From 2316c845c7af2fd1d2c86636e492e3db163eef57 Mon Sep 17 00:00:00 2001
From: Francesco Sabatini <francesco.sabatini@idiv.de>
Date: Wed, 18 Mar 2020 12:26:27 +0100
Subject: [PATCH] Added code to exclude unreliable plots from Canada - Not
 knitted!

---
 code/04_buildHeader.Rmd | 24 ++++++++++++++++++++----
 code/06_buildDT.Rmd     |  8 ++++++++
 2 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/code/04_buildHeader.Rmd b/code/04_buildHeader.Rmd
index 4e09436..6228c22 100644
--- a/code/04_buildHeader.Rmd
+++ b/code/04_buildHeader.Rmd
@@ -6,11 +6,12 @@ output: html_document
 ---
 
 
-
 <center>
   ![](/data/sPlot/users/Francesco/_sPlot_Management/splot-long-rgb.png "sPlot Logo")
 </center>
 
+MEMO : Exclude plots from CANADA and adjust DT2, CWMs & SoilClim (at the moment code is here, but eval=F)  
+\newline
   
 **Timestamp:** `r date()`  
 **Drafted:** Francesco Maria Sabatini  
@@ -96,7 +97,7 @@ header0 <- readr::read_delim("../sPlot_data_export/sPlot_3_0_2_header_test.csv",
   COMMUNITY = col_character(),
   SUBSTRATE = col_character(),
   Locality = col_character(),
-  ORIG_NUM = col_double(),
+  ORIG_NUM = col_character(),
   ALLIAN_REV = col_character(),
   REV_AUTHOR = col_character(),
   Forest = col_logical(),
@@ -133,10 +134,25 @@ The following column names occurred in the header of sPlot v2.1 and are currentl
 10. POINT_X  
 11. POINT_Y  
 ~~
-Columns #1, #2, #3, #10, #11 will be dropped. The others will be derived below.
+Columns #1, #2, #3, #10, #11 will be dropped. The others will be derived below.  
+
+
+### 1.1 Exclude unreliable plots
+Some canadian plots need to be removed, on indication of [Laura Boisvert-Marsh](laura.boisvert-marsh@canada.ca) from GIVD NA-CA-004. The plots (and corresponding `PlotObservationID`) are:  
+\newline
+
+Fabot01 - 1707776  
+Fadum01, 02 & 03 - 1707779:1707781  
+Faers01 - 1707782  
+Pfe-f-08 - 1707849  
+Pfe-o-05- 1707854  
+```{r, eval=F}
+header0 <- header0 %>% 
+  filter(PlotObservationID != c(1707776, 1707779:1707782, 1707849, 1707854))
+```
 
 
-### 1.1 Solve spatial problems
+### 1.2 Solve spatial problems
 There are 2020 plots in the Nile dataset without spatial coordinates. Assign manually with wide (90km) location uncertainty.
 ```{r}
 header <- header0 %>% 
diff --git a/code/06_buildDT.Rmd b/code/06_buildDT.Rmd
index d8eeab1..876ab29 100644
--- a/code/06_buildDT.Rmd
+++ b/code/06_buildDT.Rmd
@@ -67,6 +67,14 @@ DT0 <- readr::read_delim("../sPlot_data_export/sPlot_3_0_2_species_test.csv",
 nplots <- length(unique(DT0$PlotObservationID))
 nspecies <- length(unique(DT0$`Matched concept`))
 ```
+Match plots with those in `header`
+```{r}
+load("../_output/header_sPlot3.0.RData")
+DT0 <- DT0 %>% 
+  filter(PlotObservationID %in% unique(header$PlotObservationID))
+```
+
+
 Species data include `r nrow(DT0)` species * plot records, across `r nplots` plots. Before taxonomic resolution, there are `r nspecies` species .  
 \newline
 
-- 
GitLab