diff --git a/2-Regression/3-Linear/solution/Notebook_Julia_Editing_Linear_Regression.ipynb b/2-Regression/3-Linear/solution/Notebook_Julia_Editing_Linear_Regression.ipynb
deleted file mode 100644
index 36473d387..000000000
--- a/2-Regression/3-Linear/solution/Notebook_Julia_Editing_Linear_Regression.ipynb
+++ /dev/null
@@ -1,2500 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Linear Regression using Julia \n",
- "\n",
- "In this notebook, I presented Julia version of the solutions, Here I have used Linear Regression on Boston dataset, This notebook does not contain polynomial regression part, because It is still in progress. "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 57,
- "metadata": {},
- "outputs": [],
- "source": [
- "# import Pkg\n",
- "# Pkg.add(\"Plots\")\n",
- "# Pkg.add(\"Lathe\")\n",
- "# Pkg.add(\"GLM\")\n",
- "# Pkg.add(\"StatsPlots\")\n",
- "# Pkg.add(\"MLBase\")\n",
- "# Pkg.add(\"Metrics\") \n",
- "\n",
- "# Uncomment this if you haven't installed the above libraries "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# packages we will use \n",
- "using Plots\n",
- "using Lathe\n",
- "using GLM\n",
- "using Statistics\n",
- "using StatsPlots\n",
- "using MLBase \n",
- "using Metrics \n",
- "using DataFrames, CSV\n",
- "using Polynomials"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {
- "scrolled": true
- },
- "outputs": [
- {
- "data": {
- "text/html": [
- "
5 rows × 14 columns (omitted printing of 5 columns)
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD |
|---|
| Float64 | Float64 | Float64 | Float64 | Float64 | Float64 | Float64 | Float64 | Float64 |
|---|
| 1 | 0.00632 | 18.0 | 2.31 | 0.0 | 0.538 | 6.575 | 65.2 | 4.09 | 1.0 |
|---|
| 2 | 0.02731 | 0.0 | 7.07 | 0.0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2.0 |
|---|
| 3 | 0.02729 | 0.0 | 7.07 | 0.0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2.0 |
|---|
| 4 | 0.03237 | 0.0 | 2.18 | 0.0 | 0.458 | 6.998 | 45.8 | 6.0622 | 3.0 |
|---|
| 5 | 0.06905 | 0.0 | 2.18 | 0.0 | 0.458 | 7.147 | 54.2 | 6.0622 | 3.0 |
|---|
"
- ],
- "text/latex": [
- "\\begin{tabular}{r|cccccccccc}\n",
- "\t& CRIM & ZN & INDUS & CHAS & NOX & RM & AGE & DIS & RAD & \\\\\n",
- "\t\\hline\n",
- "\t& Float64 & Float64 & Float64 & Float64 & Float64 & Float64 & Float64 & Float64 & Float64 & \\\\\n",
- "\t\\hline\n",
- "\t1 & 0.00632 & 18.0 & 2.31 & 0.0 & 0.538 & 6.575 & 65.2 & 4.09 & 1.0 & $\\dots$ \\\\\n",
- "\t2 & 0.02731 & 0.0 & 7.07 & 0.0 & 0.469 & 6.421 & 78.9 & 4.9671 & 2.0 & $\\dots$ \\\\\n",
- "\t3 & 0.02729 & 0.0 & 7.07 & 0.0 & 0.469 & 7.185 & 61.1 & 4.9671 & 2.0 & $\\dots$ \\\\\n",
- "\t4 & 0.03237 & 0.0 & 2.18 & 0.0 & 0.458 & 6.998 & 45.8 & 6.0622 & 3.0 & $\\dots$ \\\\\n",
- "\t5 & 0.06905 & 0.0 & 2.18 & 0.0 & 0.458 & 7.147 & 54.2 & 6.0622 & 3.0 & $\\dots$ \\\\\n",
- "\\end{tabular}\n"
- ],
- "text/plain": [
- "\u001b[1m5×14 DataFrame\u001b[0m\n",
- "\u001b[1m Row \u001b[0m│\u001b[1m CRIM \u001b[0m\u001b[1m ZN \u001b[0m\u001b[1m INDUS \u001b[0m\u001b[1m CHAS \u001b[0m\u001b[1m NOX \u001b[0m\u001b[1m RM \u001b[0m\u001b[1m AGE \u001b[0m\u001b[1m DIS \u001b[0m\u001b[1m\u001b[0m ⋯\n",
- "\u001b[1m \u001b[0m│\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m\u001b[0m ⋯\n",
- "─────┼──────────────────────────────────────────────────────────────────────────\n",
- " 1 │ 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.09 ⋯\n",
- " 2 │ 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671\n",
- " 3 │ 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671\n",
- " 4 │ 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622\n",
- " 5 │ 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 ⋯\n",
- "\u001b[36m 6 columns omitted\u001b[0m"
- ]
- },
- "execution_count": 11,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# loading the data \n",
- "\n",
- "df = CSV.read(\"data\\\\out.csv\", DataFrame)\n",
- "first(df,5)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "(506, 14)\n"
- ]
- }
- ],
- "source": [
- "# printing the size of the data \n",
- "\n",
- "println(size(df))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "14 rows × 7 columns
| variable | mean | min | median | max | nmissing | eltype |
|---|
| Symbol | Float64 | Float64 | Float64 | Float64 | Int64 | DataType |
|---|
| 1 | CRIM | 3.61352 | 0.00632 | 0.25651 | 88.9762 | 0 | Float64 |
|---|
| 2 | ZN | 11.3636 | 0.0 | 0.0 | 100.0 | 0 | Float64 |
|---|
| 3 | INDUS | 11.1368 | 0.46 | 9.69 | 27.74 | 0 | Float64 |
|---|
| 4 | CHAS | 0.06917 | 0.0 | 0.0 | 1.0 | 0 | Float64 |
|---|
| 5 | NOX | 0.554695 | 0.385 | 0.538 | 0.871 | 0 | Float64 |
|---|
| 6 | RM | 6.28463 | 3.561 | 6.2085 | 8.78 | 0 | Float64 |
|---|
| 7 | AGE | 68.5749 | 2.9 | 77.5 | 100.0 | 0 | Float64 |
|---|
| 8 | DIS | 3.79504 | 1.1296 | 3.20745 | 12.1265 | 0 | Float64 |
|---|
| 9 | RAD | 9.54941 | 1.0 | 5.0 | 24.0 | 0 | Float64 |
|---|
| 10 | TAX | 408.237 | 187.0 | 330.0 | 711.0 | 0 | Float64 |
|---|
| 11 | PTRATIO | 18.4555 | 12.6 | 19.05 | 22.0 | 0 | Float64 |
|---|
| 12 | B | 356.674 | 0.32 | 391.44 | 396.9 | 0 | Float64 |
|---|
| 13 | LSTAT | 12.6531 | 1.73 | 11.36 | 37.97 | 0 | Float64 |
|---|
| 14 | SalePrice | 22.5328 | 5.0 | 21.2 | 50.0 | 0 | Float64 |
|---|
"
- ],
- "text/latex": [
- "\\begin{tabular}{r|ccccccc}\n",
- "\t& variable & mean & min & median & max & nmissing & eltype\\\\\n",
- "\t\\hline\n",
- "\t& Symbol & Float64 & Float64 & Float64 & Float64 & Int64 & DataType\\\\\n",
- "\t\\hline\n",
- "\t1 & CRIM & 3.61352 & 0.00632 & 0.25651 & 88.9762 & 0 & Float64 \\\\\n",
- "\t2 & ZN & 11.3636 & 0.0 & 0.0 & 100.0 & 0 & Float64 \\\\\n",
- "\t3 & INDUS & 11.1368 & 0.46 & 9.69 & 27.74 & 0 & Float64 \\\\\n",
- "\t4 & CHAS & 0.06917 & 0.0 & 0.0 & 1.0 & 0 & Float64 \\\\\n",
- "\t5 & NOX & 0.554695 & 0.385 & 0.538 & 0.871 & 0 & Float64 \\\\\n",
- "\t6 & RM & 6.28463 & 3.561 & 6.2085 & 8.78 & 0 & Float64 \\\\\n",
- "\t7 & AGE & 68.5749 & 2.9 & 77.5 & 100.0 & 0 & Float64 \\\\\n",
- "\t8 & DIS & 3.79504 & 1.1296 & 3.20745 & 12.1265 & 0 & Float64 \\\\\n",
- "\t9 & RAD & 9.54941 & 1.0 & 5.0 & 24.0 & 0 & Float64 \\\\\n",
- "\t10 & TAX & 408.237 & 187.0 & 330.0 & 711.0 & 0 & Float64 \\\\\n",
- "\t11 & PTRATIO & 18.4555 & 12.6 & 19.05 & 22.0 & 0 & Float64 \\\\\n",
- "\t12 & B & 356.674 & 0.32 & 391.44 & 396.9 & 0 & Float64 \\\\\n",
- "\t13 & LSTAT & 12.6531 & 1.73 & 11.36 & 37.97 & 0 & Float64 \\\\\n",
- "\t14 & SalePrice & 22.5328 & 5.0 & 21.2 & 50.0 & 0 & Float64 \\\\\n",
- "\\end{tabular}\n"
- ],
- "text/plain": [
- "\u001b[1m14×7 DataFrame\u001b[0m\n",
- "\u001b[1m Row \u001b[0m│\u001b[1m variable \u001b[0m\u001b[1m mean \u001b[0m\u001b[1m min \u001b[0m\u001b[1m median \u001b[0m\u001b[1m max \u001b[0m\u001b[1m nmissing \u001b[0m\u001b[1m eltype\u001b[0m ⋯\n",
- "\u001b[1m \u001b[0m│\u001b[90m Symbol \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Float64 \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m DataTy\u001b[0m ⋯\n",
- "─────┼──────────────────────────────────────────────────────────────────────────\n",
- " 1 │ CRIM 3.61352 0.00632 0.25651 88.9762 0 Float6 ⋯\n",
- " 2 │ ZN 11.3636 0.0 0.0 100.0 0 Float6\n",
- " 3 │ INDUS 11.1368 0.46 9.69 27.74 0 Float6\n",
- " 4 │ CHAS 0.06917 0.0 0.0 1.0 0 Float6\n",
- " 5 │ NOX 0.554695 0.385 0.538 0.871 0 Float6 ⋯\n",
- " 6 │ RM 6.28463 3.561 6.2085 8.78 0 Float6\n",
- " 7 │ AGE 68.5749 2.9 77.5 100.0 0 Float6\n",
- " 8 │ DIS 3.79504 1.1296 3.20745 12.1265 0 Float6\n",
- " 9 │ RAD 9.54941 1.0 5.0 24.0 0 Float6 ⋯\n",
- " 10 │ TAX 408.237 187.0 330.0 711.0 0 Float6\n",
- " 11 │ PTRATIO 18.4555 12.6 19.05 22.0 0 Float6\n",
- " 12 │ B 356.674 0.32 391.44 396.9 0 Float6\n",
- " 13 │ LSTAT 12.6531 1.73 11.36 37.97 0 Float6 ⋯\n",
- " 14 │ SalePrice 22.5328 5.0 21.2 50.0 0 Float6\n",
- "\u001b[36m 1 column omitted\u001b[0m"
- ]
- },
- "execution_count": 14,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# describing the data \n",
- "\n",
- "describe(df)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "14-element Vector{String}:\n",
- " \"CRIM\"\n",
- " \"ZN\"\n",
- " \"INDUS\"\n",
- " \"CHAS\"\n",
- " \"NOX\"\n",
- " \"RM\"\n",
- " \"AGE\"\n",
- " \"DIS\"\n",
- " \"RAD\"\n",
- " \"TAX\"\n",
- " \"PTRATIO\"\n",
- " \"B\"\n",
- " \"LSTAT\"\n",
- " \"SalePrice\""
- ]
- },
- "execution_count": 15,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# printing the names of the dataframe \n",
- "\n",
- "names(df)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/svg+xml": [
- "\n",
- "\n"
- ]
- },
- "execution_count": 22,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# boxplot for out target variable \n",
- "\n",
- "boxplot(df.SalePrice, title = \"Box Plot - SalePrice\", ylabel = \"CRIM\", legend = false)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/svg+xml": [
- "\n",
- "