diff --git a/01_Coursera_4.ipynb b/01_Coursera_4.ipynb
index 033ba99..d784ac1 100644
--- a/01_Coursera_4.ipynb
+++ b/01_Coursera_4.ipynb
@@ -2,35 +2,23 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "4"
- ]
- },
- "execution_count": 1,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "+(2,2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "┌ Info: Recompiling stale cache file /home/eddie/.julia/compiled/v1.2/Plots/ld3vC.ji for Plots [91a5bcdd-55d7-5caf-9e0b-520d859cae80]\n",
- "└ @ Base loading.jl:1240\n"
+ "┌ Info: Precompiling Distributions [31c24e10-a181-5473-b8eb-7969acd0382f]\n",
+ "└ @ Base loading.jl:1242\n",
+ "┌ Info: Precompiling CSV [336ed68f-0bac-5ca0-87d4-7b16caf5d00b]\n",
+ "└ @ Base loading.jl:1242\n",
+ "┌ Info: Precompiling HypothesisTests [09f84164-cd44-5f33-b23f-e6b0d136a0d5]\n",
+ "└ @ Base loading.jl:1242\n",
+ "┌ Info: Recompiling stale cache file /Users/eddie/.julia/compiled/v1.2/Plots/ld3vC.ji for Plots [91a5bcdd-55d7-5caf-9e0b-520d859cae80]\n",
+ "└ @ Base loading.jl:1240\n",
+ "┌ Info: Precompiling GLM [38e38edf-8417-5370-95a0-9cbb8c7f171a]\n",
+ "└ @ Base loading.jl:1242\n"
]
}
],
@@ -46,15 +34,79 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "┌ Info: Recompiling stale cache file /home/eddie/.julia/compiled/v1.2/PyPlot/oatAj.ji for PyPlot [d330b81b-6aea-500a-939a-2ce795aea3ee]\n",
- "└ @ Base loading.jl:1240\n"
+ "┌ Info: Precompiling PyPlot [d330b81b-6aea-500a-939a-2ce795aea3ee]\n",
+ "└ @ Base loading.jl:1242\n",
+ "┌ Info: Installing matplotlib via the Conda matplotlib package...\n",
+ "└ @ PyCall /Users/eddie/.julia/packages/PyCall/zqDXB/src/PyCall.jl:697\n",
+ "┌ Info: Running `conda install -y matplotlib` in root environment\n",
+ "└ @ Conda /Users/eddie/.julia/packages/Conda/3rPhK/src/Conda.jl:113\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Collecting package metadata (current_repodata.json): ...working... done\n",
+ "Solving environment: ...working... done\n",
+ "\n",
+ "## Package Plan ##\n",
+ "\n",
+ " environment location: /Users/eddie/.julia/conda/3\n",
+ "\n",
+ " added / updated specs:\n",
+ " - matplotlib\n",
+ "\n",
+ "\n",
+ "The following packages will be downloaded:\n",
+ "\n",
+ " package | build\n",
+ " ---------------------------|-----------------\n",
+ " cycler-0.10.0 | py37_0 14 KB\n",
+ " freetype-2.9.1 | hb4e5f40_0 555 KB\n",
+ " kiwisolver-1.2.0 | py37h04f5b5a_0 55 KB\n",
+ " libpng-1.6.37 | ha441bb4_0 262 KB\n",
+ " matplotlib-3.1.3 | py37_0 21 KB\n",
+ " matplotlib-base-3.1.3 | py37h9aa3819_0 4.9 MB\n",
+ " pyparsing-2.4.7 | py_0 65 KB\n",
+ " python-dateutil-2.8.1 | py_0 215 KB\n",
+ " tornado-6.0.4 | py37h1de35cc_1 597 KB\n",
+ " ------------------------------------------------------------\n",
+ " Total: 6.7 MB\n",
+ "\n",
+ "The following NEW packages will be INSTALLED:\n",
+ "\n",
+ " cycler pkgs/main/osx-64::cycler-0.10.0-py37_0\n",
+ " freetype pkgs/main/osx-64::freetype-2.9.1-hb4e5f40_0\n",
+ " kiwisolver pkgs/main/osx-64::kiwisolver-1.2.0-py37h04f5b5a_0\n",
+ " libpng pkgs/main/osx-64::libpng-1.6.37-ha441bb4_0\n",
+ " matplotlib pkgs/main/osx-64::matplotlib-3.1.3-py37_0\n",
+ " matplotlib-base pkgs/main/osx-64::matplotlib-base-3.1.3-py37h9aa3819_0\n",
+ " pyparsing pkgs/main/noarch::pyparsing-2.4.7-py_0\n",
+ " python-dateutil pkgs/main/noarch::python-dateutil-2.8.1-py_0\n",
+ " tornado pkgs/main/osx-64::tornado-6.0.4-py37h1de35cc_1\n",
+ "\n",
+ "\n",
+ "\n",
+ "Downloading and Extracting Packages\n",
+ "cycler-0.10.0 | 14 KB | ########## | 100% \n",
+ "python-dateutil-2.8. | 215 KB | ########## | 100% \n",
+ "pyparsing-2.4.7 | 65 KB | ########## | 100% \n",
+ "tornado-6.0.4 | 597 KB | ########## | 100% \n",
+ "matplotlib-base-3.1. | 4.9 MB | ########## | 100% \n",
+ "freetype-2.9.1 | 555 KB | ########## | 100% \n",
+ "kiwisolver-1.2.0 | 55 KB | ########## | 100% \n",
+ "libpng-1.6.37 | 262 KB | ########## | 100% \n",
+ "matplotlib-3.1.3 | 21 KB | ########## | 100% \n",
+ "Preparing transaction: ...working... done\n",
+ "Verifying transaction: ...working... done\n",
+ "Executing transaction: ...working... done\n"
]
},
{
@@ -63,7 +115,7 @@
"Plots.PyPlotBackend()"
]
},
- "execution_count": 6,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -74,12 +126,1348 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
- "age = rand(18:80,100)\n"
+ "age = rand(18:80,100)\n",
+ "wcc = round.(rand(Distributions.Normal(12,2),100), digits=1)\n",
+ "crp = round.(Int, rand(Distributions.Chisq(4),100)) .* 10\n",
+ "treatment = rand([\"A\",\"B\"],100)\n",
+ "result = rand([\"Improved\", \"Static\", \"Worse\"],100);\n"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "49.91"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mean(age)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "50.0"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "median(age)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "16.537740737079798"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "std(age)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "12.105"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mean(wcc)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2.0415568925343583"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "std(wcc)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Summary Stats:\n",
+ "Length: 100\n",
+ "Missing Count: 0\n",
+ "Mean: 49.910000\n",
+ "Minimum: 18.000000\n",
+ "1st Quartile: 36.750000\n",
+ "Median: 50.000000\n",
+ "3rd Quartile: 62.250000\n",
+ "Maximum: 80.000000\n",
+ "Type: Int64\n"
+ ]
+ }
+ ],
+ "source": [
+ "StatsBase.describe(age)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Summary Stats:\n",
+ "Length: 100\n",
+ "Missing Count: 0\n",
+ "Mean: 12.105000\n",
+ "Minimum: 4.900000\n",
+ "1st Quartile: 11.075000\n",
+ "Median: 12.350000\n",
+ "3rd Quartile: 13.525000\n",
+ "Maximum: 16.100000\n",
+ "Type: Float64\n"
+ ]
+ }
+ ],
+ "source": [
+ "StatsBase.describe(wcc)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Summary Stats:\n",
+ "Length: 100\n",
+ "Missing Count: 0\n",
+ "Mean: 12.105000\n",
+ "Minimum: 4.900000\n",
+ "1st Quartile: 11.075000\n",
+ "Median: 12.350000\n",
+ "3rd Quartile: 13.525000\n",
+ "Maximum: 16.100000\n"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "StatsBase.summarystats(wcc)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = DataFrame(Age = age, WCC = wcc, CRP= crp, Treatment = treatment, Result = result);"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(100, 5)"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "size(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
6 rows × 5 columns
| 1 | 39 | 9.3 | 10 | A | Worse |
|---|
| 2 | 51 | 14.6 | 50 | A | Worse |
|---|
| 3 | 75 | 7.1 | 50 | A | Improved |
|---|
| 4 | 59 | 12.0 | 10 | A | Improved |
|---|
| 5 | 62 | 13.6 | 60 | A | Static |
|---|
| 6 | 59 | 11.9 | 30 | B | Static |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 39 & 9.3 & 10 & A & Worse \\\\\n",
+ "\t2 & 51 & 14.6 & 50 & A & Worse \\\\\n",
+ "\t3 & 75 & 7.1 & 50 & A & Improved \\\\\n",
+ "\t4 & 59 & 12.0 & 10 & A & Improved \\\\\n",
+ "\t5 & 62 & 13.6 & 60 & A & Static \\\\\n",
+ "\t6 & 59 & 11.9 & 30 & B & Static \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "6×5 DataFrame\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 39 │ 9.3 │ 10 │ A │ Worse │\n",
+ "│ 2 │ 51 │ 14.6 │ 50 │ A │ Worse │\n",
+ "│ 3 │ 75 │ 7.1 │ 50 │ A │ Improved │\n",
+ "│ 4 │ 59 │ 12.0 │ 10 │ A │ Improved │\n",
+ "│ 5 │ 62 │ 13.6 │ 60 │ A │ Static │\n",
+ "│ 6 │ 59 │ 11.9 │ 30 │ B │ Static │"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "first(data,6)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[40]:1\n",
+ "└ @ Core In[40]:1\n",
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[40]:2\n",
+ "└ @ Core In[40]:2\n"
+ ]
+ }
+ ],
+ "source": [
+ "dataA = data[data[:Treatment] .== \"A\",:]\n",
+ "dataB = data[data[:Treatment] .== \"B\",:];"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
6 rows × 5 columns
| 1 | 39 | 9.3 | 10 | A | Worse |
|---|
| 2 | 51 | 14.6 | 50 | A | Worse |
|---|
| 3 | 75 | 7.1 | 50 | A | Improved |
|---|
| 4 | 59 | 12.0 | 10 | A | Improved |
|---|
| 5 | 62 | 13.6 | 60 | A | Static |
|---|
| 6 | 63 | 11.8 | 70 | A | Worse |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 39 & 9.3 & 10 & A & Worse \\\\\n",
+ "\t2 & 51 & 14.6 & 50 & A & Worse \\\\\n",
+ "\t3 & 75 & 7.1 & 50 & A & Improved \\\\\n",
+ "\t4 & 59 & 12.0 & 10 & A & Improved \\\\\n",
+ "\t5 & 62 & 13.6 & 60 & A & Static \\\\\n",
+ "\t6 & 63 & 11.8 & 70 & A & Worse \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "6×5 DataFrame\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 39 │ 9.3 │ 10 │ A │ Worse │\n",
+ "│ 2 │ 51 │ 14.6 │ 50 │ A │ Worse │\n",
+ "│ 3 │ 75 │ 7.1 │ 50 │ A │ Improved │\n",
+ "│ 4 │ 59 │ 12.0 │ 10 │ A │ Improved │\n",
+ "│ 5 │ 62 │ 13.6 │ 60 │ A │ Static │\n",
+ "│ 6 │ 63 │ 11.8 │ 70 │ A │ Worse │"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "first(dataA,6)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | variable | mean | min | median | max | nunique | nmissing | eltype |
|---|
| Symbol | Union… | Any | Union… | Any | Union… | Nothing | DataType |
|---|
5 rows × 8 columns
| 1 | Age | 49.91 | 18 | 50.0 | 80 | | | Int64 |
|---|
| 2 | WCC | 12.105 | 4.9 | 12.35 | 16.1 | | | Float64 |
|---|
| 3 | CRP | 47.3 | 10 | 40.0 | 210 | | | Int64 |
|---|
| 4 | Treatment | | A | | B | 2 | | String |
|---|
| 5 | Result | | Improved | | Worse | 3 | | String |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cccccccc}\n",
+ "\t& variable & mean & min & median & max & nunique & nmissing & eltype\\\\\n",
+ "\t\\hline\n",
+ "\t& Symbol & Union… & Any & Union… & Any & Union… & Nothing & DataType\\\\\n",
+ "\t\\hline\n",
+ "\t1 & Age & 49.91 & 18 & 50.0 & 80 & & & Int64 \\\\\n",
+ "\t2 & WCC & 12.105 & 4.9 & 12.35 & 16.1 & & & Float64 \\\\\n",
+ "\t3 & CRP & 47.3 & 10 & 40.0 & 210 & & & Int64 \\\\\n",
+ "\t4 & Treatment & & A & & B & 2 & & String \\\\\n",
+ "\t5 & Result & & Improved & & Worse & 3 & & String \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "5×8 DataFrame. Omitted printing of 1 columns\n",
+ "│ Row │ variable │ mean │ min │ median │ max │ nunique │ nmissing │\n",
+ "│ │ \u001b[90mSymbol\u001b[39m │ \u001b[90mUnion…\u001b[39m │ \u001b[90mAny\u001b[39m │ \u001b[90mUnion…\u001b[39m │ \u001b[90mAny\u001b[39m │ \u001b[90mUnion…\u001b[39m │ \u001b[90mNothing\u001b[39m │\n",
+ "├─────┼───────────┼────────┼──────────┼────────┼───────┼─────────┼──────────┤\n",
+ "│ 1 │ Age │ 49.91 │ 18 │ 50.0 │ 80 │ │ │\n",
+ "│ 2 │ WCC │ 12.105 │ 4.9 │ 12.35 │ 16.1 │ │ │\n",
+ "│ 3 │ CRP │ 47.3 │ 10 │ 40.0 │ 210 │ │ │\n",
+ "│ 4 │ Treatment │ │ A │ │ B │ 2 │ │\n",
+ "│ 5 │ Result │ │ Improved │ │ Worse │ 3 │ │"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "describe(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Treatment | N |
|---|
| String | Int64 |
|---|
2 rows × 2 columns
| 1 | A | 60 |
|---|
| 2 | B | 40 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Treatment & N\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Int64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & A & 60 \\\\\n",
+ "\t2 & B & 40 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "2×2 DataFrame\n",
+ "│ Row │ Treatment │ N │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mInt64\u001b[39m │\n",
+ "├─────┼───────────┼───────┤\n",
+ "│ 1 │ A │ 60 │\n",
+ "│ 2 │ B │ 40 │"
+ ]
+ },
+ "execution_count": 34,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> DataFrame(N = size(df,1)), groupby(data, :Treatment))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Treatment | x1 |
|---|
| String | Float64 |
|---|
2 rows × 2 columns
| 1 | A | 51.3333 |
|---|
| 2 | B | 47.775 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Treatment & x1\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Float64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & A & 51.3333 \\\\\n",
+ "\t2 & B & 47.775 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "2×2 DataFrame\n",
+ "│ Row │ Treatment │ x1 │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mFloat64\u001b[39m │\n",
+ "├─────┼───────────┼─────────┤\n",
+ "│ 1 │ A │ 51.3333 │\n",
+ "│ 2 │ B │ 47.775 │"
+ ]
+ },
+ "execution_count": 35,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> mean(df.Age), groupby(data, :Treatment))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Treatment | x1 |
|---|
| String | Tuple… |
|---|
2 rows × 2 columns
| 1 | A | (60, 5) |
|---|
| 2 | B | (40, 5) |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Treatment & x1\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Tuple…\\\\\n",
+ "\t\\hline\n",
+ "\t1 & A & (60, 5) \\\\\n",
+ "\t2 & B & (40, 5) \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "2×2 DataFrame\n",
+ "│ Row │ Treatment │ x1 │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mTuple…\u001b[39m │\n",
+ "├─────┼───────────┼─────────┤\n",
+ "│ 1 │ A │ (60, 5) │\n",
+ "│ 2 │ B │ (40, 5) │"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(size, groupby(data, :Treatment))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "GroupedDataFrame with 2 groups based on key: Treatment
First Group (60 rows): Treatment = \"A\"
| Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
| 1 | 39 | 9.3 | 10 | A | Worse |
|---|
| 2 | 51 | 14.6 | 50 | A | Worse |
|---|
| 3 | 75 | 7.1 | 50 | A | Improved |
|---|
| 4 | 59 | 12.0 | 10 | A | Improved |
|---|
| 5 | 62 | 13.6 | 60 | A | Static |
|---|
| 6 | 63 | 11.8 | 70 | A | Worse |
|---|
| 7 | 41 | 13.2 | 70 | A | Worse |
|---|
| 8 | 36 | 13.7 | 50 | A | Improved |
|---|
| 9 | 62 | 9.5 | 40 | A | Static |
|---|
| 10 | 34 | 13.6 | 30 | A | Static |
|---|
| 11 | 70 | 14.2 | 90 | A | Static |
|---|
| 12 | 54 | 12.9 | 30 | A | Improved |
|---|
| 13 | 78 | 11.0 | 30 | A | Improved |
|---|
| 14 | 53 | 15.5 | 100 | A | Static |
|---|
| 15 | 66 | 11.4 | 70 | A | Worse |
|---|
| 16 | 20 | 11.7 | 40 | A | Worse |
|---|
| 17 | 38 | 14.8 | 60 | A | Improved |
|---|
| 18 | 43 | 14.5 | 80 | A | Static |
|---|
| 19 | 26 | 7.9 | 10 | A | Improved |
|---|
| 20 | 63 | 9.5 | 50 | A | Improved |
|---|
| 21 | 48 | 12.4 | 30 | A | Improved |
|---|
| 22 | 46 | 11.1 | 100 | A | Static |
|---|
| 23 | 58 | 10.0 | 20 | A | Worse |
|---|
| 24 | 56 | 11.7 | 30 | A | Improved |
|---|
| 25 | 64 | 10.8 | 40 | A | Worse |
|---|
| 26 | 41 | 12.3 | 60 | A | Worse |
|---|
| 27 | 32 | 15.4 | 20 | A | Improved |
|---|
| 28 | 29 | 11.7 | 20 | A | Improved |
|---|
| 29 | 49 | 11.8 | 80 | A | Improved |
|---|
| 30 | 74 | 13.3 | 60 | A | Static |
|---|
| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
|---|
⋮
Last Group (40 rows): Treatment = \"B\"
| Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
| 1 | 59 | 11.9 | 30 | B | Static |
|---|
| 2 | 31 | 10.6 | 10 | B | Static |
|---|
| 3 | 45 | 13.6 | 90 | B | Worse |
|---|
| 4 | 78 | 11.8 | 70 | B | Improved |
|---|
| 5 | 18 | 12.3 | 20 | B | Worse |
|---|
| 6 | 53 | 12.7 | 60 | B | Worse |
|---|
| 7 | 80 | 12.1 | 20 | B | Static |
|---|
| 8 | 46 | 10.3 | 70 | B | Improved |
|---|
| 9 | 58 | 10.9 | 20 | B | Improved |
|---|
| 10 | 68 | 12.2 | 20 | B | Improved |
|---|
| 11 | 58 | 8.3 | 20 | B | Worse |
|---|
| 12 | 76 | 12.4 | 30 | B | Improved |
|---|
| 13 | 23 | 4.9 | 40 | B | Static |
|---|
| 14 | 80 | 13.7 | 80 | B | Static |
|---|
| 15 | 65 | 12.4 | 10 | B | Improved |
|---|
| 16 | 22 | 14.7 | 10 | B | Improved |
|---|
| 17 | 52 | 11.5 | 10 | B | Improved |
|---|
| 18 | 60 | 9.5 | 120 | B | Worse |
|---|
| 19 | 37 | 11.1 | 80 | B | Improved |
|---|
| 20 | 45 | 14.0 | 80 | B | Improved |
|---|
| 21 | 69 | 10.6 | 50 | B | Static |
|---|
| 22 | 56 | 9.5 | 50 | B | Improved |
|---|
| 23 | 59 | 14.2 | 30 | B | Worse |
|---|
| 24 | 65 | 14.5 | 70 | B | Worse |
|---|
| 25 | 57 | 13.6 | 20 | B | Static |
|---|
| 26 | 40 | 12.5 | 40 | B | Improved |
|---|
| 27 | 63 | 9.7 | 30 | B | Static |
|---|
| 28 | 18 | 10.0 | 70 | B | Worse |
|---|
| 29 | 30 | 14.2 | 50 | B | Improved |
|---|
| 30 | 44 | 9.7 | 70 | B | Static |
|---|
| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
|---|
"
+ ],
+ "text/latex": [
+ "GroupedDataFrame with 2 groups based on key: Treatment\n",
+ "\n",
+ "First Group (60 rows): Treatment = \"A\"\n",
+ "\n",
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 39 & 9.3 & 10 & A & Worse \\\\\n",
+ "\t2 & 51 & 14.6 & 50 & A & Worse \\\\\n",
+ "\t3 & 75 & 7.1 & 50 & A & Improved \\\\\n",
+ "\t4 & 59 & 12.0 & 10 & A & Improved \\\\\n",
+ "\t5 & 62 & 13.6 & 60 & A & Static \\\\\n",
+ "\t6 & 63 & 11.8 & 70 & A & Worse \\\\\n",
+ "\t7 & 41 & 13.2 & 70 & A & Worse \\\\\n",
+ "\t8 & 36 & 13.7 & 50 & A & Improved \\\\\n",
+ "\t9 & 62 & 9.5 & 40 & A & Static \\\\\n",
+ "\t10 & 34 & 13.6 & 30 & A & Static \\\\\n",
+ "\t11 & 70 & 14.2 & 90 & A & Static \\\\\n",
+ "\t12 & 54 & 12.9 & 30 & A & Improved \\\\\n",
+ "\t13 & 78 & 11.0 & 30 & A & Improved \\\\\n",
+ "\t14 & 53 & 15.5 & 100 & A & Static \\\\\n",
+ "\t15 & 66 & 11.4 & 70 & A & Worse \\\\\n",
+ "\t16 & 20 & 11.7 & 40 & A & Worse \\\\\n",
+ "\t17 & 38 & 14.8 & 60 & A & Improved \\\\\n",
+ "\t18 & 43 & 14.5 & 80 & A & Static \\\\\n",
+ "\t19 & 26 & 7.9 & 10 & A & Improved \\\\\n",
+ "\t20 & 63 & 9.5 & 50 & A & Improved \\\\\n",
+ "\t21 & 48 & 12.4 & 30 & A & Improved \\\\\n",
+ "\t22 & 46 & 11.1 & 100 & A & Static \\\\\n",
+ "\t23 & 58 & 10.0 & 20 & A & Worse \\\\\n",
+ "\t24 & 56 & 11.7 & 30 & A & Improved \\\\\n",
+ "\t25 & 64 & 10.8 & 40 & A & Worse \\\\\n",
+ "\t26 & 41 & 12.3 & 60 & A & Worse \\\\\n",
+ "\t27 & 32 & 15.4 & 20 & A & Improved \\\\\n",
+ "\t28 & 29 & 11.7 & 20 & A & Improved \\\\\n",
+ "\t29 & 49 & 11.8 & 80 & A & Improved \\\\\n",
+ "\t30 & 74 & 13.3 & 60 & A & Static \\\\\n",
+ "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ \\\\\n",
+ "\\end{tabular}\n",
+ "\n",
+ "$\\dots$\n",
+ "\n",
+ "Last Group (40 rows): Treatment = \"B\"\n",
+ "\n",
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 59 & 11.9 & 30 & B & Static \\\\\n",
+ "\t2 & 31 & 10.6 & 10 & B & Static \\\\\n",
+ "\t3 & 45 & 13.6 & 90 & B & Worse \\\\\n",
+ "\t4 & 78 & 11.8 & 70 & B & Improved \\\\\n",
+ "\t5 & 18 & 12.3 & 20 & B & Worse \\\\\n",
+ "\t6 & 53 & 12.7 & 60 & B & Worse \\\\\n",
+ "\t7 & 80 & 12.1 & 20 & B & Static \\\\\n",
+ "\t8 & 46 & 10.3 & 70 & B & Improved \\\\\n",
+ "\t9 & 58 & 10.9 & 20 & B & Improved \\\\\n",
+ "\t10 & 68 & 12.2 & 20 & B & Improved \\\\\n",
+ "\t11 & 58 & 8.3 & 20 & B & Worse \\\\\n",
+ "\t12 & 76 & 12.4 & 30 & B & Improved \\\\\n",
+ "\t13 & 23 & 4.9 & 40 & B & Static \\\\\n",
+ "\t14 & 80 & 13.7 & 80 & B & Static \\\\\n",
+ "\t15 & 65 & 12.4 & 10 & B & Improved \\\\\n",
+ "\t16 & 22 & 14.7 & 10 & B & Improved \\\\\n",
+ "\t17 & 52 & 11.5 & 10 & B & Improved \\\\\n",
+ "\t18 & 60 & 9.5 & 120 & B & Worse \\\\\n",
+ "\t19 & 37 & 11.1 & 80 & B & Improved \\\\\n",
+ "\t20 & 45 & 14.0 & 80 & B & Improved \\\\\n",
+ "\t21 & 69 & 10.6 & 50 & B & Static \\\\\n",
+ "\t22 & 56 & 9.5 & 50 & B & Improved \\\\\n",
+ "\t23 & 59 & 14.2 & 30 & B & Worse \\\\\n",
+ "\t24 & 65 & 14.5 & 70 & B & Worse \\\\\n",
+ "\t25 & 57 & 13.6 & 20 & B & Static \\\\\n",
+ "\t26 & 40 & 12.5 & 40 & B & Improved \\\\\n",
+ "\t27 & 63 & 9.7 & 30 & B & Static \\\\\n",
+ "\t28 & 18 & 10.0 & 70 & B & Worse \\\\\n",
+ "\t29 & 30 & 14.2 & 50 & B & Improved \\\\\n",
+ "\t30 & 44 & 9.7 & 70 & B & Static \\\\\n",
+ "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "GroupedDataFrame with 2 groups based on key: Treatment\n",
+ "First Group (60 rows): Treatment = \"A\"\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 39 │ 9.3 │ 10 │ A │ Worse │\n",
+ "│ 2 │ 51 │ 14.6 │ 50 │ A │ Worse │\n",
+ "│ 3 │ 75 │ 7.1 │ 50 │ A │ Improved │\n",
+ "│ 4 │ 59 │ 12.0 │ 10 │ A │ Improved │\n",
+ "│ 5 │ 62 │ 13.6 │ 60 │ A │ Static │\n",
+ "│ 6 │ 63 │ 11.8 │ 70 │ A │ Worse │\n",
+ "│ 7 │ 41 │ 13.2 │ 70 │ A │ Worse │\n",
+ "│ 8 │ 36 │ 13.7 │ 50 │ A │ Improved │\n",
+ "│ 9 │ 62 │ 9.5 │ 40 │ A │ Static │\n",
+ "│ 10 │ 34 │ 13.6 │ 30 │ A │ Static │\n",
+ "⋮\n",
+ "│ 50 │ 24 │ 13.4 │ 40 │ A │ Static │\n",
+ "│ 51 │ 39 │ 11.0 │ 30 │ A │ Static │\n",
+ "│ 52 │ 45 │ 13.5 │ 20 │ A │ Worse │\n",
+ "│ 53 │ 43 │ 12.5 │ 10 │ A │ Improved │\n",
+ "│ 54 │ 51 │ 14.1 │ 50 │ A │ Worse │\n",
+ "│ 55 │ 52 │ 13.7 │ 70 │ A │ Worse │\n",
+ "│ 56 │ 33 │ 11.2 │ 20 │ A │ Improved │\n",
+ "│ 57 │ 30 │ 12.5 │ 110 │ A │ Worse │\n",
+ "│ 58 │ 60 │ 12.6 │ 30 │ A │ Static │\n",
+ "│ 59 │ 76 │ 7.1 │ 10 │ A │ Static │\n",
+ "│ 60 │ 36 │ 11.8 │ 10 │ A │ Worse │\n",
+ "⋮\n",
+ "Last Group (40 rows): Treatment = \"B\"\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 59 │ 11.9 │ 30 │ B │ Static │\n",
+ "│ 2 │ 31 │ 10.6 │ 10 │ B │ Static │\n",
+ "│ 3 │ 45 │ 13.6 │ 90 │ B │ Worse │\n",
+ "│ 4 │ 78 │ 11.8 │ 70 │ B │ Improved │\n",
+ "│ 5 │ 18 │ 12.3 │ 20 │ B │ Worse │\n",
+ "│ 6 │ 53 │ 12.7 │ 60 │ B │ Worse │\n",
+ "│ 7 │ 80 │ 12.1 │ 20 │ B │ Static │\n",
+ "│ 8 │ 46 │ 10.3 │ 70 │ B │ Improved │\n",
+ "│ 9 │ 58 │ 10.9 │ 20 │ B │ Improved │\n",
+ "│ 10 │ 68 │ 12.2 │ 20 │ B │ Improved │\n",
+ "⋮\n",
+ "│ 30 │ 44 │ 9.7 │ 70 │ B │ Static │\n",
+ "│ 31 │ 29 │ 11.7 │ 80 │ B │ Worse │\n",
+ "│ 32 │ 33 │ 12.9 │ 10 │ B │ Worse │\n",
+ "│ 33 │ 27 │ 11.9 │ 20 │ B │ Improved │\n",
+ "│ 34 │ 19 │ 13.1 │ 100 │ B │ Worse │\n",
+ "│ 35 │ 49 │ 14.9 │ 40 │ B │ Worse │\n",
+ "│ 36 │ 47 │ 13.2 │ 40 │ B │ Worse │\n",
+ "│ 37 │ 38 │ 12.0 │ 210 │ B │ Worse │\n",
+ "│ 38 │ 35 │ 10.2 │ 40 │ B │ Static │\n",
+ "│ 39 │ 25 │ 13.0 │ 20 │ B │ Static │\n",
+ "│ 40 │ 54 │ 16.1 │ 50 │ B │ Improved │"
+ ]
+ },
+ "execution_count": 37,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "groupby(data, :Treatment)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Treatment | x1 |
|---|
| String | Float64 |
|---|
2 rows × 2 columns
| 1 | A | 15.3961 |
|---|
| 2 | B | 18.1072 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Treatment & x1\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Float64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & A & 15.3961 \\\\\n",
+ "\t2 & B & 18.1072 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "2×2 DataFrame\n",
+ "│ Row │ Treatment │ x1 │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mFloat64\u001b[39m │\n",
+ "├─────┼───────────┼─────────┤\n",
+ "│ 1 │ A │ 15.3961 │\n",
+ "│ 2 │ B │ 18.1072 │"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> std(df.Age), groupby(data, :Treatment))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Summary Stats:\n",
+ "Length: 60\n",
+ "Missing Count: 0\n",
+ "Mean: 51.333333\n",
+ "Minimum: 20.000000\n",
+ "1st Quartile: 39.000000\n",
+ "Median: 51.000000\n",
+ "3rd Quartile: 63.000000\n",
+ "Maximum: 80.000000\n",
+ "Type: Int64\n",
+ "Summary Stats:\n",
+ "Length: 40\n",
+ "Missing Count: 0\n",
+ "Mean: 47.775000\n",
+ "Minimum: 18.000000\n",
+ "1st Quartile: 32.500000\n",
+ "Median: 48.000000\n",
+ "3rd Quartile: 59.250000\n",
+ "Maximum: 80.000000\n",
+ "Type: Int64\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ " | Treatment | x1 |
|---|
| String | Nothing |
|---|
2 rows × 2 columns
| 1 | A | |
|---|
| 2 | B | |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Treatment & x1\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Nothing\\\\\n",
+ "\t\\hline\n",
+ "\t1 & A & \\\\\n",
+ "\t2 & B & \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "2×2 DataFrame\n",
+ "│ Row │ Treatment │ x1 │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mNothing\u001b[39m │\n",
+ "├─────┼───────────┼─────────┤\n",
+ "│ 1 │ A │ │\n",
+ "│ 2 │ B │ │"
+ ]
+ },
+ "execution_count": 41,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> describe(df.Age), groupby(data, :Treatment))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "┌ Info: Precompiling StatsPlots [f3b207a7-027a-5e70-b257-86293d7955fd]\n",
+ "└ @ Base loading.jl:1242\n"
+ ]
+ }
+ ],
+ "source": [
+ "using StatsPlots"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data density(:Age, group = :Treatment, title = \"Distribution of ages by treatment group\",\n",
+ " xlab = \"Age\", ylab = \"Distribution\",\n",
+ " legend = :topright\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data density(:Age, group = :Result, title = \"Distribution of ages by result group\",\n",
+ " xlab = \"Age\", ylab = \"Distribution\",\n",
+ " legend = :topright\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data density(:Age, group = (:Treatment,:Result), title = \"Distribution of ages by treatment and result groups\",\n",
+ " xlab = \"Age\", ylab = \"Distribution\",\n",
+ " legend = :topright\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 49,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data boxplot(:Treatment,:WCC, lab = \"WCC\", title = \"White cell count by treatment group\",\n",
+ " xlab = \"Groups\", ylab = \"WCC\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 50,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data boxplot(:Result,:WCC, lab = \"WCC\", title = \"White cell count by result group\",\n",
+ " xlab = \"Groups\", ylab = \"WCC\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 51,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data corrplot([:Age :WCC :CRP], grid = false)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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"
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "@df data cornerplot([:Age :WCC :CRP], grid = false, compact = true)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[54]:1\n",
+ "└ @ Core In[54]:1\n",
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[54]:1\n",
+ "└ @ Core In[54]:1\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "Two sample t-test (equal variance)\n",
+ "----------------------------------\n",
+ "Population details:\n",
+ " parameter of interest: Mean difference\n",
+ " value under h_0: 0\n",
+ " point estimate: 3.558333333333337\n",
+ " 95% confidence interval: (-3.1369, 10.2536)\n",
+ "\n",
+ "Test summary:\n",
+ " outcome with 95% confidence: fail to reject h_0\n",
+ " two-sided p-value: 0.2942\n",
+ "\n",
+ "Details:\n",
+ " number of observations: [60,40]\n",
+ " t-statistic: 1.05468405102565\n",
+ " degrees of freedom: 98\n",
+ " empirical standard error: 3.373838193412482\n"
+ ]
+ },
+ "execution_count": 54,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "HypothesisTests.EqualVarianceTTest(dataA[:Age],dataB[:Age])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[55]:1\n",
+ "└ @ Core In[55]:1\n",
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[55]:1\n",
+ "└ @ Core In[55]:1\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "0.5646191047328868"
+ ]
+ },
+ "execution_count": 55,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pvalue(EqualVarianceTTest(dataA[:WCC],dataB[:WCC]))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[56]:1\n",
+ "└ @ Core In[56]:1\n",
+ "┌ Warning: `getindex(df::DataFrame, col_ind::ColumnIndex)` is deprecated, use `df[!, col_ind]` instead.\n",
+ "│ caller = top-level scope at In[56]:1\n",
+ "└ @ Core In[56]:1\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "Two sample t-test (unequal variance)\n",
+ "------------------------------------\n",
+ "Population details:\n",
+ " parameter of interest: Mean difference\n",
+ " value under h_0: 0\n",
+ " point estimate: -3.6666666666666643\n",
+ " 95% confidence interval: (-17.7595, 10.4261)\n",
+ "\n",
+ "Test summary:\n",
+ " outcome with 95% confidence: fail to reject h_0\n",
+ " two-sided p-value: 0.6052\n",
+ "\n",
+ "Details:\n",
+ " number of observations: [60,40]\n",
+ " t-statistic: -0.5195095536758766\n",
+ " degrees of freedom: 65.70999926955622\n",
+ " empirical standard error: 7.057938859300185\n"
+ ]
+ },
+ "execution_count": 56,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "UnequalVarianceTTest(dataA[:CRP],dataB[:CRP])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredChol{Float64,LinearAlgebra.Cholesky{Float64,Array{Float64,2}}}},Array{Float64,2}}\n",
+ "\n",
+ "CRP ~ 1\n",
+ "\n",
+ "Coefficients:\n",
+ "──────────────────────────────────────────────────────────────────────────\n",
+ " Estimate Std. Error t value Pr(>|t|) Lower 95% Upper 95%\n",
+ "──────────────────────────────────────────────────────────────────────────\n",
+ "(Intercept) 47.3 3.23446 14.6238 <1e-25 40.8821 53.7179\n",
+ "──────────────────────────────────────────────────────────────────────────"
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "fit(LinearModel, @formula(CRP ~ 1), data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredChol{Float64,LinearAlgebra.Cholesky{Float64,Array{Float64,2}}}},Array{Float64,2}}\n",
+ "\n",
+ "CRP ~ 1 + Age\n",
+ "\n",
+ "Coefficients:\n",
+ "────────────────────────────────────────────────────────────────────────────────\n",
+ " Estimate Std. Error t value Pr(>|t|) Lower 95% Upper 95%\n",
+ "────────────────────────────────────────────────────────────────────────────────\n",
+ "(Intercept) 47.5107 10.3826 4.576 <1e-4 26.9068 68.1146 \n",
+ "Age -0.00422142 0.197566 -0.0213672 0.9830 -0.396284 0.387841\n",
+ "────────────────────────────────────────────────────────────────────────────────"
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "fit(LinearModel, @formula(CRP ~ Age), data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredChol{Float64,LinearAlgebra.Cholesky{Float64,Array{Float64,2}}}},Array{Float64,2}}\n",
+ "\n",
+ "CRP ~ 1 + Age + WCC\n",
+ "\n",
+ "Coefficients:\n",
+ "────────────────────────────────────────────────────────────────────────────────\n",
+ " Estimate Std. Error t value Pr(>|t|) Lower 95% Upper 95%\n",
+ "────────────────────────────────────────────────────────────────────────────────\n",
+ "(Intercept) 24.0772 22.2914 1.08011 0.2828 -20.165 68.3193 \n",
+ "Age 0.00504769 0.197308 0.0255827 0.9796 -0.386555 0.39665\n",
+ "WCC 1.89764 1.59831 1.18728 0.2380 -1.27456 5.06984\n",
+ "────────────────────────────────────────────────────────────────────────────────"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "fit(LinearModel, @formula(CRP ~ Age + WCC), data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | N |
|---|
| Int64 |
|---|
1 rows × 1 columns
| 1 | 100 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|c}\n",
+ "\t& N\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 100 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "1×1 DataFrame\n",
+ "│ Row │ N │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │\n",
+ "├─────┼───────┤\n",
+ "│ 1 │ 100 │"
+ ]
+ },
+ "execution_count": 60,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "DataFrame(N = size(data,1))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 61,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "100"
+ ]
+ },
+ "execution_count": 61,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "size(data,1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Result | N |
|---|
| String | Int64 |
|---|
3 rows × 2 columns
| 1 | Worse | 17 |
|---|
| 2 | Improved | 21 |
|---|
| 3 | Static | 22 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Result & N\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Int64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & Worse & 17 \\\\\n",
+ "\t2 & Improved & 21 \\\\\n",
+ "\t3 & Static & 22 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "3×2 DataFrame\n",
+ "│ Row │ Result │ N │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mInt64\u001b[39m │\n",
+ "├─────┼──────────┼───────┤\n",
+ "│ 1 │ Worse │ 17 │\n",
+ "│ 2 │ Improved │ 21 │\n",
+ "│ 3 │ Static │ 22 │"
+ ]
+ },
+ "execution_count": 63,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> DataFrame(N = size(df,1)), groupby(dataA, :Result))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Result | N |
|---|
| String | Int64 |
|---|
3 rows × 2 columns
| 1 | Static | 11 |
|---|
| 2 | Worse | 14 |
|---|
| 3 | Improved | 15 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|cc}\n",
+ "\t& Result & N\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Int64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & Static & 11 \\\\\n",
+ "\t2 & Worse & 14 \\\\\n",
+ "\t3 & Improved & 15 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "3×2 DataFrame\n",
+ "│ Row │ Result │ N │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mInt64\u001b[39m │\n",
+ "├─────┼──────────┼───────┤\n",
+ "│ 1 │ Static │ 11 │\n",
+ "│ 2 │ Worse │ 14 │\n",
+ "│ 3 │ Improved │ 15 │"
+ ]
+ },
+ "execution_count": 64,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "combine(df -> DataFrame(N = size(df,1)), groupby(dataB, :Result))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2×3 Array{Int64,2}:\n",
+ " 17 21 22\n",
+ " 14 15 11"
+ ]
+ },
+ "execution_count": 67,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "observed = reshape([17,14,21,15,22,11],(2,3)) #reshape([17,21,22,14,15,11],(2,3))\n",
+ "observed"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Pearson's Chi-square Test\n",
+ "-------------------------\n",
+ "Population details:\n",
+ " parameter of interest: Multinomial Probabilities\n",
+ " value under h_0: [0.18600000000000003, 0.124, 0.21600000000000003, 0.14400000000000002, 0.198, 0.132]\n",
+ " point estimate: [0.17, 0.14, 0.21, 0.15, 0.22, 0.11]\n",
+ " 95% confidence interval: Tuple{Float64,Float64}[(0.08, 0.2688), (0.05, 0.2388), (0.12, 0.3088), (0.06, 0.2488), (0.13, 0.3188), (0.02, 0.2088)]\n",
+ "\n",
+ "Test summary:\n",
+ " outcome with 95% confidence: fail to reject h_0\n",
+ " one-sided p-value: 0.6075\n",
+ "\n",
+ "Details:\n",
+ " Sample size: 100\n",
+ " statistic: 0.9968637992831542\n",
+ " degrees of freedom: 2\n",
+ " residuals: [-0.3709911166081349, 0.45436946739765177, -0.12909944487358085, 0.1581138830084189, 0.494413232473044, -0.6055300708194982]\n",
+ " std. residuals: [-0.7061695217765019, 0.7061695217765013, -0.255155181539915, 0.25515518153991423, 0.9550424786294757, -0.9550424786294757]\n"
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "ChisqTest(observed)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 69,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "CSV.write(\"ProjectData_1_point_0.csv\", data);"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {
diff --git a/02_Coursera_4.ipynb b/02_Coursera_4.ipynb
new file mode 100644
index 0000000..5aed9e8
--- /dev/null
+++ b/02_Coursera_4.ipynb
@@ -0,0 +1,385 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "using Distributions\n",
+ "using StatsBase\n",
+ "using CSV\n",
+ "using DataFrames\n",
+ "using HypothesisTests\n",
+ "using Plots\n",
+ "using GLM"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "test1 = CSV.read(\"ProjectData_1_point_0.csv\");"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
100 rows × 5 columns
| 1 | 39 | 9.3 | 10 | A | Worse |
|---|
| 2 | 51 | 14.6 | 50 | A | Worse |
|---|
| 3 | 75 | 7.1 | 50 | A | Improved |
|---|
| 4 | 59 | 12.0 | 10 | A | Improved |
|---|
| 5 | 62 | 13.6 | 60 | A | Static |
|---|
| 6 | 59 | 11.9 | 30 | B | Static |
|---|
| 7 | 31 | 10.6 | 10 | B | Static |
|---|
| 8 | 63 | 11.8 | 70 | A | Worse |
|---|
| 9 | 41 | 13.2 | 70 | A | Worse |
|---|
| 10 | 45 | 13.6 | 90 | B | Worse |
|---|
| 11 | 78 | 11.8 | 70 | B | Improved |
|---|
| 12 | 36 | 13.7 | 50 | A | Improved |
|---|
| 13 | 62 | 9.5 | 40 | A | Static |
|---|
| 14 | 34 | 13.6 | 30 | A | Static |
|---|
| 15 | 70 | 14.2 | 90 | A | Static |
|---|
| 16 | 54 | 12.9 | 30 | A | Improved |
|---|
| 17 | 18 | 12.3 | 20 | B | Worse |
|---|
| 18 | 78 | 11.0 | 30 | A | Improved |
|---|
| 19 | 53 | 12.7 | 60 | B | Worse |
|---|
| 20 | 53 | 15.5 | 100 | A | Static |
|---|
| 21 | 66 | 11.4 | 70 | A | Worse |
|---|
| 22 | 80 | 12.1 | 20 | B | Static |
|---|
| 23 | 46 | 10.3 | 70 | B | Improved |
|---|
| 24 | 58 | 10.9 | 20 | B | Improved |
|---|
| 25 | 68 | 12.2 | 20 | B | Improved |
|---|
| 26 | 58 | 8.3 | 20 | B | Worse |
|---|
| 27 | 20 | 11.7 | 40 | A | Worse |
|---|
| 28 | 38 | 14.8 | 60 | A | Improved |
|---|
| 29 | 76 | 12.4 | 30 | B | Improved |
|---|
| 30 | 23 | 4.9 | 40 | B | Static |
|---|
| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 39 & 9.3 & 10 & A & Worse \\\\\n",
+ "\t2 & 51 & 14.6 & 50 & A & Worse \\\\\n",
+ "\t3 & 75 & 7.1 & 50 & A & Improved \\\\\n",
+ "\t4 & 59 & 12.0 & 10 & A & Improved \\\\\n",
+ "\t5 & 62 & 13.6 & 60 & A & Static \\\\\n",
+ "\t6 & 59 & 11.9 & 30 & B & Static \\\\\n",
+ "\t7 & 31 & 10.6 & 10 & B & Static \\\\\n",
+ "\t8 & 63 & 11.8 & 70 & A & Worse \\\\\n",
+ "\t9 & 41 & 13.2 & 70 & A & Worse \\\\\n",
+ "\t10 & 45 & 13.6 & 90 & B & Worse \\\\\n",
+ "\t11 & 78 & 11.8 & 70 & B & Improved \\\\\n",
+ "\t12 & 36 & 13.7 & 50 & A & Improved \\\\\n",
+ "\t13 & 62 & 9.5 & 40 & A & Static \\\\\n",
+ "\t14 & 34 & 13.6 & 30 & A & Static \\\\\n",
+ "\t15 & 70 & 14.2 & 90 & A & Static \\\\\n",
+ "\t16 & 54 & 12.9 & 30 & A & Improved \\\\\n",
+ "\t17 & 18 & 12.3 & 20 & B & Worse \\\\\n",
+ "\t18 & 78 & 11.0 & 30 & A & Improved \\\\\n",
+ "\t19 & 53 & 12.7 & 60 & B & Worse \\\\\n",
+ "\t20 & 53 & 15.5 & 100 & A & Static \\\\\n",
+ "\t21 & 66 & 11.4 & 70 & A & Worse \\\\\n",
+ "\t22 & 80 & 12.1 & 20 & B & Static \\\\\n",
+ "\t23 & 46 & 10.3 & 70 & B & Improved \\\\\n",
+ "\t24 & 58 & 10.9 & 20 & B & Improved \\\\\n",
+ "\t25 & 68 & 12.2 & 20 & B & Improved \\\\\n",
+ "\t26 & 58 & 8.3 & 20 & B & Worse \\\\\n",
+ "\t27 & 20 & 11.7 & 40 & A & Worse \\\\\n",
+ "\t28 & 38 & 14.8 & 60 & A & Improved \\\\\n",
+ "\t29 & 76 & 12.4 & 30 & B & Improved \\\\\n",
+ "\t30 & 23 & 4.9 & 40 & B & Static \\\\\n",
+ "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "100×5 DataFrame\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 39 │ 9.3 │ 10 │ A │ Worse │\n",
+ "│ 2 │ 51 │ 14.6 │ 50 │ A │ Worse │\n",
+ "│ 3 │ 75 │ 7.1 │ 50 │ A │ Improved │\n",
+ "│ 4 │ 59 │ 12.0 │ 10 │ A │ Improved │\n",
+ "│ 5 │ 62 │ 13.6 │ 60 │ A │ Static │\n",
+ "│ 6 │ 59 │ 11.9 │ 30 │ B │ Static │\n",
+ "│ 7 │ 31 │ 10.6 │ 10 │ B │ Static │\n",
+ "│ 8 │ 63 │ 11.8 │ 70 │ A │ Worse │\n",
+ "│ 9 │ 41 │ 13.2 │ 70 │ A │ Worse │\n",
+ "│ 10 │ 45 │ 13.6 │ 90 │ B │ Worse │\n",
+ "⋮\n",
+ "│ 90 │ 43 │ 12.5 │ 10 │ A │ Improved │\n",
+ "│ 91 │ 51 │ 14.1 │ 50 │ A │ Worse │\n",
+ "│ 92 │ 35 │ 10.2 │ 40 │ B │ Static │\n",
+ "│ 93 │ 52 │ 13.7 │ 70 │ A │ Worse │\n",
+ "│ 94 │ 33 │ 11.2 │ 20 │ A │ Improved │\n",
+ "│ 95 │ 30 │ 12.5 │ 110 │ A │ Worse │\n",
+ "│ 96 │ 60 │ 12.6 │ 30 │ A │ Static │\n",
+ "│ 97 │ 25 │ 13.0 │ 20 │ B │ Static │\n",
+ "│ 98 │ 76 │ 7.1 │ 10 │ A │ Static │\n",
+ "│ 99 │ 54 │ 16.1 │ 50 │ B │ Improved │\n",
+ "│ 100 │ 36 │ 11.8 │ 10 │ A │ Worse │"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Group | Variable1 | Variable2 |
|---|
| String | Float64 | Float64 |
|---|
20 rows × 3 columns
| 1 | B | -0.395164 | 0.785108 |
|---|
| 2 | A | -0.477911 | 0.94664 |
|---|
| 3 | B | 1.3248 | 0.683507 |
|---|
| 4 | A | 2.18945 | 0.655638 |
|---|
| 5 | B | -1.8022 | 0.40504 |
|---|
| 6 | B | -0.0415339 | 0.0649169 |
|---|
| 7 | A | -0.988776 | 0.579329 |
|---|
| 8 | B | 0.452246 | 0.0049928 |
|---|
| 9 | B | -1.23054 | 0.529847 |
|---|
| 10 | A | -0.923378 | 0.258118 |
|---|
| 11 | B | 0.874476 | 0.642472 |
|---|
| 12 | A | -1.02009 | 0.0728385 |
|---|
| 13 | B | -0.422106 | 0.319547 |
|---|
| 14 | B | 0.953726 | 0.0257164 |
|---|
| 15 | A | -2.52417 | 0.0487641 |
|---|
| 16 | B | 0.494937 | 0.869764 |
|---|
| 17 | A | 1.47704 | 0.824756 |
|---|
| 18 | A | -0.133367 | 0.875263 |
|---|
| 19 | B | -0.906293 | 0.0709776 |
|---|
| 20 | B | -0.36659 | 0.452148 |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccc}\n",
+ "\t& Group & Variable1 & Variable2\\\\\n",
+ "\t\\hline\n",
+ "\t& String & Float64 & Float64\\\\\n",
+ "\t\\hline\n",
+ "\t1 & B & -0.395164 & 0.785108 \\\\\n",
+ "\t2 & A & -0.477911 & 0.94664 \\\\\n",
+ "\t3 & B & 1.3248 & 0.683507 \\\\\n",
+ "\t4 & A & 2.18945 & 0.655638 \\\\\n",
+ "\t5 & B & -1.8022 & 0.40504 \\\\\n",
+ "\t6 & B & -0.0415339 & 0.0649169 \\\\\n",
+ "\t7 & A & -0.988776 & 0.579329 \\\\\n",
+ "\t8 & B & 0.452246 & 0.0049928 \\\\\n",
+ "\t9 & B & -1.23054 & 0.529847 \\\\\n",
+ "\t10 & A & -0.923378 & 0.258118 \\\\\n",
+ "\t11 & B & 0.874476 & 0.642472 \\\\\n",
+ "\t12 & A & -1.02009 & 0.0728385 \\\\\n",
+ "\t13 & B & -0.422106 & 0.319547 \\\\\n",
+ "\t14 & B & 0.953726 & 0.0257164 \\\\\n",
+ "\t15 & A & -2.52417 & 0.0487641 \\\\\n",
+ "\t16 & B & 0.494937 & 0.869764 \\\\\n",
+ "\t17 & A & 1.47704 & 0.824756 \\\\\n",
+ "\t18 & A & -0.133367 & 0.875263 \\\\\n",
+ "\t19 & B & -0.906293 & 0.0709776 \\\\\n",
+ "\t20 & B & -0.36659 & 0.452148 \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "20×3 DataFrame\n",
+ "│ Row │ Group │ Variable1 │ Variable2 │\n",
+ "│ │ \u001b[90mString\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mFloat64\u001b[39m │\n",
+ "├─────┼────────┼────────────┼───────────┤\n",
+ "│ 1 │ B │ -0.395164 │ 0.785108 │\n",
+ "│ 2 │ A │ -0.477911 │ 0.94664 │\n",
+ "│ 3 │ B │ 1.3248 │ 0.683507 │\n",
+ "│ 4 │ A │ 2.18945 │ 0.655638 │\n",
+ "│ 5 │ B │ -1.8022 │ 0.40504 │\n",
+ "│ 6 │ B │ -0.0415339 │ 0.0649169 │\n",
+ "│ 7 │ A │ -0.988776 │ 0.579329 │\n",
+ "│ 8 │ B │ 0.452246 │ 0.0049928 │\n",
+ "│ 9 │ B │ -1.23054 │ 0.529847 │\n",
+ "│ 10 │ A │ -0.923378 │ 0.258118 │\n",
+ "│ 11 │ B │ 0.874476 │ 0.642472 │\n",
+ "│ 12 │ A │ -1.02009 │ 0.0728385 │\n",
+ "│ 13 │ B │ -0.422106 │ 0.319547 │\n",
+ "│ 14 │ B │ 0.953726 │ 0.0257164 │\n",
+ "│ 15 │ A │ -2.52417 │ 0.0487641 │\n",
+ "│ 16 │ B │ 0.494937 │ 0.869764 │\n",
+ "│ 17 │ A │ 1.47704 │ 0.824756 │\n",
+ "│ 18 │ A │ -0.133367 │ 0.875263 │\n",
+ "│ 19 │ B │ -0.906293 │ 0.0709776 │\n",
+ "│ 20 │ B │ -0.36659 │ 0.452148 │"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "DataFrame(Group=rand([\"A\", \"B\"], 20), Variable1=randn(20), Variable2=rand(20))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "DataFrameRow (5 columns)
| Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
| 3 | 75 | 7.1 | 50 | A | Improved |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t3 & 75 & 7.1 & 50 & A & Improved \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "DataFrameRow\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 3 │ 75 │ 7.1 │ 50 │ A │ Improved │"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "view(test1,3,:)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " | Age | WCC | CRP | Treatment | Result |
|---|
| Int64 | Float64 | Int64 | String | String |
|---|
97 rows × 5 columns
| 1 | 39 | 9.3 | 10 | A | Worse |
|---|
| 2 | 51 | 14.6 | 50 | A | Worse |
|---|
| 3 | 59 | 12.0 | 10 | A | Improved |
|---|
| 4 | 59 | 11.9 | 30 | B | Static |
|---|
| 5 | 31 | 10.6 | 10 | B | Static |
|---|
| 6 | 63 | 11.8 | 70 | A | Worse |
|---|
| 7 | 45 | 13.6 | 90 | B | Worse |
|---|
| 8 | 78 | 11.8 | 70 | B | Improved |
|---|
| 9 | 36 | 13.7 | 50 | A | Improved |
|---|
| 10 | 62 | 9.5 | 40 | A | Static |
|---|
| 11 | 34 | 13.6 | 30 | A | Static |
|---|
| 12 | 70 | 14.2 | 90 | A | Static |
|---|
| 13 | 54 | 12.9 | 30 | A | Improved |
|---|
| 14 | 18 | 12.3 | 20 | B | Worse |
|---|
| 15 | 78 | 11.0 | 30 | A | Improved |
|---|
| 16 | 53 | 12.7 | 60 | B | Worse |
|---|
| 17 | 53 | 15.5 | 100 | A | Static |
|---|
| 18 | 66 | 11.4 | 70 | A | Worse |
|---|
| 19 | 80 | 12.1 | 20 | B | Static |
|---|
| 20 | 46 | 10.3 | 70 | B | Improved |
|---|
| 21 | 58 | 10.9 | 20 | B | Improved |
|---|
| 22 | 68 | 12.2 | 20 | B | Improved |
|---|
| 23 | 58 | 8.3 | 20 | B | Worse |
|---|
| 24 | 20 | 11.7 | 40 | A | Worse |
|---|
| 25 | 38 | 14.8 | 60 | A | Improved |
|---|
| 26 | 76 | 12.4 | 30 | B | Improved |
|---|
| 27 | 23 | 4.9 | 40 | B | Static |
|---|
| 28 | 80 | 13.7 | 80 | B | Static |
|---|
| 29 | 65 | 12.4 | 10 | B | Improved |
|---|
| 30 | 22 | 14.7 | 10 | B | Improved |
|---|
| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
|---|
"
+ ],
+ "text/latex": [
+ "\\begin{tabular}{r|ccccc}\n",
+ "\t& Age & WCC & CRP & Treatment & Result\\\\\n",
+ "\t\\hline\n",
+ "\t& Int64 & Float64 & Int64 & String & String\\\\\n",
+ "\t\\hline\n",
+ "\t1 & 39 & 9.3 & 10 & A & Worse \\\\\n",
+ "\t2 & 51 & 14.6 & 50 & A & Worse \\\\\n",
+ "\t3 & 59 & 12.0 & 10 & A & Improved \\\\\n",
+ "\t4 & 59 & 11.9 & 30 & B & Static \\\\\n",
+ "\t5 & 31 & 10.6 & 10 & B & Static \\\\\n",
+ "\t6 & 63 & 11.8 & 70 & A & Worse \\\\\n",
+ "\t7 & 45 & 13.6 & 90 & B & Worse \\\\\n",
+ "\t8 & 78 & 11.8 & 70 & B & Improved \\\\\n",
+ "\t9 & 36 & 13.7 & 50 & A & Improved \\\\\n",
+ "\t10 & 62 & 9.5 & 40 & A & Static \\\\\n",
+ "\t11 & 34 & 13.6 & 30 & A & Static \\\\\n",
+ "\t12 & 70 & 14.2 & 90 & A & Static \\\\\n",
+ "\t13 & 54 & 12.9 & 30 & A & Improved \\\\\n",
+ "\t14 & 18 & 12.3 & 20 & B & Worse \\\\\n",
+ "\t15 & 78 & 11.0 & 30 & A & Improved \\\\\n",
+ "\t16 & 53 & 12.7 & 60 & B & Worse \\\\\n",
+ "\t17 & 53 & 15.5 & 100 & A & Static \\\\\n",
+ "\t18 & 66 & 11.4 & 70 & A & Worse \\\\\n",
+ "\t19 & 80 & 12.1 & 20 & B & Static \\\\\n",
+ "\t20 & 46 & 10.3 & 70 & B & Improved \\\\\n",
+ "\t21 & 58 & 10.9 & 20 & B & Improved \\\\\n",
+ "\t22 & 68 & 12.2 & 20 & B & Improved \\\\\n",
+ "\t23 & 58 & 8.3 & 20 & B & Worse \\\\\n",
+ "\t24 & 20 & 11.7 & 40 & A & Worse \\\\\n",
+ "\t25 & 38 & 14.8 & 60 & A & Improved \\\\\n",
+ "\t26 & 76 & 12.4 & 30 & B & Improved \\\\\n",
+ "\t27 & 23 & 4.9 & 40 & B & Static \\\\\n",
+ "\t28 & 80 & 13.7 & 80 & B & Static \\\\\n",
+ "\t29 & 65 & 12.4 & 10 & B & Improved \\\\\n",
+ "\t30 & 22 & 14.7 & 10 & B & Improved \\\\\n",
+ "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/plain": [
+ "97×5 DataFrame\n",
+ "│ Row │ Age │ WCC │ CRP │ Treatment │ Result │\n",
+ "│ │ \u001b[90mInt64\u001b[39m │ \u001b[90mFloat64\u001b[39m │ \u001b[90mInt64\u001b[39m │ \u001b[90mString\u001b[39m │ \u001b[90mString\u001b[39m │\n",
+ "├─────┼───────┼─────────┼───────┼───────────┼──────────┤\n",
+ "│ 1 │ 39 │ 9.3 │ 10 │ A │ Worse │\n",
+ "│ 2 │ 51 │ 14.6 │ 50 │ A │ Worse │\n",
+ "│ 3 │ 59 │ 12.0 │ 10 │ A │ Improved │\n",
+ "│ 4 │ 59 │ 11.9 │ 30 │ B │ Static │\n",
+ "│ 5 │ 31 │ 10.6 │ 10 │ B │ Static │\n",
+ "│ 6 │ 63 │ 11.8 │ 70 │ A │ Worse │\n",
+ "│ 7 │ 45 │ 13.6 │ 90 │ B │ Worse │\n",
+ "│ 8 │ 78 │ 11.8 │ 70 │ B │ Improved │\n",
+ "│ 9 │ 36 │ 13.7 │ 50 │ A │ Improved │\n",
+ "│ 10 │ 62 │ 9.5 │ 40 │ A │ Static │\n",
+ "⋮\n",
+ "│ 87 │ 43 │ 12.5 │ 10 │ A │ Improved │\n",
+ "│ 88 │ 51 │ 14.1 │ 50 │ A │ Worse │\n",
+ "│ 89 │ 35 │ 10.2 │ 40 │ B │ Static │\n",
+ "│ 90 │ 52 │ 13.7 │ 70 │ A │ Worse │\n",
+ "│ 91 │ 33 │ 11.2 │ 20 │ A │ Improved │\n",
+ "│ 92 │ 30 │ 12.5 │ 110 │ A │ Worse │\n",
+ "│ 93 │ 60 │ 12.6 │ 30 │ A │ Static │\n",
+ "│ 94 │ 25 │ 13.0 │ 20 │ B │ Static │\n",
+ "│ 95 │ 76 │ 7.1 │ 10 │ A │ Static │\n",
+ "│ 96 │ 54 │ 16.1 │ 50 │ B │ Improved │\n",
+ "│ 97 │ 36 │ 11.8 │ 10 │ A │ Worse │"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test1[[1:2;4:4;6:8;10:end],:]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "101.20293783633616"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "var(rand(Normal(80, 10), 200))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "-0.0520584551299503"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mean(randn(100))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "TDist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "EqualVarianceTTest()"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Julia 1.2.0",
+ "language": "julia",
+ "name": "julia-1.2"
+ },
+ "language_info": {
+ "file_extension": ".jl",
+ "mimetype": "application/julia",
+ "name": "julia",
+ "version": "1.2.0"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/ProjectData_1_point_0.csv b/ProjectData_1_point_0.csv
new file mode 100644
index 0000000..4eb94da
--- /dev/null
+++ b/ProjectData_1_point_0.csv
@@ -0,0 +1,101 @@
+Age,WCC,CRP,Treatment,Result
+39,9.3,10,A,Worse
+51,14.6,50,A,Worse
+75,7.1,50,A,Improved
+59,12.0,10,A,Improved
+62,13.6,60,A,Static
+59,11.9,30,B,Static
+31,10.6,10,B,Static
+63,11.8,70,A,Worse
+41,13.2,70,A,Worse
+45,13.6,90,B,Worse
+78,11.8,70,B,Improved
+36,13.7,50,A,Improved
+62,9.5,40,A,Static
+34,13.6,30,A,Static
+70,14.2,90,A,Static
+54,12.9,30,A,Improved
+18,12.3,20,B,Worse
+78,11.0,30,A,Improved
+53,12.7,60,B,Worse
+53,15.5,100,A,Static
+66,11.4,70,A,Worse
+80,12.1,20,B,Static
+46,10.3,70,B,Improved
+58,10.9,20,B,Improved
+68,12.2,20,B,Improved
+58,8.3,20,B,Worse
+20,11.7,40,A,Worse
+38,14.8,60,A,Improved
+76,12.4,30,B,Improved
+23,4.9,40,B,Static
+80,13.7,80,B,Static
+65,12.4,10,B,Improved
+22,14.7,10,B,Improved
+43,14.5,80,A,Static
+26,7.9,10,A,Improved
+63,9.5,50,A,Improved
+48,12.4,30,A,Improved
+46,11.1,100,A,Static
+52,11.5,10,B,Improved
+60,9.5,120,B,Worse
+58,10.0,20,A,Worse
+56,11.7,30,A,Improved
+64,10.8,40,A,Worse
+41,12.3,60,A,Worse
+37,11.1,80,B,Improved
+45,14.0,80,B,Improved
+69,10.6,50,B,Static
+56,9.5,50,B,Improved
+59,14.2,30,B,Worse
+65,14.5,70,B,Worse
+32,15.4,20,A,Improved
+29,11.7,20,A,Improved
+49,11.8,80,A,Improved
+74,13.3,60,A,Static
+80,10.9,20,A,Improved
+57,13.6,20,B,Static
+65,15.0,10,A,Improved
+56,12.6,40,A,Static
+71,11.5,90,A,Static
+49,13.0,40,A,Static
+32,15.6,40,A,Improved
+40,12.5,40,B,Improved
+31,12.7,30,A,Improved
+63,9.7,30,B,Static
+77,14.5,40,A,Static
+18,10.0,70,B,Worse
+49,6.1,50,A,Static
+30,14.2,50,B,Improved
+44,9.7,70,B,Static
+45,12.8,110,A,Worse
+29,11.7,80,B,Worse
+49,12.2,40,A,Improved
+59,10.5,20,A,Static
+33,12.9,10,B,Worse
+66,12.6,30,A,Static
+67,13.8,110,A,Static
+27,11.9,20,B,Improved
+19,13.1,100,B,Worse
+49,14.9,40,B,Worse
+52,11.8,20,A,Worse
+45,12.2,70,A,Static
+76,13.4,30,A,Worse
+34,12.5,40,A,Static
+58,12.7,60,A,Improved
+47,13.2,40,B,Worse
+38,12.0,210,B,Worse
+24,13.4,40,A,Static
+39,11.0,30,A,Static
+45,13.5,20,A,Worse
+43,12.5,10,A,Improved
+51,14.1,50,A,Worse
+35,10.2,40,B,Static
+52,13.7,70,A,Worse
+33,11.2,20,A,Improved
+30,12.5,110,A,Worse
+60,12.6,30,A,Static
+25,13.0,20,B,Static
+76,7.1,10,A,Static
+54,16.1,50,B,Improved
+36,11.8,10,A,Worse