{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "respective-store",
   "metadata": {},
   "source": [
    "# In Class Notebook, Week 06"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a597611",
   "metadata": {},
   "source": [
    "You can click on the GitHub URL of this notebook to access the file in near-real time: https://github.com/UIUC-iSchool-DataViz/is445_bcubcg_fall2024/blob/master/week06/inClass_week06.ipynb \n",
    "\n",
    "Or you can copy-paste into the nbviewer interface for a plain-text rendering:\n",
    "\n",
    "https://kokes.github.io/nbviewer.js/viewer.html"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d799951d-c8d2-4248-93be-351087fb4429",
   "metadata": {},
   "source": [
    "## Hints for HW3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bb28494f-8697-4560-94e8-511584737297",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "87cfb925-6502-4682-9400-2157a94d5085",
   "metadata": {},
   "outputs": [],
   "source": [
    "bf = pd.read_csv('https://raw.githubusercontent.com/UIUC-iSchool-DataViz/is445_bcubcg_fall2022/main/data/bfro_reports_fall2022.csv',\n",
    "                parse_dates = ['date'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c8e6d12c-fde6-4046-a634-d037070575e1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>observed</th>\n",
       "      <th>location_details</th>\n",
       "      <th>county</th>\n",
       "      <th>state</th>\n",
       "      <th>season</th>\n",
       "      <th>title</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>date</th>\n",
       "      <th>number</th>\n",
       "      <th>...</th>\n",
       "      <th>precip_intensity</th>\n",
       "      <th>precip_probability</th>\n",
       "      <th>precip_type</th>\n",
       "      <th>pressure</th>\n",
       "      <th>summary</th>\n",
       "      <th>uv_index</th>\n",
       "      <th>visibility</th>\n",
       "      <th>wind_bearing</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Ed L. was salmon fishing with a companion in P...</td>\n",
       "      <td>East side of Prince William Sound</td>\n",
       "      <td>Valdez-Chitina-Whittier County</td>\n",
       "      <td>Alaska</td>\n",
       "      <td>Fall</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaT</td>\n",
       "      <td>1261.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>heh i kinda feel a little dumb that im reporti...</td>\n",
       "      <td>the road is off us rt 80, i dont know the exit...</td>\n",
       "      <td>Warren County</td>\n",
       "      <td>New Jersey</td>\n",
       "      <td>Fall</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaT</td>\n",
       "      <td>438.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>I was on my way to Claremont from Lebanon on R...</td>\n",
       "      <td>Close to Claremont down 120 not far from Kings...</td>\n",
       "      <td>Sullivan County</td>\n",
       "      <td>New Hampshire</td>\n",
       "      <td>Summer</td>\n",
       "      <td>Report 55269: Dawn sighting at Stevens Brook o...</td>\n",
       "      <td>43.41549</td>\n",
       "      <td>-72.33093</td>\n",
       "      <td>2016-06-07</td>\n",
       "      <td>55269.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.001</td>\n",
       "      <td>0.7</td>\n",
       "      <td>rain</td>\n",
       "      <td>998.87</td>\n",
       "      <td>Mostly cloudy throughout the day.</td>\n",
       "      <td>6.0</td>\n",
       "      <td>9.70</td>\n",
       "      <td>262.0</td>\n",
       "      <td>0.49</td>\n",
       "      <td>POINT(-72.33093000000001 43.415490000000005)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>I was northeast of Macy Nebraska along the Mis...</td>\n",
       "      <td>Latitude &amp; Longitude :  42.158230  -96.344197</td>\n",
       "      <td>Thurston County</td>\n",
       "      <td>Nebraska</td>\n",
       "      <td>Spring</td>\n",
       "      <td>Report 59757: Possible daylight sighting of a ...</td>\n",
       "      <td>42.15685</td>\n",
       "      <td>-96.34203</td>\n",
       "      <td>2018-05-25</td>\n",
       "      <td>59757.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1008.07</td>\n",
       "      <td>Partly cloudy in the morning.</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.25</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3.33</td>\n",
       "      <td>POINT(-96.34203000000001 42.15685)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>While this incident occurred a long time ago, ...</td>\n",
       "      <td>Ward County, Just outside of a the Minuteman T...</td>\n",
       "      <td>Ward County</td>\n",
       "      <td>North Dakota</td>\n",
       "      <td>Spring</td>\n",
       "      <td>Report 751: Hunter describes described being s...</td>\n",
       "      <td>48.25422</td>\n",
       "      <td>-101.31660</td>\n",
       "      <td>2000-04-21</td>\n",
       "      <td>751.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>rain</td>\n",
       "      <td>1011.47</td>\n",
       "      <td>Partly cloudy until evening.</td>\n",
       "      <td>6.0</td>\n",
       "      <td>10.00</td>\n",
       "      <td>237.0</td>\n",
       "      <td>11.14</td>\n",
       "      <td>POINT(-101.3166 48.254220000000004)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 29 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            observed  \\\n",
       "0  Ed L. was salmon fishing with a companion in P...   \n",
       "1  heh i kinda feel a little dumb that im reporti...   \n",
       "2  I was on my way to Claremont from Lebanon on R...   \n",
       "3  I was northeast of Macy Nebraska along the Mis...   \n",
       "4  While this incident occurred a long time ago, ...   \n",
       "\n",
       "                                    location_details  \\\n",
       "0                  East side of Prince William Sound   \n",
       "1  the road is off us rt 80, i dont know the exit...   \n",
       "2  Close to Claremont down 120 not far from Kings...   \n",
       "3      Latitude & Longitude :  42.158230  -96.344197   \n",
       "4  Ward County, Just outside of a the Minuteman T...   \n",
       "\n",
       "                           county          state  season  \\\n",
       "0  Valdez-Chitina-Whittier County         Alaska    Fall   \n",
       "1                   Warren County     New Jersey    Fall   \n",
       "2                 Sullivan County  New Hampshire  Summer   \n",
       "3                 Thurston County       Nebraska  Spring   \n",
       "4                     Ward County   North Dakota  Spring   \n",
       "\n",
       "                                               title  latitude  longitude  \\\n",
       "0                                                NaN       NaN        NaN   \n",
       "1                                                NaN       NaN        NaN   \n",
       "2  Report 55269: Dawn sighting at Stevens Brook o...  43.41549  -72.33093   \n",
       "3  Report 59757: Possible daylight sighting of a ...  42.15685  -96.34203   \n",
       "4  Report 751: Hunter describes described being s...  48.25422 -101.31660   \n",
       "\n",
       "        date   number  ... precip_intensity precip_probability  precip_type  \\\n",
       "0        NaT   1261.0  ...              NaN                NaN          NaN   \n",
       "1        NaT    438.0  ...              NaN                NaN          NaN   \n",
       "2 2016-06-07  55269.0  ...            0.001                0.7         rain   \n",
       "3 2018-05-25  59757.0  ...            0.000                0.0          NaN   \n",
       "4 2000-04-21    751.0  ...              NaN                NaN         rain   \n",
       "\n",
       "   pressure                            summary  uv_index  visibility  \\\n",
       "0       NaN                                NaN       NaN         NaN   \n",
       "1       NaN                                NaN       NaN         NaN   \n",
       "2    998.87  Mostly cloudy throughout the day.       6.0        9.70   \n",
       "3   1008.07      Partly cloudy in the morning.      10.0        8.25   \n",
       "4   1011.47       Partly cloudy until evening.       6.0       10.00   \n",
       "\n",
       "   wind_bearing  wind_speed                                      location  \n",
       "0           NaN         NaN                                           NaN  \n",
       "1           NaN         NaN                                           NaN  \n",
       "2         262.0        0.49  POINT(-72.33093000000001 43.415490000000005)  \n",
       "3         193.0        3.33            POINT(-96.34203000000001 42.15685)  \n",
       "4         237.0       11.14           POINT(-101.3166 48.254220000000004)  \n",
       "\n",
       "[5 rows x 29 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c6d6c22c-9b4c-4a78-a306-fabe8bfb1296",
   "metadata": {},
   "source": [
    "Check out downsampling for large datasets in the prep notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f5052fc0-fada-49f5-80b7-7fa379be61a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4219f3bd-8528-4610-af4c-bae28f3017cb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x16e471b40>]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(bf['longitude'], bf['latitude'], '.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ca412c97-98c7-418a-b8b1-365e62db442c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x16e569090>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(bf['longitude'], bf['latitude'], c=np.log10(bf['pressure']), cmap='rainbow')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "315b2429-dabb-4f63-99fc-177653eec1a6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x200 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(10,2))\n",
    "bf.hist(column='longitude', ax=ax, bins=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ecf2e517-3b3b-4133-8b35-c0a0db62e516",
   "metadata": {},
   "source": [
    "## Review of ipywidgets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2d69b682-44e4-4fa1-8727-ec4a0c9a8721",
   "metadata": {},
   "outputs": [],
   "source": [
    "import ipywidgets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "56b830ac-18f9-44d4-9701-4f479b967975",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8d6e707989b04a5ca1bec54dc39f40b8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "IntSlider(value=0, max=10, orientation='vertical')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "islider = ipywidgets.IntSlider(min=0,max=10,step=1,orientation='vertical')\n",
    "islider"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8e7b3b93-0eae-4174-8363-e8c6f7a2df8a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1d7ef6b7c6ef4f4e9bc0ecd1747f397d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "ColorPicker(value='black')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cp = ipywidgets.ColorPicker()\n",
    "cp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d30e2249-02c2-4e4f-8c8a-a47bec099a92",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<traitlets.traitlets.link at 0x16e77a290>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ipywidgets.link( (cp, 'value'), (islider.style, 'handle_color') )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ba487639-bbc1-4d77-b5ef-07d717773e6a",
   "metadata": {},
   "outputs": [],
   "source": [
    "class MyObject():\n",
    "    name = 'unnamed'\n",
    "    age = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5bc695b2-f117-4712-b16c-b2fc74ce85e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_obj = MyObject()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "998ac113-2955-4329-8911-829865d847bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'unnamed'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_obj.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "03197b77-21e6-41f7-9d53-c700f815d300",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_obj.age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "8d14d972-1ef1-41ab-a55e-bbef50776326",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_obj.name = 'Bob'\n",
    "my_obj.age = 47"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "505908d3-a5a7-4a9a-877f-1edbadfa030d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Bob', 47)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_obj.name, my_obj.age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "44a9d4ee-4ff5-4a95-ac73-f9a1cd9f4058",
   "metadata": {},
   "outputs": [],
   "source": [
    "import traitlets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "147829ea-dd91-4393-9e3c-66a40fa1dbf3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# class MyObject():\n",
    "#     name = 'unnamed'\n",
    "#     age = 0\n",
    "\n",
    "class MyTraitletsObject(traitlets.HasTraits):\n",
    "    name = traitlets.Unicode('unnamed')\n",
    "    age = traitlets.Int(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "8e22e788-b79b-4a1b-9699-aeeea77fd0ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_t_obj = MyTraitletsObject()\n",
    "my_t_obj.name = 'Bob'\n",
    "my_t_obj.age = 47"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "aac21ccc-a191-42aa-b320-26e0fb6537a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Bob', 47)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_t_obj.name, my_t_obj.age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c17454d8-9994-465e-a22d-49266d8802ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "def name_changed(change):\n",
    "    print(change)\n",
    "\n",
    "my_t_obj.observe(name_changed, ['name'])\n",
    "# .observe is similar to .on_click we used for buttons\n",
    "# 'name' here is the trait we want to watch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "07b2eacb-ea27-40cd-aefb-70f16247c23c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'name': 'name', 'old': 'Bob', 'new': 'Linda', 'owner': <__main__.MyTraitletsObject object at 0x16e77a650>, 'type': 'change'}\n"
     ]
    }
   ],
   "source": [
    "my_t_obj.name = 'Linda'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "96146e50-052e-46ef-9ba2-2a1f33577523",
   "metadata": {},
   "outputs": [],
   "source": [
    "def name_change2(change):\n",
    "    #print('Hello my name is', change['owner'].name, 'and I am', change['owner'].age, 'years old.')\n",
    "    print('Hello my name is', change['new'], 'and I am', change['owner'].age, 'years old.')\n",
    "\n",
    "my_t_obj.observe(name_change2, ['name'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "db671514-bb41-41f2-b07b-8d8652b78f50",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'name': 'name', 'old': 'Linda', 'new': 'Bob', 'owner': <__main__.MyTraitletsObject object at 0x16e77a650>, 'type': 'change'}\n",
      "Hello my name is Bob and I am 47 years old.\n"
     ]
    }
   ],
   "source": [
    "my_t_obj.name = 'Bob'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "a2706636-9157-4a02-8387-47d35a39a30d",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_t_obj.unobserve(name_changed, ['name'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "99a05fb1-66e9-4a72-8f53-063f627b1ba6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello my name is Linda and I am 47 years old.\n"
     ]
    }
   ],
   "source": [
    "my_t_obj.name = 'Linda'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "2ca48843-4af2-4ef5-b8f2-6f47d7579258",
   "metadata": {},
   "outputs": [],
   "source": [
    "# try with changing age\n",
    "def age_change(change):\n",
    "    print('Hello my name is', change['owner'].name, 'and I am', change['new'], 'years old.')\n",
    "\n",
    "my_t_obj.observe(age_change, ['age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "1dae7d27-847e-4c18-b324-6a9fe060f15c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello my name is Linda and I am 45 years old.\n"
     ]
    }
   ],
   "source": [
    "my_t_obj.age = 45"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "8844c844-9afc-4fc2-b792-0d17246e86b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_t_obj.name = 'Linda'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "444c7c96-7efe-4f59-a1ac-7a1b086b37e6",
   "metadata": {},
   "source": [
    "# Bqplot intro"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "f1b958ae-54a2-4cac-8a80-4457ecd4f75e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import bqplot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "88669b61-1d11-40be-8bb1-adc55323a051",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. Data\n",
    "x = np.arange(100)\n",
    "y = np.random.random(100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "b7283898-5858-41f3-8b03-8f50d4b54002",
   "metadata": {},
   "outputs": [],
   "source": [
    "#x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "ec57f4e7-a865-4e9b-8ce8-cc623e5a21db",
   "metadata": {},
   "outputs": [],
   "source": [
    "#y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "1c10ec28-38f5-45d7-a5d6-90d83f5fd288",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[0;31mInit signature:\u001b[0m \u001b[0mbqplot\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLinearScale\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mDocstring:\u001b[0m     \n",
       "A linear scale.\n",
       "\n",
       "An affine mapping from a numerical domain to a numerical range.\n",
       "\n",
       "Attributes\n",
       "----------\n",
       "min: float or None (default: None)\n",
       "    if not None, min is the minimal value of the domain\n",
       "max: float or None (default: None)\n",
       "    if not None, max is the maximal value of the domain\n",
       "rtype: string (class-level attribute)\n",
       "    This attribute should not be modified. The range type of a linear\n",
       "    scale is numerical.\n",
       "dtype: type (class-level attribute)\n",
       "    the associated data type / domain type\n",
       "precedence: int (class-level attribute, default_value=2)\n",
       "    attribute used to determine which scale takes precedence in cases when\n",
       "    two or more scales have the same rtype and dtype.\n",
       "    default_value is 2 because for the same range and domain types,\n",
       "    LinearScale should take precedence.\n",
       "stabilized: bool (default: False)\n",
       "    if set to False, the domain of the scale is tied to the data range\n",
       "    if set to True, the domain of the scale is updated only when\n",
       "    the data range is beyond certain thresholds, given by the attributes\n",
       "    mid_range and min_range.\n",
       "mid_range: float (default: 0.8)\n",
       "    Proportion of the range that is spanned initially.\n",
       "    Used only if stabilized is True.\n",
       "min_range: float (default: 0.6)\n",
       "    Minimum proportion of the range that should be spanned by the data.\n",
       "    If the data span falls beneath that level, the scale is reset.\n",
       "    min_range must be <= mid_range.\n",
       "    Used only if stabilized is True.\n",
       "\u001b[0;31mInit docstring:\u001b[0m Public constructor\n",
       "\u001b[0;31mFile:\u001b[0m           /opt/anaconda3/envs/DataViz2/lib/python3.10/site-packages/bqplot/scales.py\n",
       "\u001b[0;31mType:\u001b[0m           MetaHasTraits\n",
       "\u001b[0;31mSubclasses:\u001b[0m     "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. Scales\n",
    "bqplot.LinearScale?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "cafc7f9f-c0ae-4eac-9357-9e3fbf3c4ad6",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_sc = bqplot.LinearScale()\n",
    "y_sc = bqplot.LinearScale()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "44295e62-05e1-480a-b01b-5331de266862",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 3. Axis (sometimes will be marks, depending on how we are feeling!)\n",
    "#bqplot.Axis?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "b5bf90bc-223a-473a-9bf7-b9b98438d52c",
   "metadata": {},
   "outputs": [],
   "source": [
    "ax_x = bqplot.Axis(scale=x_sc, label='X Value')\n",
    "ax_y = bqplot.Axis(scale=y_sc, label='Y Value', orientation='vertical')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "4892cd44-df7b-46e1-819f-abfd5878502d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 4. Marks (sometimes will swap with Axis)\n",
    "#bqplot.Lines?\n",
    "lines = bqplot.Lines(x=x, y=y, scales = {'x':x_sc, 'y':y_sc})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "975e48e0-e450-44c9-ba4f-b2e85112f8af",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 5. around here is where we would add interactivity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "20df05ff-2f90-4401-9e7a-3a799937c0e8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8caf4ee2e4264b51b32722afc0745976",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[Axis(label='X Value', scale=LinearScale(), side='bottom'), Axis(label='Y Value', orientation='ver…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 6. Put it all together as a figure\n",
    "fig = bqplot.Figure(marks=[lines], axes=[ax_x, ax_y])\n",
    "fig"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "82172a27-aba6-425d-9b39-c3a6da59463d",
   "metadata": {},
   "source": [
    "One more time, but all together:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "51ab7c2b-4b87-40bc-8c8b-b255ad77afaf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d3cb94594c994cbab437d1e86241561b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[Axis(label='X Value', scale=LinearScale()), Axis(label='Y Value', orientation='vertical', scale=L…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 1. Data\n",
    "x = np.arange(100)\n",
    "y = np.random.random(100)\n",
    "\n",
    "# 2. Scales\n",
    "x_sc = bqplot.LinearScale()\n",
    "y_sc = bqplot.LinearScale()\n",
    "\n",
    "# 3. Axis (sometimes will be marks, depending on how we are feeling!)\n",
    "ax_x = bqplot.Axis(scale=x_sc, label='X Value')\n",
    "ax_y = bqplot.Axis(scale=y_sc, label='Y Value', orientation='vertical')\n",
    "\n",
    "# 4. Marks (sometimes will swap with Axis)\n",
    "lines = bqplot.Lines(x=x, y=y, scales = {'x':x_sc, 'y':y_sc})\n",
    "\n",
    "# 5. add in interactivity\n",
    "pz = bqplot.interacts.PanZoom(scales = {'x':[x_sc], 'y':[y_sc]})\n",
    "\n",
    "# 6. Put it all together as a figure\n",
    "fig = bqplot.Figure(marks=[lines], axes=[ax_x, ax_y], interaction=pz)\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "412ace27-4baa-40e1-9ec9-33d271c56885",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[0;31mInit signature:\u001b[0m \u001b[0mbqplot\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minteracts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mPanZoom\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mDocstring:\u001b[0m     \n",
       "An interaction to pan and zoom wrt scales.\n",
       "\n",
       "Attributes\n",
       "----------\n",
       "allow_pan: bool (default: True)\n",
       "    Toggle the ability to pan.\n",
       "allow_zoom: bool (default: True)\n",
       "    Toggle the ability to zoom.\n",
       "scales: Dictionary of lists of Scales (default: {})\n",
       "    Dictionary with keys such as 'x' and 'y' and values being the scales in\n",
       "    the corresponding direction (dimensions) which should be panned or\n",
       "    zoomed.\n",
       "\u001b[0;31mInit docstring:\u001b[0m Public constructor\n",
       "\u001b[0;31mFile:\u001b[0m           /opt/anaconda3/envs/DataViz2/lib/python3.10/site-packages/bqplot/interacts.py\n",
       "\u001b[0;31mType:\u001b[0m           MetaHasTraits\n",
       "\u001b[0;31mSubclasses:\u001b[0m     "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bqplot.interacts.PanZoom?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0740d24-7df3-4d5a-b129-27f7563e1788",
   "metadata": {},
   "source": [
    "### Random scatter plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "92c3a886-7dfc-4153-8088-9f2c1f8cf5bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. Data\n",
    "x = np.random.random(100)\n",
    "y = np.random.random(100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "998f85f3-4f2a-45be-92be-6c831bbeff4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2. scales\n",
    "x_sc = bqplot.LinearScale()\n",
    "y_sc = bqplot.LinearScale()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "e69ee21a-65db-43ea-8608-d684bbd09326",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 3. axis\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='X')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Y', orientation = 'vertical')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "d2cd5e0e-0c3b-4aaa-89ba-b2eb6162cbc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "#bqplot.Scatter?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "a44273da-cdfc-444d-8a2d-d562d8fc67ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 4. marks\n",
    "scatters = bqplot.Scatter(x=x, y=y, scales={'x':x_sc, 'y':y_sc})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "6160d1cd-b12a-47d1-9237-47f0c33449e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 5. interactivity -- just a moment!\n",
    "#bqplot.interacts.FastIntervalSelector?\n",
    "pz = bqplot.interacts.PanZoom(scales = {'x':[x_sc], 'y':[y_sc]})\n",
    "selector = bqplot.interacts.FastIntervalSelector(scale=x_sc, marks=[scatters])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "93ea0a1a-8225-436b-9654-f2da7c96a92d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fa85ea36fe5d4596a3c0b595c98c736f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[Axis(label='X', scale=LinearScale(), side='bottom'), Axis(label='Y', orientation='vertical', scal…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 6. together as a figure\n",
    "#fig = bqplot.Figure(marks=[scatters], axes=[x_ax,y_ax], interaction=[selector,pz]) # TBD, multipl interactions\n",
    "# could be issue with mouse-use for multiples?\n",
    "fig = bqplot.Figure(marks=[scatters], axes=[x_ax,y_ax], interaction=selector)\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "39e3c4c5-13fc-4ad0-a873-dc6c9dbf8b02",
   "metadata": {},
   "outputs": [],
   "source": [
    "selector.selected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "b2941ba6-133e-4998-a55b-61084d68a402",
   "metadata": {},
   "outputs": [],
   "source": [
    "scatters.selected_style = {'fill':'red', 'stroke':'yellow'}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "993f1a99-d490-47bc-a4b0-4e0721cc1645",
   "metadata": {},
   "source": [
    "## 2D Heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "d2dc6c7e-35c1-4226-a23b-fa2f75c5445f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. data\n",
    "data = np.random.random((10,10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "b306c351-edc0-4307-b3e3-2a53e0907b06",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10, 10)"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "c72165da-6428-4bdb-b1f4-faa929ee91db",
   "metadata": {},
   "outputs": [],
   "source": [
    "#bqplot.ColorScale?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "9d57971c-510f-412e-9003-da2c47697d21",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d0f93aaba190474c8981223f9a3382fc",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(fig_margin={'top': 60, 'bottom': 60, 'left': 60, 'right': 60}, marks=[GridHeatMap(color=array([[0.52709…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale()\n",
    "\n",
    "# 3. Axis (skip)\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc})\n",
    "\n",
    "# 5. interactivity\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "6fb5ef52-4ee5-4829-a8e6-810305a43652",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[0;31mInit signature:\u001b[0m \u001b[0mbqplot\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGridHeatMap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mDocstring:\u001b[0m     \n",
       "GridHeatMap mark.\n",
       "\n",
       "Alignment: The tiles can be aligned so that the data matches either the\n",
       "start, the end or the midpoints of the tiles. This is controlled by the\n",
       "align attribute.\n",
       "\n",
       "Suppose the data passed is a m-by-n matrix. If the scale for the rows is\n",
       "Ordinal, then alignment is by default the mid points. For a non-ordinal\n",
       "scale, the data cannot be aligned to the mid points of the rectangles.\n",
       "\n",
       "If it is not ordinal, then two cases arise. If the number of rows passed\n",
       "is m, then align attribute can be used. If the number of rows passed\n",
       "is m+1, then the data are the boundaries of the m rectangles.\n",
       "\n",
       "If rows and columns are not passed, and scales for them are also\n",
       "not passed, then ordinal scales are generated for the rows and columns.\n",
       "\n",
       "Attributes\n",
       "----------\n",
       "row_align: Enum(['start', 'end'])\n",
       "    This is only valid if the number of entries in `row` exactly match the\n",
       "    number of rows in `color` and the `row_scale` is not `OrdinalScale`.\n",
       "    `start` aligns the row values passed to be aligned with the start\n",
       "    of the tiles and `end` aligns the row values to the end of the tiles.\n",
       "column_align: Enum(['start', end'])\n",
       "    This is only valid if the number of entries in `column` exactly\n",
       "    match the number of columns in `color` and the `column_scale` is\n",
       "    not `OrdinalScale`. `start` aligns the column values passed to\n",
       "    be aligned with the start of the tiles and `end` aligns the\n",
       "    column values to the end of the tiles.\n",
       "anchor_style: dict (default: {})\n",
       "    Controls the style for the element which serves as the anchor during\n",
       "    selection.\n",
       "display_format: string (default: None)\n",
       "    format for displaying values. If None, then values are not displayed\n",
       "font_style: dict\n",
       "    CSS style for the text of each cell\n",
       "\n",
       "Data Attributes\n",
       "\n",
       "color: numpy.ndarray or None (default: None)\n",
       "    color of the data points (2d array). The number of elements in\n",
       "    this array correspond to the number of cells created in the heatmap.\n",
       "row: numpy.ndarray or None (default: None)\n",
       "    labels for the rows of the `color` array passed. The length of\n",
       "    this can be no more than 1 away from the number of rows in `color`.\n",
       "    This is a scaled attribute and can be used to affect the height of the\n",
       "    cells as the entries of `row` can indicate the start or the end points\n",
       "    of the cells. Refer to the property `row_align`.\n",
       "    If this property is None, then a uniformly spaced grid is generated in\n",
       "    the row direction.\n",
       "column: numpy.ndarray or None (default: None)\n",
       "    labels for the columns of the `color` array passed. The length of\n",
       "    this can be no more than 1 away from the number of columns in `color`\n",
       "    This is a scaled attribute and can be used to affect the width of the\n",
       "    cells as the entries of `column` can indicate the start or the\n",
       "    end points of the cells. Refer to the property `column_align`.\n",
       "    If this property is None, then a uniformly spaced grid is generated in\n",
       "    the column direction.\n",
       "\u001b[0;31mInit docstring:\u001b[0m Public constructor\n",
       "\u001b[0;31mFile:\u001b[0m           /opt/anaconda3/envs/DataViz2/lib/python3.10/site-packages/bqplot/marks.py\n",
       "\u001b[0;31mType:\u001b[0m           MetaHasTraits\n",
       "\u001b[0;31mSubclasses:\u001b[0m     "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bqplot.GridHeatMap?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "a1e48f8f-4b89-448e-a778-de796e7032cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[0;31mInit signature:\u001b[0m \u001b[0mbqplot\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mColorAxis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;34m't.Any'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mDocstring:\u001b[0m     \n",
       "A colorbar axis.\n",
       "\n",
       "A color axis is the visual representation of a color scale.\n",
       "\n",
       "Attributes\n",
       "----------\n",
       "scale: ColorScale\n",
       "    The scale represented by the axis\n",
       "\u001b[0;31mInit docstring:\u001b[0m Public constructor\n",
       "\u001b[0;31mFile:\u001b[0m           /opt/anaconda3/envs/DataViz2/lib/python3.10/site-packages/bqplot/axes.py\n",
       "\u001b[0;31mType:\u001b[0m           MetaHasTraits\n",
       "\u001b[0;31mSubclasses:\u001b[0m     "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bqplot.ColorAxis?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "d030ae5f-cec0-4e6a-ae07-50d35f050e16",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e45b89dc4959479abdc3ae8192a12515",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[ColorAxis(orientation='vertical', scale=ColorScale(scheme='Greens'), side='right'), Axis(label='C…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc})\n",
    "\n",
    "# 5. interactivity\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "f68f041e-e882-490e-9d63-465b0457458f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c34cf528b4c745ffa15228393560726c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[ColorAxis(orientation='vertical', scale=ColorScale(scheme='Greens'), side='right'), Axis(label='C…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc})\n",
    "\n",
    "# 5. interactivity\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "7e9387bb-620e-48a5-9910-f50758c664a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "967c2945f6354565a1e1891972aea6f4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[ColorAxis(orientation='vertical', scale=ColorScale(scheme='Greens'), side='right'), Axis(label='C…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "a628de12-6126-4dbd-8124-4eae59c7e741",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5, 1]])"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "heat_map.selected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "fa6ab8c0-dd3a-4dea-80ac-b8afe1094409",
   "metadata": {},
   "outputs": [],
   "source": [
    "import ipywidgets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "9f8cc48d-1c00-4dfc-ab95-6fcf99bb1a5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "myLabel = ipywidgets.Label()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "4be74a5d-234d-4d8f-b8c7-d1d1e3bfd16f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "55432ccde50d44eeb2710caa81c4d605",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Label(value='')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "myLabel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "2a1fcf33-23c2-4570-a2d8-5cfa18fbb710",
   "metadata": {},
   "outputs": [],
   "source": [
    "myLabel.value = 'Data value = '"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "849608cb-3492-4865-97e2-c12d2a169fb8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "05361aa50aaa47e7bf406eeb4de9c582",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[ColorAxis(orientation='vertical', scale=ColorScale(scheme='Greens'), side='right'), Axis(label='C…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "def on_selected(change):\n",
    "    print(change)\n",
    "heat_map.observe(on_selected, 'selected')\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "32c88ff5-d45f-402e-b891-93febd832c3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c8eeaab9c9d84898be21b45021908be3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[ColorAxis(orientation='vertical', scale=ColorScale(scheme='Greens'), side='right'), Axis(label='C…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "def on_selected(change):\n",
    "    #print(change)\n",
    "    if len(change['owner'].selected) == 1: # only one cell selected at a time\n",
    "        #print(change['owner'].selected[0])\n",
    "        i,j = change['owner'].selected[0]\n",
    "        myLabel.value = 'Data value = ' + str(data[i,j])\n",
    "heat_map.observe(on_selected, 'selected')\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "fig"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "3d62d566-4c83-4977-8d96-c43b06c4cc5f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5, 3]])"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "heat_map.selected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "ab12e1d4-f7e0-49e8-8088-61a6cb9a6448",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "55432ccde50d44eeb2710caa81c4d605",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Label(value='Data value = 0.6724727383787')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "myLabel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "4f177977-fd2d-49af-9b4c-cfe27754c260",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2ec7bbe1eb284a6599aeaed8768f8b57",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(Label(value='Data value = 0.19097005087221808'), Figure(axes=[ColorAxis(orientation='vertical',…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=data, scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "def on_selected(change):\n",
    "    #print(change)\n",
    "    if len(change['owner'].selected) == 1: # only one cell selected at a time\n",
    "        #print(change['owner'].selected[0])\n",
    "        i,j = change['owner'].selected[0]\n",
    "        myLabel.value = 'Data value = ' + str(data[i,j])\n",
    "heat_map.observe(on_selected, 'selected')\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "#fig\n",
    "\n",
    "# 7. dashboard it\n",
    "dashboard = ipywidgets.VBox([myLabel, fig])\n",
    "dashboard"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cef8278d-fee1-4b99-aa29-f3c27b533fa2",
   "metadata": {},
   "source": [
    "## 3d random data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "e0313026-f0ce-459b-8d73-a5f1b0130e3f",
   "metadata": {},
   "outputs": [],
   "source": [
    "data3d = np.random.random((10,10,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "ec79bd55-4469-49fd-8dbd-ef4ab56edeaa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7159b72a56b448fa895790dbc2a68dab",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(Label(value='Data value = 0.814372757369537'), Figure(axes=[ColorAxis(orientation='vertical', s…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=np.sum(data3d,axis=2), # changed here for data3d\n",
    "                              scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "def on_selected(change):\n",
    "    if len(change['owner'].selected) == 1: # only one cell selected at a time\n",
    "        i,j = change['owner'].selected[0]\n",
    "        myLabel.value = 'Data value (sum) = ' + str(np.sum(data3d[i,j,:])) # changed here for data3d\n",
    "heat_map.observe(on_selected, 'selected')\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "#fig\n",
    "\n",
    "# 7. dashboard it\n",
    "dashboard = ipywidgets.VBox([myLabel, fig])\n",
    "dashboard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "b69a0b82-028b-4a9f-bfb3-df943d6bec56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2, 4]])"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "heat_map.selected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "28818176-6186-4b43-b15b-22e1a1f6d3db",
   "metadata": {},
   "outputs": [],
   "source": [
    "i,j = 2, 4 # hardcoded for right now"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "0872a05c-0ebf-49b8-86dd-7481f9976f93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.82547582, 0.77680535, 0.67754424, 0.68122857, 0.46838934,\n",
       "       0.1395366 , 0.64964929, 0.49782137, 0.93877159, 0.34961361,\n",
       "       0.0277085 , 0.15967826, 0.6345999 , 0.84664458, 0.25910891,\n",
       "       0.26997155, 0.07221534, 0.35591331, 0.63635353, 0.58816059])"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data3d[i,j,:] # 1. data for histogram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "fed68314-2b1a-4021-8cb6-42041132817a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2. scales\n",
    "x_sch = bqplot.LinearScale()\n",
    "y_sch = bqplot.LinearScale()\n",
    "\n",
    "# 3. axis\n",
    "x_axh = bqplot.Axis(scale=x_sch, label='Value of 3rd axis')\n",
    "y_axh = bqplot.Axis(scale=y_sch, label='Frequency', orientation='vertical')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "1ba3a878-c649-41f5-af80-aa973c2bbbb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "#bqplot.Hist?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "3e1d656d-9875-45e4-ba23-3958886418ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 4. Marks -- histogram\n",
    "hist = bqplot.Hist(sample=data3d[i,j,:], scales={'sample':x_sch, 'count':y_sch}, bins=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "71fb3a47-3094-4b42-9dbf-8b2c2e8da3e8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2e432997c7de4b078100db5f53926f18",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(axes=[Axis(label='Value of 3rd axis', scale=LinearScale(), side='bottom'), Axis(label='Frequency', orie…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 5. interactions -- skip (but see prep notebook for more!)\n",
    "\n",
    "# 6. figure\n",
    "figh = bqplot.Figure(marks=[hist], axes=[x_axh,y_axh])\n",
    "figh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "14e0eba9-ec1c-41a4-b028-1baf48a0c503",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['_model_module',\n",
       " '_model_module_version',\n",
       " '_model_name',\n",
       " '_view_count',\n",
       " '_view_module',\n",
       " '_view_module_version',\n",
       " '_view_name',\n",
       " 'apply_clip',\n",
       " 'bins',\n",
       " 'colors',\n",
       " 'count',\n",
       " 'display_legend',\n",
       " 'enable_hover',\n",
       " 'interactions',\n",
       " 'labels',\n",
       " 'midpoints',\n",
       " 'normalized',\n",
       " 'opacities',\n",
       " 'preserve_domain',\n",
       " 'sample',\n",
       " 'scales',\n",
       " 'scales_metadata',\n",
       " 'selected',\n",
       " 'selected_style',\n",
       " 'stroke',\n",
       " 'tooltip',\n",
       " 'tooltip_location',\n",
       " 'tooltip_style',\n",
       " 'unselected_style',\n",
       " 'visible']"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hist.keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "8891c8fe-97eb-471e-bb76-0300cb391db8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.82547582, 0.77680535, 0.67754424, 0.68122857, 0.46838934,\n",
       "       0.1395366 , 0.64964929, 0.49782137, 0.93877159, 0.34961361,\n",
       "       0.0277085 , 0.15967826, 0.6345999 , 0.84664458, 0.25910891,\n",
       "       0.26997155, 0.07221534, 0.35591331, 0.63635353, 0.58816059])"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hist.sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "9074f796-7b24-416e-85c1-de3e035243f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.82547582, 0.77680535, 0.67754424, 0.68122857, 0.46838934,\n",
       "       0.1395366 , 0.64964929, 0.49782137, 0.93877159, 0.34961361,\n",
       "       0.0277085 , 0.15967826, 0.6345999 , 0.84664458, 0.25910891,\n",
       "       0.26997155, 0.07221534, 0.35591331, 0.63635353, 0.58816059])"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data3d[i,j,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "350d09a5-3ce8-4451-88a4-883db7ad74b9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1832a548c6c144a2ba839df191492ca6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(Label(value='Data value (sum) = 9.855190244510057'), Figure(axes=[ColorAxis(orientation='vertic…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 2. scales\n",
    "col_sc = bqplot.ColorScale(scheme='Greens')\n",
    "x_sc = bqplot.OrdinalScale() # ordered bin numbers\n",
    "y_sc = bqplot.OrdinalScale()\n",
    "\n",
    "# 3. Axis \n",
    "col_ax = bqplot.ColorAxis(scale=col_sc, orientation='vertical', side='right')\n",
    "x_ax = bqplot.Axis(scale=x_sc, label='Column Bin')\n",
    "y_ax = bqplot.Axis(scale=y_sc, label='Row Bin', orientation='vertical')\n",
    "\n",
    "# 4. Mark\n",
    "heat_map = bqplot.GridHeatMap(color=np.sum(data3d,axis=2), # changed here for data3d\n",
    "                              scales={'color':col_sc,\n",
    "                                                 'row':y_sc,\n",
    "                                                 'column':x_sc},\n",
    "                             interactions={'click':'select'}, \n",
    "                             anchor_style={'fill':'magenta'}\n",
    "                             )\n",
    "\n",
    "# 5. interactivity\n",
    "def on_selected(change):\n",
    "    if len(change['owner'].selected) == 1: # only one cell selected at a time\n",
    "        i,j = change['owner'].selected[0]\n",
    "        myLabel.value = 'Data value (sum) = ' + str(np.sum(data3d[i,j,:])) # changed here for data3d\n",
    "        hist.sample = data3d[i,j,:]\n",
    "heat_map.observe(on_selected, 'selected')\n",
    "\n",
    "# 6. figure\n",
    "fig = bqplot.Figure(marks=[heat_map], axes=[col_ax, x_ax, y_ax])\n",
    "#fig\n",
    "\n",
    "# 7. dashboard it\n",
    "dashboard = ipywidgets.VBox([myLabel, fig])\n",
    "dashboard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "2fedcb0e-084b-4565-89f0-b6f68bb1b004",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b4d5a8a7c75844bbb4e28712ab661ae5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(Label(value='Data value (sum) = 11.185800903922226'), HBox(children=(Figure(axes=[ColorAxis(ori…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "figures = ipywidgets.HBox([fig, figh])\n",
    "dashboard = ipywidgets.VBox([myLabel, figures])\n",
    "fig.layout.min_width = '500px'\n",
    "figh.layout.min_width = '500px'\n",
    "dashboard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3bce0935-9907-4b6a-a4a2-6f74ececed9f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}