update species lists

.gitignore

@@ -34,3 +34,6 @@ vignettes/*.pdf
 
 # Shiny token, see https://shiny.rstudio.com/articles/shinyapps.html
 rsconnect/
+
+# large file
+intermediate-data/hs_US_records_080421.csv

code/risk_score_analysis.R

@@ -164,13 +164,24 @@ mod2 <- update(mod1, .~. - Terrestrial)
 anova(mod1, mod2)
 # okay to remove terrestrial
 
+mod_summ <- tibble(Variable = "habitat (terrestrial vs. aquatic)",
+                   ChiSq = anova(mod1, mod2)[2, "LR stat."],
+                   df = anova(mod1, mod2)[2, "   df"],
+                   P = anova(mod1, mod2)[2, "Pr(Chi)"])
+
 summary(mod2)
 # counts are not sig
 
 mod3 <- update(mod2, .~. - countS)
 anova(mod2, mod3)
 # remove
 
+mod_summ2 <- mod_summ %>%
+  add_row(Variable = "records in US",
+          ChiSq = anova(mod2, mod3)[2, "LR stat."],
+          df = anova(mod2, mod3)[2, "   df"],
+          P = anova(mod2, mod3)[2, "Pr(Chi)"])
+
 summary(mod3)
 
 # test significance of each remaining
@@ -183,6 +194,21 @@ anova(mod3, mod5)
 mod6 <- update(mod3, .~. - earlYearS)
 anova(mod3, mod6)
 
+# model table
+mod_summ3 <- mod_summ2 %>%
+  add_row(Variable = "assessor",
+          ChiSq = anova(mod3, mod4)[2, "LR stat."],
+          df = anova(mod3, mod4)[2, "   df"],
+          P = anova(mod3, mod4)[2, "Pr(Chi)"]) %>%
+  add_row(Variable = "certainty",
+          ChiSq = anova(mod3, mod5)[2, "LR stat."],
+          df = anova(mod3, mod5)[2, "   df"],
+          P = anova(mod3, mod5)[2, "Pr(Chi)"]) %>%
+  add_row(Variable = "earliest US record",
+          ChiSq = anova(mod3, mod6)[2, "LR stat."],
+          df = anova(mod3, mod6)[2, "   df"],
+          P = anova(mod3, mod6)[2, "Pr(Chi)"])
+
 
 #### diagnostics ####
 

code/taxa_list_processing.R

@@ -1051,7 +1051,7 @@ syn_cabi10[!complete.cases(syn_cabi10),] %>%
 # some occurrences missing
 
 # save
-write_csv(syn_cabi10, "intermediate-data/horizon_scan_all_names_plant_list_011522")
+write_csv(syn_cabi10, "intermediate-data/horizon_scan_all_names_plant_list_011522.csv")
 
 # summarize
 acc_fin <- syn_cabi10 %>%
@@ -1068,9 +1068,11 @@ acc_fin <- syn_cabi10 %>%
               summarize(Atlas = as.numeric(sum(Atlas) > 0),
                         climate = as.numeric(sum(climate) > 0),
                         acc_name_source = paste(unique(acc_name_source), collapse = ", ")) %>%
-              ungroup())
+              ungroup()) %>%
+  select(acc_name, synonyms, acc_name_source, climate, Atlas, fl_nox, fed_nox, naturalized, weedy, occurrences, occurrences_new)
+
 # 2071 taxa
-write_csv(acc_fin, "intermediate-data/horizon_scan_accepted_names_plant_list_011522")
+write_csv(acc_fin, "intermediate-data/horizon_scan_accepted_names_plant_list_011522.csv")
 
 # check for missing values
 acc_fin[!complete.cases(acc_fin),] %>%