{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "parameters"
    ]
   },
   "outputs": [],
   "source": [
    "flex_title = \"Altair plots\"\n",
    "flex_author = \"built using jupyter-flex\"\n",
    "flex_source_link = \"https://github.com/danielfrg/jupyter-flex/blob/master/examples/plots/altair.ipynb\"\n",
    "flex_include_source = True"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Simple charts"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Simple Scatter Plot with Tooltips"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import altair as alt\n",
    "from vega_datasets import data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "alt.renderers.set_embed_options(actions=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "np.random.seed(42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.cars()\n",
    "\n",
    "plot = alt.Chart(source).mark_circle(size=60).encode(\n",
    "    x='Horsepower',\n",
    "    y='Miles_per_Gallon',\n",
    "    color='Origin',\n",
    "    tooltip=['Name', 'Origin', 'Horsepower', 'Miles_per_Gallon']\n",
    ")\n",
    "plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "plot.properties(\n",
    "    width='container',\n",
    "    height='container'\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Col 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Simple bar chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "source = pd.DataFrame({\n",
    "    'a': ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I'],\n",
    "    'b': [28, 55, 43, 91, 81, 53, 19, 87, 52]\n",
    "})\n",
    "\n",
    "plot = alt.Chart(source).mark_bar().encode(\n",
    "    x='a',\n",
    "    y='b'\n",
    ")\n",
    "plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "plot.properties(\n",
    "    width='container',\n",
    "    height='container'\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Simple Heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "# Compute x^2 + y^2 across a 2D grid\n",
    "x, y = np.meshgrid(range(-5, 5), range(-5, 5))\n",
    "z = x ** 2 + y ** 2\n",
    "\n",
    "# Convert this grid to columnar data expected by Altair\n",
    "source = pd.DataFrame({'x': x.ravel(),\n",
    "                     'y': y.ravel(),\n",
    "                     'z': z.ravel()})\n",
    "\n",
    "plot = alt.Chart(source).mark_rect().encode(\n",
    "    x='x:O',\n",
    "    y='y:O',\n",
    "    color='z:Q'\n",
    ")\n",
    "plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "plot.properties(\n",
    "    width='container',\n",
    "    height='container'\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bar Charts"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Bar Chart with Negative Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body",
     "source"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.us_employment()\n",
    "\n",
    "alt.Chart(source).mark_bar().encode(\n",
    "    x=\"month:T\",\n",
    "    y=\"nonfarm_change:Q\",\n",
    "    color=alt.condition(\n",
    "        alt.datum.nonfarm_change > 0,\n",
    "        alt.value(\"steelblue\"),  # The positive color\n",
    "        alt.value(\"orange\")  # The negative color\n",
    "    )\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Horizontal Bar Chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.wheat()\n",
    "\n",
    "alt.Chart(source).mark_bar().encode(\n",
    "    x='wheat:Q',\n",
    "    y=\"year:O\"\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Col 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Stacked Bar Chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.barley()\n",
    "\n",
    "alt.Chart(source).mark_bar().encode(\n",
    "    x='variety',\n",
    "    y='sum(yield)',\n",
    "    color='site'\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Line and Area Charts"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Filled Step Chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.stocks()\n",
    "\n",
    "alt.Chart(source).mark_area(\n",
    "    color=\"lightblue\",\n",
    "    interpolate='step-after',\n",
    "    line=True\n",
    ").encode(\n",
    "    x='date',\n",
    "    y='price'\n",
    ").transform_filter(alt.datum.symbol == 'GOOG').properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Multi Series Line Chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.stocks()\n",
    "\n",
    "alt.Chart(source).mark_line().encode(\n",
    "    x='date',\n",
    "    y='price',\n",
    "    color='symbol'\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Col 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Cumulative Count Chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.movies.url\n",
    "\n",
    "alt.Chart(source).transform_window(\n",
    "    cumulative_count=\"count()\",\n",
    "    sort=[{\"field\": \"IMDB_Rating\"}],\n",
    ").mark_area().encode(\n",
    "    x=\"IMDB_Rating:Q\",\n",
    "    y=\"cumulative_count:Q\"\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Stacked Density Estimates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.iris()\n",
    "\n",
    "alt.Chart(source).transform_fold(\n",
    "    ['petalWidth',\n",
    "     'petalLength',\n",
    "     'sepalWidth',\n",
    "     'sepalLength'],\n",
    "    as_ = ['Measurement_type', 'value']\n",
    ").transform_density(\n",
    "    density='value',\n",
    "    bandwidth=0.3,\n",
    "    groupby=['Measurement_type'],\n",
    "    extent= [0, 8],\n",
    "    counts = True,\n",
    "    steps=200\n",
    ").mark_area().encode(\n",
    "    alt.X('value:Q'),\n",
    "    alt.Y('density:Q', stack='zero'),\n",
    "    alt.Color('Measurement_type:N')\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scatter and Maps"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Binned Scatterplot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.movies.url\n",
    "\n",
    "alt.Chart(source).mark_circle().encode(\n",
    "    alt.X('IMDB_Rating:Q', bin=True),\n",
    "    alt.Y('Rotten_Tomatoes_Rating:Q', bin=True),\n",
    "    size='count()'\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Multifeature Scatter Plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.iris()\n",
    "\n",
    "alt.Chart(source).mark_circle().encode(\n",
    "    alt.X('sepalLength', scale=alt.Scale(zero=False)),\n",
    "    alt.Y('sepalWidth', scale=alt.Scale(zero=False, padding=1)),\n",
    "    color='species',\n",
    "    size='petalWidth'\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Col 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Choropleth Map"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "from vega_datasets import data\n",
    "\n",
    "counties = alt.topo_feature(data.us_10m.url, 'counties')\n",
    "source = data.unemployment.url\n",
    "\n",
    "alt.Chart(counties).mark_geoshape().encode(\n",
    "    color='rate:Q'\n",
    ").transform_lookup(\n",
    "    lookup='id',\n",
    "    from_=alt.LookupData(source, 'id', ['rate'])\n",
    ").project(\n",
    "    type='albersUsa'\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Layered Histogram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "# Generating Data\n",
    "source = pd.DataFrame({\n",
    "    'Trial A': np.random.normal(0, 0.8, 1000),\n",
    "    'Trial B': np.random.normal(-2, 1, 1000),\n",
    "    'Trial C': np.random.normal(3, 2, 1000)\n",
    "})\n",
    "\n",
    "alt.Chart(source).transform_fold(\n",
    "    ['Trial A', 'Trial B', 'Trial C'],\n",
    "    as_=['Experiment', 'Measurement']\n",
    ").mark_area(\n",
    "    opacity=0.3,\n",
    "    interpolate='step'\n",
    ").encode(\n",
    "    alt.X('Measurement:Q', bin=alt.Bin(maxbins=100)),\n",
    "    alt.Y('count()', stack=None),\n",
    "    alt.Color('Experiment:N')\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scatter Matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.cars()\n",
    "\n",
    "alt.Chart(source).mark_circle().encode(\n",
    "    alt.X(alt.repeat(\"column\"), type='quantitative'),\n",
    "    alt.Y(alt.repeat(\"row\"), type='quantitative'),\n",
    "    color='Origin:N'\n",
    ").repeat(\n",
    "    row=['Horsepower', 'Acceleration', 'Miles_per_Gallon'],\n",
    "    column=['Miles_per_Gallon', 'Acceleration', 'Horsepower']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Faceted Density Estimates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.iris()\n",
    "\n",
    "alt.Chart(source).transform_fold(\n",
    "    ['petalWidth',\n",
    "     'petalLength',\n",
    "     'sepalWidth',\n",
    "     'sepalLength'],\n",
    "    as_ = ['Measurement_type', 'value']\n",
    ").transform_density(\n",
    "    density='value',\n",
    "    bandwidth=0.3,\n",
    "    groupby=['Measurement_type'],\n",
    "    extent= [0, 8]\n",
    ").mark_area().encode(\n",
    "    alt.X('value:Q'),\n",
    "    alt.Y('density:Q'),\n",
    "    alt.Row('Measurement_type:N')\n",
    ").properties(width=600, height=180)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Interactive "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Interactive Crossfilter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = alt.UrlData(\n",
    "    data.flights_2k.url,\n",
    "    format={'parse': {'date': 'date'}}\n",
    ")\n",
    "\n",
    "brush = alt.selection(type='interval', encodings=['x'])\n",
    "\n",
    "# Define the base chart, with the common parts of the\n",
    "# background and highlights\n",
    "base = alt.Chart().mark_bar().encode(\n",
    "    x=alt.X(alt.repeat('column'), type='quantitative', bin=alt.Bin(maxbins=20)),\n",
    "    y='count()'\n",
    ").properties(\n",
    "    width=200,\n",
    "    height=300\n",
    ")\n",
    "\n",
    "# gray background with selection\n",
    "background = base.encode(\n",
    "    color=alt.value('#ddd')\n",
    ").add_selection(brush)\n",
    "\n",
    "# blue highlights on the transformed data\n",
    "highlight = base.transform_filter(brush)\n",
    "\n",
    "# layer the two charts & repeat\n",
    "alt.layer(\n",
    "    background,\n",
    "    highlight,\n",
    "    data=source\n",
    ").transform_calculate(\n",
    "    \"time\",\n",
    "    \"hours(datum.date)\"\n",
    ").repeat(column=[\"distance\", \"delay\", \"time\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Scatter Plot and Histogram with Interval Selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "x = np.random.normal(size=100)\n",
    "y = np.random.normal(size=100)\n",
    "\n",
    "m = np.random.normal(15, 1, size=100)\n",
    "\n",
    "source = pd.DataFrame({\"x\": x, \"y\":y, \"m\":m})\n",
    "\n",
    "# interval selection in the scatter plot\n",
    "pts = alt.selection(type=\"interval\", encodings=[\"x\"])\n",
    "\n",
    "# left panel: scatter plot\n",
    "points = alt.Chart().mark_point(filled=True, color=\"black\").encode(\n",
    "    x='x',\n",
    "    y='y'\n",
    ").transform_filter(\n",
    "    pts\n",
    ").properties(\n",
    "    width=300,\n",
    "    height=300\n",
    ")\n",
    "\n",
    "# right panel: histogram\n",
    "mag = alt.Chart().mark_bar().encode(\n",
    "    x='mbin:N',\n",
    "    y=\"count()\",\n",
    "    color=alt.condition(pts, alt.value(\"black\"), alt.value(\"lightgray\"))\n",
    ").properties(\n",
    "    width=300,\n",
    "    height=300\n",
    ").add_selection(pts)\n",
    "\n",
    "# build the chart:\n",
    "alt.hconcat(\n",
    "    points,\n",
    "    mag,\n",
    "    data=source\n",
    ").transform_bin(\n",
    "    \"mbin\",\n",
    "    field=\"m\",\n",
    "    bin=alt.Bin(maxbins=20)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Col 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Interactive average"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.seattle_weather()\n",
    "brush = alt.selection(type='interval', encodings=['x'])\n",
    "\n",
    "bars = alt.Chart().mark_bar().encode(\n",
    "    x='month(date):O',\n",
    "    y='mean(precipitation):Q',\n",
    "    opacity=alt.condition(brush, alt.OpacityValue(1), alt.OpacityValue(0.7)),\n",
    ").add_selection(\n",
    "    brush\n",
    ").properties(width=700, height=300)\n",
    "\n",
    "line = alt.Chart().mark_rule(color='firebrick').encode(\n",
    "    y='mean(precipitation):Q',\n",
    "    size=alt.SizeValue(3)\n",
    ").transform_filter(\n",
    "    brush\n",
    ").properties(width=700, height=300)\n",
    "\n",
    "alt.layer(bars, line, data=source)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Interactive Legend"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "body"
    ]
   },
   "outputs": [],
   "source": [
    "source = data.unemployment_across_industries.url\n",
    "\n",
    "selection = alt.selection_multi(fields=['series'], bind='legend')\n",
    "\n",
    "alt.Chart(source).mark_area().encode(\n",
    "    alt.X('yearmonth(date):T', axis=alt.Axis(domain=False, format='%Y', tickSize=0)),\n",
    "    alt.Y('sum(count):Q', stack='center', axis=None),\n",
    "    alt.Color('series:N', scale=alt.Scale(scheme='category20b')),\n",
    "    opacity=alt.condition(selection, alt.value(1), alt.value(0.2))\n",
    ").properties(\n",
    "    width=\"container\",\n",
    "    height=\"container\"\n",
    ").add_selection(\n",
    "    selection\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "celltoolbar": "Tags",
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}