bugfix docsb2b

docs/literate/explanations/b2b_why.jl

@@ -4,15 +4,15 @@ using UnfoldSim
 using UnfoldDecode
 using DataFrames
 using Statistics
-include("../../example_rename_events.jl")
+include("../../../example_rename_events.jl")
 
 #
 # # [Motivation for BacktoBack](@id explainer-b2b)
 # ## Introduction
 
 # “Back-to-Back” regression (B2B) is an approach to estimate the decoding performance from a set of correlated factors.
 # Why do we need this? Let's have a look at a simple example:
-# ![My Image](pic/dog_and_cat.png)
+# ![My Image](assets/dog_and_cat.png)
 #
 # Imagine we record EEG data from an eyetracking experiment, and investigate each fixation (a resting period of the eye) as an event for an ERP.
 # Imagine, we have both cats and dogs, but that we also make large and small eye-movements.
@@ -27,10 +27,10 @@ evts = example_rename_events(evts)
 # To make the example more impressive, let's add an orthogonal variable `vegetable`. But this variable is special:
 # It is correlated with the covariate `eye_movement_size`.
 evts.vegetable .=
-    ["tomato", "carrot"][1 .+ (evts.eye_movement_size.+10 .* rand(size(evts, 1)).>7.5)];
+    ["tomato", "carrot"][1 .+ (evts.eye_movement_size .+ 10 .* rand(size(evts, 1)) .> 7.5)];
 cor(evts.eye_movement_size, evts.vegetable .== "carrot")
 
-# ![My Image](pic/dog_and_cat_and_vegetable.png)
+# ![My Image](assets/dog_and_cat_and_vegetable.png)
 
 # Summarized, we have three independent variables: `animal`, `eye_movement_size`, and `vegetable`, with the latter two being correlated.
 
@@ -57,7 +57,7 @@ function run_b2b(f)
 
     results = coeftable(m)
     results.estimate = abs.(results.estimate)
-    results = results[results.coefname.!="(Intercept)", :]
+    results = results[results.coefname .!= "(Intercept)", :]
     results.formula .= string(f)
     return results
 end;