Plotly 2 vs 3 Plot time exploration with Bixi Data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<script>requirejs.config({paths: { 'plotly': ['https://cdn.plot.ly/plotly-latest.min']},});if(!window.Plotly) {{require(['plotly'],function(plotly) {window.Plotly=plotly;});}}</script>"
      ],
      "text/vnd.plotly.v1+html": [
       "<script>requirejs.config({paths: { 'plotly': ['https://cdn.plot.ly/plotly-latest.min']},});if(!window.Plotly) {{require(['plotly'],function(plotly) {window.Plotly=plotly;});}}</script>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import time\n",
    "\n",
    "import pandas as pd\n",
    "import plotly.offline as py  # Use \"import plotly.plotly\" for online graphs\n",
    "import plotly.graph_objs as go\n",
    "import numpy as np\n",
    "\n",
    "py.init_notebook_mode(connected=True)  # Plots inside Jupyter Notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3.0.0rc10\n"
     ]
    }
   ],
   "source": [
    "from plotly import __version__\n",
    "print(__version__) # requires version >= 1.9.0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(4740357, 6)\n"
     ]
    },
    {
     "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>start_date</th>\n",
       "      <th>start_station_code</th>\n",
       "      <th>end_date</th>\n",
       "      <th>end_station_code</th>\n",
       "      <th>duration_sec</th>\n",
       "      <th>is_member</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2017-04-15 00:00</td>\n",
       "      <td>7060</td>\n",
       "      <td>2017-04-15 00:31</td>\n",
       "      <td>7060</td>\n",
       "      <td>1841</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2017-04-15 00:01</td>\n",
       "      <td>6173</td>\n",
       "      <td>2017-04-15 00:10</td>\n",
       "      <td>6173</td>\n",
       "      <td>553</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017-04-15 00:01</td>\n",
       "      <td>6203</td>\n",
       "      <td>2017-04-15 00:04</td>\n",
       "      <td>6204</td>\n",
       "      <td>195</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2017-04-15 00:01</td>\n",
       "      <td>6104</td>\n",
       "      <td>2017-04-15 00:06</td>\n",
       "      <td>6114</td>\n",
       "      <td>285</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2017-04-15 00:01</td>\n",
       "      <td>6174</td>\n",
       "      <td>2017-04-15 00:11</td>\n",
       "      <td>6174</td>\n",
       "      <td>569</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         start_date  start_station_code          end_date  end_station_code  \\\n",
       "0  2017-04-15 00:00                7060  2017-04-15 00:31              7060   \n",
       "1  2017-04-15 00:01                6173  2017-04-15 00:10              6173   \n",
       "2  2017-04-15 00:01                6203  2017-04-15 00:04              6204   \n",
       "3  2017-04-15 00:01                6104  2017-04-15 00:06              6114   \n",
       "4  2017-04-15 00:01                6174  2017-04-15 00:11              6174   \n",
       "\n",
       "   duration_sec  is_member  \n",
       "0          1841          1  \n",
       "1           553          1  \n",
       "2           195          1  \n",
       "3           285          1  \n",
       "4           569          1  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Collect all the 2018 \n",
    "df_ls = []\n",
    "\n",
    "df_ls = [pd.read_csv(f'data/Bixi/2017/OD_2017-{n:02d}.csv') for n in range(4,12)]\n",
    "\n",
    "df = pd.concat(df_ls)\n",
    "\n",
    "print(df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def trace(x,y):\n",
    "    return go.Scattergl(\n",
    "        x=x,\n",
    "        y=y,\n",
    "        mode='markers',\n",
    "        marker=dict(\n",
    "            size=2,\n",
    "            symbol='circle'\n",
    "        )\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotly 2.7"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The output of the run is cleared due to overwelming size of the file when it is saved"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 500,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_small = df.sample(n=500000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t1 = time.time()\n",
    "fig = go.Figure(data=[trace(x,y)])\n",
    "\n",
    "py.iplot(fig, filename='simple-scatter')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7.0769500732421875\n"
     ]
    }
   ],
   "source": [
    "t2 = time.time()\n",
    "print(t2-t1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 1,000,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_small = df.sample(n=1000000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t3 = time.time()\n",
    "fig = go.Figure(data=[trace(x,y)])\n",
    "\n",
    "py.iplot(fig, filename='simple-scatter')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "15.005493879318237\n"
     ]
    }
   ],
   "source": [
    "t4 = time.time()\n",
    "print(t4-t3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 2,000,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_small = df.sample(n=2000000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t5 = time.time()\n",
    "fig = go.Figure(data=[trace(x,y)])\n",
    "\n",
    "py.iplot(fig, filename='simple-scatter')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "29.524930715560913\n"
     ]
    }
   ],
   "source": [
    "t6 = time.time()\n",
    "print(t6-t5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 500,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.1366443634033203\n"
     ]
    }
   ],
   "source": [
    "df_small = df.sample(n=500000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t1 = time.time()\n",
    "\n",
    "go.FigureWidget(data=[trace(x,y)])\n",
    "\n",
    "t2 = time.time()\n",
    "print(t2-t1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 1,000,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.218580484390259\n"
     ]
    }
   ],
   "source": [
    "df_small = df.sample(n=1000000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t1 = time.time()\n",
    "\n",
    "go.FigureWidget(data=[trace(x,y)])\n",
    "\n",
    "t2 = time.time()\n",
    "print(t2-t1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting 2,000,000 points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.26620626449585\n"
     ]
    }
   ],
   "source": [
    "df_small = df.sample(n=2000000, random_state=1)\n",
    "x = df_small['start_station_code']\n",
    "y = df_small['duration_sec']\n",
    "\n",
    "t1 = time.time()\n",
    "\n",
    "go.FigureWidget(data=[trace(x,y)])\n",
    "\n",
    "t2 = time.time()\n",
    "print(t2-t1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting entire dataset (4.5 mil data points)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9.956984996795654\n"
     ]
    }
   ],
   "source": [
    "x = df['start_station_code']\n",
    "y = df['duration_sec']\n",
    "\n",
    "t1 = time.time()\n",
    "\n",
    "go.FigureWidget(data=[trace(x,y)])\n",
    "\n",
    "t2 = time.time()\n",
    "print(t2-t1)"
   ]
  }
 ],
 "metadata": {
  "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}