{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[this doc on github](https://github.com/dotnet/interactive/tree/master/samples/notebooks/csharp/Samples)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "#i \"nuget:https://pkgs.dev.azure.com/dnceng/public/_packaging/dotnet5/nuget/v3/index.json\" \r\n",
    "#i \"nuget:https://pkgs.dev.azure.com/dnceng/public/_packaging/dotnet-tools/nuget/v3/index.json\" \r\n",
    "\r\n",
    "#r \"nuget:Microsoft.Data.Analysis,0.2.0\"\r\n",
    "#r \"nuget: XPlot.Plotly.Interactive, 4.0.6\"\r\n",
    "\r\n",
    "using Microsoft.Data.Analysis;\r\n",
    "using static Microsoft.DotNet.Interactive.Formatting.PocketViewTags;\r\n",
    "using Microsoft.DotNet.Interactive.Formatting;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "PrimitiveDataFrameColumn<DateTime> dateTimes = new PrimitiveDataFrameColumn<DateTime>(\"DateTimes\"); // Default length is 0.\n",
    "PrimitiveDataFrameColumn<int> ints = new PrimitiveDataFrameColumn<int>(\"Ints\", 3); // Makes a column of length 3. Filled with nulls initially\n",
    "StringDataFrameColumn strings = new StringDataFrameColumn(\"Strings\", 3); // Makes a column of length 3. Filled with nulls initially"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Append 3 values to dateTimes\n",
    "dateTimes.Append(DateTime.Parse(\"2019/01/01\"));\n",
    "dateTimes.Append(DateTime.Parse(\"2019/01/01\"));\n",
    "dateTimes.Append(DateTime.Parse(\"2019/01/02\"));"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "DataFrame df = new DataFrame(dateTimes, ints, strings ); // This will throw if the columns are of different lengths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "using Microsoft.AspNetCore.Html;\n",
    "Formatter.Register<DataFrame>((df, writer) =>\n",
    "{\n",
    "    var headers = new List<IHtmlContent>();\n",
    "    headers.Add(th(i(\"index\")));\n",
    "    headers.AddRange(df.Columns.Select(c => (IHtmlContent) th(c.Name)));\n",
    "    var rows = new List<List<IHtmlContent>>();\n",
    "    var take = 20;\n",
    "    for (var i = 0; i < Math.Min(take, df.Rows.Count); i++)\n",
    "    {\n",
    "        var cells = new List<IHtmlContent>();\n",
    "        cells.Add(td(i));\n",
    "        foreach (var obj in df.Rows[i])\n",
    "        {\n",
    "            cells.Add(td(obj));\n",
    "        }\n",
    "        rows.Add(cells);\n",
    "    }\n",
    "    \n",
    "    var t = table(\n",
    "        thead(\n",
    "            headers),\n",
    "        tbody(\n",
    "            rows.Select(\n",
    "                r => tr(r))));\n",
    "    \n",
    "    writer.Write(t);\n",
    "}, \"text/html\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// To change a value directly through df\n",
    "df[0, 1] = 10; // 0 is the rowIndex, and 1 is the columnIndex. This sets the 0th value in the Ints columns to 10\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Modify ints and strings columns by indexing\n",
    "ints[1] = 100;\n",
    "strings[1] = \"Foo!\";\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Indexing can throw when types don't match.\n",
    "// ints[1] = \"this will throw because I am a string\";  \n",
    "// Info can be used to figure out the type of data in a column. \n",
    "df.Info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Add 5 to ints through the DataFrame\n",
    "df[\"Ints\"].Add(5, inPlace: true);\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// We can also use binary operators. Binary operators produce a copy, so assign it back to our Ints column \n",
    "df[\"Ints\"] = (ints / 5) * 100;\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Fill nulls in our columns, if any. Ints[2], Strings[0] and Strings[1] are null\n",
    "df[\"Ints\"].FillNulls(-1, inPlace: true);\n",
    "df[\"Strings\"].FillNulls(\"Bar\", inPlace: true);\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// To inspect the first row\n",
    "DataFrameRow row0 = df.Rows[0];\n",
    "row0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "using Microsoft.AspNetCore.Html;\n",
    "Formatter.Register<DataFrameRow>((dataFrameRow, writer) =>\n",
    "{\n",
    "    var cells = new List<IHtmlContent>();\n",
    "    cells.Add(td(i));\n",
    "    foreach (var obj in dataFrameRow)\n",
    "    {\n",
    "        cells.Add(td(obj));\n",
    "    }\n",
    "    \n",
    "    var t = table(\n",
    "        tbody(\n",
    "            cells));\n",
    "    \n",
    "    writer.Write(t);\n",
    "}, \"text/html\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "row0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Filter rows based on equality\n",
    "PrimitiveDataFrameColumn<bool> boolFilter = df[\"Strings\"].ElementwiseEquals(\"Bar\");\n",
    "boolFilter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "DataFrame filtered = df.Filter(boolFilter);\n",
    "filtered"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Sort our dataframe using the Ints column\n",
    "DataFrame sorted = df.Sort(\"Ints\");\n",
    "sorted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// GroupBy \n",
    "GroupBy groupBy = df.GroupBy(\"DateTimes\");\n",
    "// Count of values in each group\n",
    "DataFrame groupCounts = groupBy.Count();\n",
    "groupCounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "// Alternatively find the sum of the values in each group in Ints\n",
    "DataFrame intsGroupSum = groupBy.Sum(\"Ints\");\n",
    "intsGroupSum"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "using XPlot.Plotly;\n",
    "using System.Linq;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "#r \"nuget:MathNet.Numerics,4.9.0\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "using MathNet.Numerics.Distributions;\n",
    "double mean = 0;\n",
    "double stdDev = 0.1;\n",
    "\n",
    "MathNet.Numerics.Distributions.Normal normalDist = new Normal(mean, stdDev);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "PrimitiveDataFrameColumn<double> doubles = new PrimitiveDataFrameColumn<double>(\"Normal Distribution\", normalDist.Samples().Take(1000));\n",
    "display(Chart.Plot(\n",
    "    new Histogram()\n",
    "    {\n",
    "        x = doubles,\n",
    "        nbinsx = 30\n",
    "    }\n",
    "));"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".NET (C#)",
   "language": "C#",
   "name": ".net-csharp"
  },
  "language_info": {
   "file_extension": ".cs",
   "mimetype": "text/x-csharp",
   "name": "C#",
   "pygments_lexer": "csharp",
   "version": "8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}