Julia Dataframes

import Pkg; Pkg.add(["CSV","CategoricalArrays", "Chain", "DataFrames", "GLM", "Plots", "Random", "StatsPlots", "Statistics","Interact", "Blink"])

using CSV using CategoricalArrays using Chain using DataFrames using GLM using Plots using Random using StatsPlots using Statistics ENV["LINES"] = 20 # to limit nuber of rows. ENV["COLUMNS"] = 20 # to limit number of columns

ENV["LINES"] = 20 ENV["COLUMNS"] = 1000

df_raw = CSV.read("/work/Data/Heart Disease Dataset.csv", DataFrame)

size(df_raw)

describe(df_raw)

df = select(df_raw,:age,:sex => categorical => :sex, Between(:cp, :chol), :fbs => categorical => :fbs,:restecg,:thalach, :exang => categorical => :exang, Between(:oldpeak,:thal), :target => categorical => :target )

@chain df_raw begin dropmissing groupby(:target) combine([:age, :sex, :chol, :restecg, :slope] .=> mean) end

@chain df_raw begin groupby(:target) combine(names(df, Real) .=> mean) end

@chain df_raw begin groupby([:target, :sex]) combine(nrow) end

@chain df_raw begin groupby([:target, :sex]) combine(nrow) unstack(:target, :sex, :nrow) end

gd = groupby(df_raw, :target)

gd[1]

@df df_raw corrplot(cols(1:6), grid = false)

@df df_raw violin(string.(:target), :chol, linewidth=0,label = "voilin") @df df_raw boxplot!(string.(:target), :chol, fillalpha=0.75, linewidth=2,label = "boxplot") @df df_raw dotplot!(string.(:target), :chol, marker=(:black, stroke(0)),label = "dotplot")

@df df_raw groupedhist(:chol, group = :target, bar_position = :dodge)

@df df_raw andrewsplot(:target, cols(1:4), legend = :topleft)

@df df density(:chol, group=:target)

probit = glm(@formula(target ~ trestbps + age + chol + thalach + oldpeak + slope + ca), df_raw, Binomial(), ProbitLink())

test_pred = predict(probit, test, interval=:confidence)

test.predict = test_pred.prediction; prob_pred = predict(probit, df_pred, interval=:confidence)

plot(df_pred.cp, Matrix(prob_pred),labels=["Predicted" "Lower" "Upper"], xlabel="cp", ylabel="Pr(lfp=1)")