2020-05-29 18:37:25 +00:00
{
"cells": [
{
"cell_type": "code",
2020-05-30 02:09:04 +00:00
"execution_count": 3,
2020-05-29 18:37:25 +00:00
"metadata": {},
"outputs": [
2020-05-30 02:09:04 +00:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"┌ 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"
]
}
],
"source": [
"using Distributions\n",
"using StatsBase\n",
"using CSV\n",
"using DataFrames\n",
"using HypothesisTests\n",
"using Plots\n",
"using GLM\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"┌ 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"
]
},
{
"data": {
"text/plain": [
"Plots.PyPlotBackend()"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pyplot()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Age</th><th>WCC</th><th>CRP</th><th>Treatment</th><th>Result</th></tr><tr><th></th><th>Int64</th><th>Float64</th><th>Int64</th><th>String</th><th>String</th></tr></thead><tbody><p>6 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Age</th><th>WCC</th><th>CRP</th><th>Treatment</th><th>Result</th></tr><tr><th></th><th>Int64</th><th>Float64</th><th>Int64</th><th>String</th><th>String</th></tr></thead><tbody><p>6 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>variable</th><th>mean</th><th>min</th><th>median</th><th>max</th><th>nunique</th><th>nmissing</th><th>eltype</th></tr><tr><th></th><th>Symbol</th><th>Union…</th><th>Any</th><th>Union…</th><th>Any</th><th>Union…</th><th>Nothing</th><th>DataType</th></tr></thead><tbody><p>5 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Treatment</th><th>N</th></tr><tr><th></th><th>String</th><th>Int64</th></tr></thead><tbody><p>2 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Treatment</th><th>x1</th></tr><tr><th></th><th>String</th><th>Float64</th></tr></thead><tbody><p>2 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Treatment</th><th>x1</th></tr><tr><th></th><th>String</th><th>Tuple…</th></tr></thead><tbody><p>2 rows ×
],
"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×
"│ 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": [
"<p><b>GroupedDataFrame with 2 groups based on key: Treatment</b></p><p><i>First Group (60 rows): Treatment = \"A\"</i></p><table class=\"data-frame\"><thead><tr><th></th><th>Age</th><th>WCC</th><th>CRP</th><th>Treatment</th><th>Result</th></tr><tr><th></th><th>Int64</th><th>Float64</th><th>Int64</th><th>String</th><th>String</th></tr></thead><tbody><tr><th>1</th><td>39</td><td>9.3</td><td>10</td><td>A</td><td>Worse</td></tr><tr><th>2</th><td>51</td><td>14.6</td><td>50</td><td>A</td><td>Worse</td></tr><tr><th>3</th><td>75</td><td>7.1</td><td>50</td><td>A</td><td>Improved</td></tr><tr><th>4</th><td>59</td><td>12.0</td><td>10</td><td>A</td><td>Improved</td></tr><tr><th>5</th><td>62</td><td>13.6</td><td>60</td><td>A</td><td>Static</td></tr><tr><th>6</th><td>63</td><td>11.8</td><td>70</td><td>A</td><td>Worse</td></tr><tr><th>7</th><td>41</td><td>13.2</td><td>70</td><td>A</td><td>Worse</td></tr><tr><th>8</th><td>36</td><td>13.7</td><td>50</td><td>A</td><td>Improved</td></tr><tr><th>9</th><td>62</td><td>9.5</td><td>40</td><td>A</td><td>Static</td></tr><tr><th>10</th><td>34</td><td>13.6</td><td>30</td><td>A</td><td>Static</td></tr><tr><th>11</th><td>70</td><td>14.2</td><td>90</td><td>A</td><td>Static</td></tr><tr><th>12</th><td>54</td><td>12.9</td><td>30</td><td>A</td><td>Improved</td></tr><tr><th>13</th><td>78</td><td>11.0</td><td>30</td><td>A</td><td>Improved</td></tr><tr><th>14</th><td>53</td><td>15.5</td><td>100</td><td>A</td><td>Static</td></tr><tr><th>15</th><td>66</td><td>11.4</td><td>70</td><td>A</td><td>Worse</td></tr><tr><th>16</th><td>20</td><td>11.7</td><td>40</td><td>A</td><td>Worse</td></tr><tr><th>17</th><td>38</td><td>14.8</td><td>60</td><td>A</td><td>Improved</td></tr><tr><th>18</th><td>43</td><td>14.5</td><td>80</td><td>A</td><td>Static</td></tr><tr><th>19</th><td>26</td><td>7.9</td><td>10</td><td>A</td><td>Improved</td></tr><tr><th>20</th><td>63</td><td>9.5</td><td>50</td><td>A</td><td>Improved</td></tr><tr><th>21</th><td>48</td><td>12.4</td><td>30</td><td>A</td><td>Improved</td></tr><tr><th>22</th><td>46</td><td>11.1</td><td>100</td><td>A</td><td>Static</td></tr><tr><th>23</th><td>58</td><td>10.0</td><td>20</td><td>A</td><td>Worse</td></tr><tr><th>24</th><td>56</td><td>11.7</td><td>30</td><td>A</td><td>Improved</td></tr><tr><th>25</th><td>64</td><td>10.8</td><td>40</td><td>A</td><td>Worse</td></tr><tr><th>26</th><td>41</td><td>12.3</td><td>60</td><td>A</td><td>Worse</td></tr><tr><th>27</th><td>32</td><td>15.4</td><td>20</td><td>A</td><td>Improved</td></tr><tr><th>28</th><td>29</td><td>11.7</td><td>20</td><td>A</td><td>Improved</td></tr><tr><th>29</th><td>49</td><td>11.8</td><td>80</td><td>A</td><td>Improved</td></tr><tr><th>30</th><td>74</td><td>13.3</td><td>60</td><td>A</td><td>Static</td></tr><tr><th>⋮</th><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td></tr></tbody></table><p>⋮</p><p><i>Last Group (40 rows): Treatment = \"B\"</i></p><table class=\"data-frame\"><thead><tr><th></th><th>Age</th><th>WCC</th><th>CRP</th><th>Treatment</th><th>Result</th></tr><tr><th></th><th>Int64</th><th>Float64</th><th>Int64</th><th>String</th><th>String</th></tr></thead><tbody><tr><th>1</th><td>59</td><td>11.9</td><td>30</td><td>B</td><td>Static</td></tr><tr><th>2</th><td>31</td><td>10.6</td><td>10</td><td>B</td><td>Static</td></tr><tr><th>3</th><td>45</td><td>13.6</td><td>90</td><td>B</td><td>Worse</td></tr><tr><th>4</th><td>78</td><td>11.8</td><td>70</td><td>B</td><td>Improved</td></tr><tr><th>5</th><td>18</td><td>12.3</td><td>20</td><td>B</td><td>Worse</td></tr><tr><th>6</th><td>53</td><td>12.7</td><td>60</td><td>B</td><td>Worse</td></tr><tr><th>7</th><td>80</td><td>12.1</td><td>20</td><td>B</td><td>Static</td></tr><tr><th>8</th><td>46</td><td>10.3</td><td>70</td><td>B</td><td>Improved</td></tr><tr><th>9</th><td>58</td><td>10.9</td><td>20</td><td>B</td><td>Improved</td></tr><tr><th>10</th><td>68</td><td>12.2</td><td>20</td><td>B</td><td>Improved</td></tr><tr><th>11</th><td>58</td><td>8.3</td><td>20</td><td>B</td><td>Worse</td></tr><tr><th>12</th><td>76</td><td>12.
],
"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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Treatment</th><th>x1</th></tr><tr><th></th><th>String</th><th>Float64</th></tr></thead><tbody><p>2 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Treatment</th><th>x1</th></tr><tr><th></th><th>String</th><th>Nothing</th></tr></thead><tbody><p>2 rows ×
],
"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×
"│ 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"
]
},
2020-05-29 18:37:25 +00:00
{
"data": {
"text/plain": [
2020-05-30 02:09:04 +00:00
"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"
2020-05-29 18:37:25 +00:00
]
},
2020-05-30 02:09:04 +00:00
"execution_count": 54,
2020-05-29 18:37:25 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2020-05-30 02:09:04 +00:00
"HypothesisTests.EqualVarianceTTest(dataA[:Age],dataB[:Age])"
2020-05-29 18:37:25 +00:00
]
},
{
"cell_type": "code",
2020-05-30 02:09:04 +00:00
"execution_count": 55,
2020-05-29 18:37:25 +00:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
2020-05-30 02:09:04 +00:00
"┌ 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"
2020-05-29 18:37:25 +00:00
]
2020-05-30 02:09:04 +00:00
},
{
"data": {
"text/plain": [
"0.5646191047328868"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
2020-05-29 18:37:25 +00:00
}
],
"source": [
2020-05-30 02:09:04 +00:00
"pvalue(EqualVarianceTTest(dataA[:WCC],dataB[:WCC]))"
2020-05-29 18:37:25 +00:00
]
},
{
"cell_type": "code",
2020-05-30 02:09:04 +00:00
"execution_count": 56,
2020-05-29 18:37:25 +00:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
2020-05-30 02:09:04 +00:00
"┌ 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"
2020-05-29 18:37:25 +00:00
]
},
{
"data": {
"text/plain": [
2020-05-30 02:09:04 +00:00
"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"
2020-05-29 18:37:25 +00:00
]
},
2020-05-30 02:09:04 +00:00
"execution_count": 56,
2020-05-29 18:37:25 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2020-05-30 02:09:04 +00:00
"UnequalVarianceTTest(dataA[:CRP],dataB[:CRP])"
2020-05-29 18:37:25 +00:00
]
},
{
"cell_type": "code",
2020-05-30 02:09:04 +00:00
"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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>N</th></tr><tr><th></th><th>Int64</th></tr></thead><tbody><p>1 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Result</th><th>N</th></tr><tr><th></th><th>String</th><th>Int64</th></tr></thead><tbody><p>3 rows ×
],
"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×
"│ 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": [
"<table class=\"data-frame\"><thead><tr><th></th><th>Result</th><th>N</th></tr><tr><th></th><th>String</th><th>Int64</th></tr></thead><tbody><p>3 rows ×
],
"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×
"│ 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×
" 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,
2020-05-29 18:37:25 +00:00
"metadata": {},
"outputs": [],
"source": [
2020-05-30 02:09:04 +00:00
"CSV.write(\"ProjectData_1_point_0.csv\", data);"
2020-05-29 18:37:25 +00:00
]
2020-05-30 02:09:04 +00:00
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
2020-05-29 18:37:25 +00:00
}
],
"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
}
