Update README.md

README.md

@@ -36,41 +36,3 @@ library(fingerPro)
 #AG (cropland)
 #PI and PI1 (Pine forest, at first looks different but when you display de LDA plot you will see that the wisher decision in join both pines as the same source)
 #SS (subsoil)
-data <- catchment
-boxPlot(data, columns = 1:6, ncol = 3)
-correlationPlot(data, columns = 1:5, mixtures = T)
-LDAPlot(data, P3D=FALSE)
-#variables are collinear
-#select the optimum set of tracers by implementing the statistical tests 
-data <- rangeTest(data)
-data <- KWTest(data)
-data <- DFATest(data)
-#Check how the selected tracers discriminate between sources
-LDAPlot(data, P3D=F)
-LDAPlot(data, P3D=T)
-#2D and 3D LDAPlots suggest that two of the sources have to be combined
-#reload the original dataset "catchment"
-data <- catchment
-# Combine sources PI1 and PI based on the previous LDAPlot
-data$Land_Use[data$Land_Use == 'PI1'] <- 'PI'
-#select the optimum set of tracers by implementing the statistical tests 
-data <- rangeTest(data)
-data <- KWTest(data)
-data <- DFATest(data)
-LDAPlot(data, P3D=F)
-#Now the optimum tracer properties selected show a good discrimination, so proceed with the unmix function
-``` 
-![lda comparisson](https://user-images.githubusercontent.com/30837036/43969407-535dab0c-9cca-11e8-8c3d-18fbc3048fb0.png)
-```r
-# Figure a) LDAPlot previous to PI1+PI fusion. b) LDAPlot after the fusion of both pines
-result <- unmix(data, samples = 100L, iter =100L)
-#Display the results
-plotResults(result, y_high = 5, n = 1)
-```
-
-![results](https://user-images.githubusercontent.com/30837036/43969666-2ebd7a1a-9ccb-11e8-8d71-445ad2e15daa.png)
-```r
-    id   GOF.mean     GOF.SD    AG.mean      AG.SD    PI.mean      PI.SD    SS.mean      SS.SD
-  42744 0.94430071 0.03681212  0.18148918  0.061388  0.4726643   0.0785878  0.3458461  0.0654922
-
-```