started report

prep/Project.toml

@@ -2,5 +2,4 @@
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DataFramesMeta = "1313f7d8-7da2-5740-9ea0-a2ca25f37964"
-Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
-StatsPlots = "f3b207a7-027a-5e70-b257-86293d7955fd"
+PlotlyJS = "f0f68f2c-4968-5e81-91da-67840de0976a"

prep/prep.jl

@@ -2,13 +2,14 @@ using DataFrames
 using LinearAlgebra
 using CSV
 using DataFramesMeta
-using Plots
-using StatsPlots
+# using Plots
+# using StatsPlots
+using PlotlyJS
 
 begin
     df = CSV.read("compiled.csv", DataFrame)
 
-    df.bb_volume = df.bb_length .* df.bb_width .* df.bb_height
+    df.box = df.bb_length .* df.bb_width .* df.bb_height
 
 
     @eachrow! df begin
@@ -33,7 +34,7 @@ begin
     # Convert material to scalar
     begin
         kv = Dict(reverse.(enumerate(Set(df.material_name))))
-        mats = []
+        mats = [] |> Vector{Int}
         for material in df.material_name
             push!(mats, kv[material])
         end
@@ -41,20 +42,28 @@ begin
     end
 
     # Remove columns not needed for analysis
-    df = df[!, [:mass, :volume, :density, :area, :bb_volume, :Ibar]]
+    # df = df[!, [:mass, :volume, :density, :area, :bb_volume, :Ibar, :material_index]]
 
     # Remove outliers
-    df = df[df.bb_volume.<1e6, :]
+    df = df[df.box.<1e6, :]
     df = df[df.mass.<1000, :]
 end
 
-@df df cornerplot(cols(1:4), compact = true)
+# @df df cornerplot(cols(1:7), compact = true)
 
 # plot(df.mass)
 # histogram(df.mass)
-scatter(df.mass, df.volume)
+# scatter(df.mass, df.Ibar)
+
+features = [:mass, :volume, :density, :area, :box, :Ibar]
+
+plot(df, dimensions = features, kind = "splom", Layout(title = "Raw Data"))
+
+corner(df)
+
+CSV.write("prepped.csv", df)
 
 
-
-
-CSV.write("prepped.csv", df)
+df = dataset(DataFrame, "iris")
+features = [:sepal_width, :sepal_length, :petal_width, :petal_length]
+plot(df, dimensions = features, color = :species, kind = "splom")