 'TZA-001')

#keep values only with TZA-001 to match
library(dplyr)
dat_names_cleaned <- dat_names %>%
  filter(grepl("^TZA-001", deployment_id, ignore.case = TRUE))


#mean median mode
dat_names_cleaned%>%group_by(common_name)%>%summarise(N = n())->dataset_grouped

#joins
new_data <- merge(deployments, dat_names_cleaned, by = "deployment_id")
all_data <- merge(new_data, dataset_grouped, by = "common_name")
#extracting date data
all_data%>%mutate(Date = as_date(timestamp))->full_data
#joins
dated_data <- merge(dataset_grouped, full_data, by = "common_name")

#just antelopes

library(dplyr)
antelopes_only <- dataset_grouped %>% filter(common_name %in% c("Blue Duiker", "Bushbuck", "Harvey's Duiker", "Suni"))
write.csv(antelopes_only, "antelopes_only_fr.csv", row.names = FALSE)

#only antelopes density

antelopes_filtered <-full_data %>%
  filter(common_name %in% c("Blue Duiker", "Bushbuck", "Harvey's Duiker", "Suni"))

ggplot(antelopes_filtered, aes(x = N, fill = common_name, colour = common_name))+
  geom_density(alpha = 0.5)+
  labs(title = "Density Plot of Antelope Species in the Study",
       x = "Population of Antelope",
       y = "Density Observed")+
  theme_minimal()

#LINE PLOTS FOR DEPLOYMENT
#NEW CODE FOR GLM INFORMATION
images <- read_csv("images.csv")

# Confirm exact species names
images %>%
  count(common_name, sort = TRUE)

# Filter focal species and count detections per deployment
species_counts <- images %>%
  filter(common_name %in% c(
    "Harvey's Duiker",
    "Suni",
    "Bushbuck",
    "Blue Duiker"
  )) %>%
  count(deployment_id, common_name, name = "occurences")

#CONTINUED FOR LINE PLOTS
#NEW CODE FOR GLM
#keep values only with TZA-001 to match
library(dplyr)
dat_names_cleaned <- species_counts %>%
  filter(grepl("^TZA-001", deployment_id, ignore.case = TRUE))

#CONTINUING FOR LINE PLOTS
#NEW CODE FOR GLM
library(tidyverse)
library(lubridate)

species_wide <- dat_names_cleaned %>%
  tidyr::pivot_wider(
    names_from  = common_name,
    values_from = occurences,
    values_fill = 0
  ) %>%
  rename(
    harveys_duiker = `Harvey's Duiker`,
    suni           = `Suni`,
    bushbuck       = `Bushbuck`,
    blue_duiker    = `Blue Duiker`
  )

glimpse(species_wide)

Rows: 92
Columns: 5
$ deployment_id  <chr> "TZA-001-D0005", "TZA-001-D0010", "TZA-001-D0019", "TZA-001-D0025", "TZA-001-D0031", "T…
$ harveys_duiker <int> 10, 5, 26, 9, 4, 4, 1, 0, 21, 2, 5, 8, 1, 0, 3, 0, 0, 1, 1, 2, 0, 1, 1, 1, 3, 2, 0, 0, …
$ suni           <int> 4, 0, 4, 4, 0, 1, 0, 0, 1, 0, 4, 6, 0, 0, 0, 2, 0, 0, 0, 0, 1, 0, 1, 0, 2, 0, 2, 3, 1, …
$ blue_duiker    <int> 0, 0, 0, 0, 0, 4, 1, 1, 0, 0, 0, 0, 1, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
$ bushbuck       <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …

#CONTINUING FOR LINE PLOTS

library(tidyverse)

species_long <- species_wide %>%
  pivot_longer(
    cols = c(harveys_duiker, suni, bushbuck, blue_duiker),
    names_to = "species",
    values_to = "count"
  )

glimpse(species_long)

Rows: 368
Columns: 3
$ deployment_id <chr> "TZA-001-D0005", "TZA-001-D0005", "TZA-001-D0005", "TZA-001-D0005", "TZA-001-D0010", "TZ…
$ species       <chr> "harveys_duiker", "suni", "bushbuck", "blue_duiker", "harveys_duiker", "suni", "bushbuck…
$ count         <int> 10, 4, 0, 0, 5, 0, 0, 0, 26, 4, 0, 0, 9, 4, 0, 0, 4, 0, 0, 0, 4, 1, 0, 4, 1, 0, 0, 1, 0,…

#CONTINUING FOR LINE PLOTS

library(tidyverse)

ggplot(
  species_long,
  aes(x = deployment_id, y = count, group = species, colour = species)
) +
  geom_line() +
  geom_point() +
  facet_wrap(
    ~ species,
    ncol = 1,
    scales = "free_y",
    labeller = labeller(
      species = c(
        harveys_duiker = "Harvey’s Duiker",
        suni           = "Suni",
        bushbuck       = "Bushbuck",
        blue_duiker    = "Blue Duiker"
      )
    )
  ) +
  scale_colour_manual(values = c(
    harveys_duiker = "dodgerblue",
    suni           = "purple",
    bushbuck       = "olivedrab",
    blue_duiker    = "tomato"
  )) +
  labs(
    title = "Detections Across Deployments by Species",
    y = "Number of Detections",
    x = "Deployments"
  ) +
  theme(
    axis.text.x  = element_blank(),   # removes TZA-001 labels
    axis.ticks.x = element_blank(),   # removes tick marks
    legend.position = "none"          # legend unnecessary with facets
  )

#TILE PLOTS

#ratio (antelope / per harvey)


compare_long_ratio <- species_wide %>%
  transmute(
    deployment_id,
    Suni         = (suni + 1) / (harveys_duiker + 1),
    Bushbuck     = (bushbuck + 1) / (harveys_duiker + 1),
    `Blue Duiker`= (blue_duiker + 1) / (harveys_duiker + 1)
  ) %>%
  pivot_longer(cols = -deployment_id, names_to = "species", values_to = "ratio")

ggplot(compare_long_ratio, aes(x = deployment_id, y = 1, fill = ratio)) +
  geom_tile(color = "gray") +
  facet_wrap(~ species, ncol = 1) +
  scale_fill_viridis_c() +
  labs(
    title = "Detection Ratio Compared to Harvey's Duiker (Species/Harvey's, +1 smoothing)",
    x = "Deployment",
    y = NULL,
    fill = "Ratio"
  ) +
  theme(
    axis.text.y  = element_blank(),
    axis.ticks.y = element_blank(),
    axis.text.x  = element_blank(),
    axis.ticks.x = element_blank()
  )

#CODE FOR POLYGON -> USED TO MAP STUDY AREA IN ARCGIS

#CREATING POLYGON WITH COORDINATES

library(sf)

#CONVERT POINTS TO POLYGON

points_df <- data.frame(
  lon = c(36.31811, 41.15940,41.99961, 37.67042),
  lat = c(-8.080697, -8.693828,-8.386151, -3.568570)
)

library(sf)

#CONVERT TO POLYGON
 coords <- as.matrix(points_df)
coords_closed <- rbind(coords, coords[1, ])

polygon_geom <- st_polygon(list(coords_closed))

#CONVERT TO SF

polygon_sf <- st_sf(
  geometry = st_sfc(polygon_geom),
  crs = 4326
)

#PLOT IN R
plot(polygon_sf, col = "lightblue", border = "black")