{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# Data wrangling basics: supported filetypes\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import datawrangler as dw\n",
    "import numpy as np\n",
    "import os\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "from tutorial_helpers import data_file, image_file, text_file"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Let's load in some sample data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "dataframe = dw.io.load(data_file, index_col=0)\n",
    "array = dataframe.values\n",
    "image = dw.io.load(image_file)\n",
    "text = dw.io.load(text_file)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Sample DataFrame:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>FirstDim</th>\n",
       "      <th>SecondDim</th>\n",
       "      <th>ThirdDim</th>\n",
       "      <th>FourthDim</th>\n",
       "      <th>FifthDim</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ByTwos</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>15</td>\n",
       "      <td>20</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6</td>\n",
       "      <td>12</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>7</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>28</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        FirstDim  SecondDim  ThirdDim  FourthDim  FifthDim\n",
       "ByTwos                                                    \n",
       "0              1          2         3          4         5\n",
       "2              2          4         6          8        10\n",
       "4              3          6         9         12        15\n",
       "5              4          8        12         16        20\n",
       "6              5         10        15         20        25\n",
       "8              6         12        18         24        30\n",
       "10             7         14        21         28        35"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Sample Array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5],\n",
       "       [ 2,  4,  6,  8, 10],\n",
       "       [ 3,  6,  9, 12, 15],\n",
       "       [ 4,  8, 12, 16, 20],\n",
       "       [ 5, 10, 15, 20, 25],\n",
       "       [ 6, 12, 18, 24, 30],\n",
       "       [ 7, 14, 21, 28, 35]])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Sample image:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fb72ab06cd0>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(image)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Sample text:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "O give me a home where the buffaloes roam\n",
      "Where the deer and the antelope play\n",
      "Where seldom is heard a discouraging word\n",
      "And the skies are not cloudy all day\n",
      "Home, home on the range\n",
      "Where the deer and the antelope play\n",
      "Where seldom is heard a discouraging word\n",
      "And the skies are not cloudy all day\n",
      "Where the air is so pure and the zephyrs so free\n",
      "And the breezes so balmy and light\n",
      "That I would not exchange my home on the range\n",
      "For all of the cities so bright\n",
      "Home, home on the range\n",
      "Where the deer and the antelope play\n",
      "Where seldom is heard a discouraging word\n",
      "And the skies are not cloudy all day\n",
      "How often at night when the heavens are bright\n",
      "With the light of the glittering stars\n",
      "I stand there amazed and I ask as I gaze\n",
      "Does their glory exceed that of ours?\n",
      "Home, home on the range\n",
      "Where the deer and the antelope play\n",
      "Where seldom is heard a discouraging word\n",
      "And the skies are not cloudy all day\n"
     ]
    }
   ],
   "source": [
    "print(text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Wrangling DataFrames\n",
    "\n",
    "Wrangling a well-formed DataFrame just returns itself:"
   ]
  },
  {
   "cell_type": "markdown",
   "source": "## High-Performance DataFrames with Polars\n\n`data-wrangler` now supports [Polars](https://pola.rs/), a lightning-fast DataFrame library that can provide 2-100x performance improvements over pandas for many operations. You can choose your DataFrame backend on a per-operation basis or globally.\n\n### Installation\n\nPolars is now included as a core dependency of `data-wrangler`, so no additional installation is required!\n\n### Basic Polars Usage\n\nYou can specify the backend for any wrangling operation:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>FirstDim</th>\n",
       "      <th>SecondDim</th>\n",
       "      <th>ThirdDim</th>\n",
       "      <th>FourthDim</th>\n",
       "      <th>FifthDim</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ByTwos</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>15</td>\n",
       "      <td>20</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6</td>\n",
       "      <td>12</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>7</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>28</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        FirstDim  SecondDim  ThirdDim  FourthDim  FifthDim\n",
       "ByTwos                                                    \n",
       "0              1          2         3          4         5\n",
       "2              2          4         6          8        10\n",
       "4              3          6         9         12        15\n",
       "5              4          8        12         16        20\n",
       "6              5         10        15         20        25\n",
       "8              6         12        18         24        30\n",
       "10             7         14        21         28        35"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wrangled_df = dw.wrangle(dataframe)\n",
    "assert np.allclose(dataframe, wrangled_df)\n",
    "wrangled_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Wrangling Arrays\n",
    "\n",
    "Wrangling an Array turns it into a DataFrame.  If the Array is 2D, the resulting DataFrame will have the same\n",
    "shape:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>15</td>\n",
       "      <td>20</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>12</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>28</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0   1   2   3   4\n",
       "0  1   2   3   4   5\n",
       "1  2   4   6   8  10\n",
       "2  3   6   9  12  15\n",
       "3  4   8  12  16  20\n",
       "4  5  10  15  20  25\n",
       "5  6  12  18  24  30\n",
       "6  7  14  21  28  35"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wrangled_array = dw.wrangle(array)\n",
    "assert np.allclose(dataframe, wrangled_array)\n",
    "wrangled_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Note that we've recovered the original DataFrame, but the index and column labels have been reset.  We can provide\n",
    "these labels to the wrangle function.  The `array_kwargs` keyword argument specifies how array (or array-like) data\n",
    "objects should be turned into DataFrames:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>FirstDim</th>\n",
       "      <th>SecondDim</th>\n",
       "      <th>ThirdDim</th>\n",
       "      <th>FourthDim</th>\n",
       "      <th>FifthDim</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ByTwos</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>15</td>\n",
       "      <td>20</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6</td>\n",
       "      <td>12</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>7</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>28</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        FirstDim  SecondDim  ThirdDim  FourthDim  FifthDim\n",
       "ByTwos                                                    \n",
       "0              1          2         3          4         5\n",
       "2              2          4         6          8        10\n",
       "4              3          6         9         12        15\n",
       "5              4          8        12         16        20\n",
       "6              5         10        15         20        25\n",
       "8              6         12        18         24        30\n",
       "10             7         14        21         28        35"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "array_kwargs = {'index': dataframe.index, 'columns': dataframe.columns}\n",
    "wrangled_array2 = dw.wrangle(array, array_kwargs=array_kwargs)\n",
    "wrangled_array2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Wrangling text data using natural language processing models\n",
    "\n",
    "Next, let's play with some text data.  By default, `data-wrangler` embeds text using a Latent Dirichlet Allocation model\n",
    "trained on a curated version of Wikipedia, called the \"minipedia\" corpus.  First we'll split the text into its component\n",
    "lines, and then we'll wrangle the result:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "loading corpus: minipedia...done!\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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>40</th>\n",
       "      <th>41</th>\n",
       "      <th>42</th>\n",
       "      <th>43</th>\n",
       "      <th>44</th>\n",
       "      <th>45</th>\n",
       "      <th>46</th>\n",
       "      <th>47</th>\n",
       "      <th>48</th>\n",
       "      <th>49</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.51</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>24 rows \u00d7 50 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      0     1     2     3     4     5     6     7     8     9   ...    40  \\\n",
       "0   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "1   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "2   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "3   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "4   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "5   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "6   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "7   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "8   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "9   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "10  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "11  0.01  0.01  0.01  0.51  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "12  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "13  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "14  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "15  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "16  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "17  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "18  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "19  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "20  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "21  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  ...  0.01   \n",
       "22  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "23  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  ...  0.02   \n",
       "\n",
       "      41    42    43    44    45    46    47    48    49  \n",
       "0   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "1   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "2   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "3   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "4   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "5   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "6   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "7   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "8   0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "9   0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "10  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "11  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "12  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "13  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "14  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "15  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "16  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "17  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "18  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "19  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "20  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "21  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  0.01  \n",
       "22  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "23  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  0.02  \n",
       "\n",
       "[24 rows x 50 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lines = text.split('\\n')  # creates a list of strings (one string per line)\n",
    "wrangled_text = dw.wrangle(lines)\n",
    "wrangled_text"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "In the resulting DataFrame, each row corresponds to a line of text, and each column corresponds to an embedding\n",
    "dimension.  To get a better feel for what these dimensions mean, we can use the `return_model` flag to get back the\n",
    "fitted model, and then we can examine the top-weighted words from each topic:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "wrangled_text2, text_model = dw.wrangle(lines, text_kwargs={'return_model': True})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top words from each of the 50 discovered topics:\n",
      "\n",
      "Topic 0: angle, points, normal, units, equal, measure, distribution, distance, unit, constant\n",
      "Topic 1: foot, feet, double, speed, running, course, action, round, distance, motion\n",
      "Topic 2: game, play, team, played, rules, sports, field, events, competition, women\n",
      "Topic 3: mm, metal, plastic, glass, steel, diameter, sizes, machine, strength, cm\n",
      "Topic 4: 2008, million, 2007, 2009, 2011, 2010, march, december, 2006, january\n",
      "Topic 5: color, green, blue, yellow, colors, brown, tree, dark, plant, plants\n",
      "Topic 6: music, sound, film, rock, played, television, play, record, records, classical\n",
      "Topic 7: hours, night, hour, days, minutes, 24, week, daily, sun, working\n",
      "Topic 8: theory, self, behavior, science, cultural, concept, studies, individuals, model, relationship\n",
      "Topic 9: earth, sun, god, million, appears, visible, bodies, believed, billion, ago\n",
      "Topic 10: computer, data, management, project, key, electronic, access, online, devices, technology\n",
      "Topic 11: church, god, christian, religious, roman, religion, tradition, eastern, traditions, st\n",
      "Topic 12: military, forces, force, ii, arms, russian, royal, service, units, operations\n",
      "Topic 13: objects, mass, object, field, core, space, matter, fields, visible, energy\n",
      "Topic 14: building, built, buildings, construction, house, floor, room, space, houses, walls\n",
      "Topic 15: class, classes, anti, active, business, fall, military, 1950s, divided, feature\n",
      "Topic 16: cross, symbol, sign, al, et, shaped, version, appears, represents, link\n",
      "Topic 17: wind, ice, scale, energy, temperature, weather, speed, pressure, flow, sea\n",
      "Topic 18: gas, energy, temperature, heat, chemical, carbon, liquid, compounds, acid, reaction\n",
      "Topic 19: gain, southern, species, models, california, northern, frequency, active, components, spring\n",
      "Topic 20: pressure, flow, fluid, test, volume, supply, liquid, inner, internal, outer\n",
      "Topic 21: gold, iron, silver, metal, steel, value, carbon, bc, pure, ii\n",
      "Topic 22: death, stage, dead, die, remains, man, performed, stages, carried, bodies\n",
      "Topic 23: species, humans, male, female, million, ago, live, population, living, animals\n",
      "Topic 24: language, languages, books, writing, written, words, text, published, formal, literature\n",
      "Topic 25: health, medical, care, treatment, poor, population, million, studies, report, risk\n",
      "Topic 26: animals, animal, skin, humans, eye, eyes, wild, kept, domestic, raised\n",
      "Topic 27: cells, cell, growth, plants, structures, layer, plant, acid, functions, biological\n",
      "Topic 28: women, sexual, children, men, female, male, child, woman, man, mother\n",
      "Topic 29: oil, fruit, varieties, hot, served, consumption, grown, fresh, content, sold\n",
      "Topic 30: service, court, legal, services, civil, department, federal, government, laws, issued\n",
      "Topic 31: blood, disease, heart, risk, diseases, treatment, health, causes, medical, loss\n",
      "Topic 32: vehicles, electric, speed, built, drive, safety, equipment, transport, electrical, technology\n",
      "Topic 33: art, style, london, works, 18th, museum, tradition, saw, famous, william\n",
      "Topic 34: political, party, government, rights, legal, organization, exchange, status, organizations, economic\n",
      "Topic 35: fish, sea, ft, river, deep, land, fresh, 200, island, 500\n",
      "Topic 36: city, road, street, cities, town, river, urban, population, island, travel\n",
      "Topic 37: god, fruit, trees, disease, risk, treatment, head, million, cultural, medical\n",
      "Topic 38: soil, land, plant, bc, plants, rock, regions, region, india, stone\n",
      "Topic 39: story, damage, article, loss, ring, exposure, protection, journal, published, severe\n",
      "Topic 40: section, big, principal, differences, ii, fully, model, wind, 32, split\n",
      "Topic 41: base, lines, wall, pieces, piece, opening, figure, upper, vertical, branch\n",
      "Topic 42: property, elements, numbers, element, table, properties, real, value, classical, theory\n",
      "Topic 43: worn, paper, wear, clothing, fashion, women, men, style, styles, cover\n",
      "Topic 44: chinese, king, india, east, african, africa, japanese, asia, indian, spanish\n",
      "Topic 45: species, trees, plants, leaves, winter, wild, tree, season, summer, northern\n",
      "Topic 46: foot, et, al, feet, science, political, height, 18th, court, religious\n",
      "Topic 47: market, price, product, products, goods, store, chain, supply, industry, company\n",
      "Topic 48: school, education, training, schools, degree, college, children, professional, programs, degrees\n",
      "Topic 49: wood, head, image, cut, wooden, tools, edge, tool, images, face\n"
     ]
    }
   ],
   "source": [
    "# display top words from the model\n",
    "def get_top_words(model, n_words=10):\n",
    "  vectorizer = model[0]['model']\n",
    "  embedder = model[1]['model']\n",
    "\n",
    "  vocab = {v: k for k, v in vectorizer.vocabulary_.items()}\n",
    "  top_words = []\n",
    "  for k in range(embedder.components_.shape[0]):\n",
    "      top_words.append([vocab[i] for i in np.argsort(embedder.components_[k, :])[::-1][:n_words]])\n",
    "  return top_words\n",
    "\n",
    "def display_top_words(model, n_words=10):\n",
    "  for k, w in enumerate(get_top_words(model, n_words=n_words)):\n",
    "      print(f'Topic {k}: {\", \".join(w)}')\n",
    "\n",
    "print(f'Top words from each of the {wrangled_text2.shape[1]} discovered topics:\\n')\n",
    "display_top_words(text_model)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Then we can ask which topics had the most weight in each line:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Line 1 put the most weight on topic 2: Where the deer and the antelope play\n"
     ]
    }
   ],
   "source": [
    "i = 1\n",
    "line_embedding = wrangled_text2.loc[i].values\n",
    "line_top_topic = np.where(line_embedding == np.max(line_embedding))[0][0]\n",
    "\n",
    "print(f'Line {i} put the most weight on topic {line_top_topic}: {lines[i]}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Note that each time the model is re-trained, the topic weights will change.  If all text data are wrangled in a single\n",
    "pass, `data-wrangler` will automatically apply the same model to all text data.  However, if the data are wrangled in\n",
    "multiple calls to `dw.wrangle`, the model fit during the first pass should be re-used in subsequent analyses:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Topics do NOT match!\n"
     ]
    }
   ],
   "source": [
    "def match(a, b, type):\n",
    "    if np.allclose(a, b):\n",
    "        print(f'{type.capitalize()}s match!')\n",
    "    else:\n",
    "        print(f'{type.capitalize()}s do NOT match!')\n",
    "\n",
    "match(wrangled_text, wrangled_text2, 'topic')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We can re-apply the already-fitted model to \"new\" text:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Topics match!\n"
     ]
    }
   ],
   "source": [
    "wrangled_text3 = dw.wrangle(lines, text_kwargs={'model': text_model})\n",
    "match(wrangled_text2, wrangled_text3, 'topic')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": "## Modern Text Processing with Sentence-Transformers\n\nIn addition to scikit-learn text embedding models, `data-wrangler` provides comprehensive support for state-of-the-art sentence-transformers models via [HuggingFace](https://huggingface.co/models).\n\n### Installation Requirements\n\nSentence-transformers support requires additional ML libraries. To keep `data-wrangler` lightweight, these are optional dependencies:\n\n```bash\npip install --upgrade \"pydata-wrangler[hf]\"\n```\n\nThis installs sentence-transformers, transformers, and related HuggingFace libraries.\n\n### Popular Sentence-Transformers Models\n\nDifferent models are optimized for different tasks:\n\n- **`all-MiniLM-L6-v2`**: Fast, general-purpose sentence embeddings (384 dimensions)\n- **`all-mpnet-base-v2`**: High-quality sentence embeddings (768 dimensions) \n- **`paraphrase-MiniLM-L6-v2`**: Optimized for paraphrase detection\n- **`all-distilroberta-v1`**: Balanced performance and speed\n\n### Basic Usage\n\nHere's how to use sentence-transformers with your text data:"
  },
  {
   "cell_type": "code",
   "source": "# High-quality model - better for production applications\n# Using simplified API - just pass the model name as a string!\nquality_embeddings = dw.wrangle(lines, text_kwargs={'model': 'all-mpnet-base-v2'})\n\nprint(f\"Quality model embeddings shape: {quality_embeddings.shape}\")\nprint(f\"Quality model (first few dimensions):\")\nquality_embeddings.iloc[:3, :5]",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "### Model Comparison\n\nNotice the difference in embedding dimensions:\n- **Fast model (all-MiniLM-L6-v2)**: 384 dimensions - good for speed and memory efficiency\n- **Quality model (all-mpnet-base-v2)**: 768 dimensions - better semantic understanding\n\n### Practical Applications\n\nDifferent models work better for different tasks:\n\n1. **Similarity Search**: Use `all-MiniLM-L6-v2` for fast similarity search\n2. **Semantic Analysis**: Use `all-mpnet-base-v2` for deeper semantic understanding\n3. **Paraphrase Detection**: Use `paraphrase-MiniLM-L6-v2` for finding similar content\n\nLet's see how these embeddings can be used for similarity analysis:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "source": "# Example: Find similar lines using cosine similarity\nfrom sklearn.metrics.pairwise import cosine_similarity\nimport numpy as np\n\n# Calculate similarity matrix\nsimilarity_matrix = cosine_similarity(fast_embeddings)\n\n# Find the most similar lines to the first line\nline_0_similarities = similarity_matrix[0]\nmost_similar_indices = np.argsort(line_0_similarities)[-3:]  # Top 3 similar lines\n\nprint(\"Original line 0:\", lines[0])\nprint(\"\\nMost similar lines:\")\nfor idx in reversed(most_similar_indices):\n    if idx != 0:  # Don't include the line itself\n        print(f\"Line {idx} (similarity: {line_0_similarities[idx]:.3f}): {lines[idx]}\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": "# Fast model - good for quick prototyping\n# Using simplified API - just pass the model name as a string!\nfast_embeddings = dw.wrangle(lines, text_kwargs={'model': 'all-MiniLM-L6-v2'})\n\nprint(f\"Fast model embeddings shape: {fast_embeddings.shape}\")\nprint(f\"Fast model (first few dimensions):\")\nfast_embeddings.iloc[:3, :5]",
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Wrangling images\n",
    "\n",
    "Images (stored in any format supported by [matplotlib](https://matplotlib.org/)) treated as Arrays.  Images are wrangled\n",
    "into `DataFrame`s by slicing the image along axis 2 (i.e., the color dimension), horizontally concatenating the slices,\n",
    "and then turning the result into a `DataFrame`.  In general, this approach is taken for all high-dimensional (> 2D)\n",
    "Arrays:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "wrangled_image = dw.wrangle(image)\n",
    "plt.imshow(wrangled_image);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Objects, file paths, and URLs\n",
    "\n",
    "Data supplied to `data-wrangler` may be passed in directly as a Python object that is already loaded into memory (as in\n",
    "the above examples).  However, data may also be supplied as a (string) file path or URL.  For example,\n",
    "wrangling the already loaded-in image versus wrangling the image's file path will yield the same result:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Images match!\n"
     ]
    }
   ],
   "source": [
    "wrangled_image_from_path = dw.wrangle(image_file)\n",
    "match(wrangled_image, wrangled_image_from_path, 'image')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "# Handling multiple data types\n",
    "\n",
    "Multiple objects, file paths, or URLs may be wrangled in a single function call.  If desired, type-specific wrangling\n",
    "preferences may be provided.  Specifying `return_dtype=True` also returns a list of the automatically detected data\n",
    "types for each object:"
   ]
  },
  {
   "cell_type": "code",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": "# Using simplified API - just pass the model name as a string\\!\ntext_kwargs = {'model': 'all-MiniLM-L6-v2'}\n\ni = 10\nfirst_lines = lines[:i]\nlast_lines = lines[i:]",
   "execution_count": 37
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight']\n",
      "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight']\n",
      "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
     ]
    }
   ],
   "source": [
    "wrangled_data, dtypes = dw.wrangle([dataframe, array, image_file, first_lines, last_lines],\n",
    "                                   text_kwargs=text_kwargs,\n",
    "                                   return_dtype=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We can check the inferred datatypes:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['dataframe', 'array', 'array', 'text', 'text']"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We can also verify that when the data are wrangled simultaneously, we get the same results as when each object is\n",
    "wrangled separately.  For example, here's the newly wrangled image:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fb72b2ea890>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualize the wrangled image\n",
    "plt.imshow(wrangled_data[2])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "And here's how the text embeddings compare to our previous results:"
   ]
  },
  {
   "cell_type": "code",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": "# compare the first lines' embeddings:\nmatch(sentence_embeddings.iloc[:i], wrangled_data[3], 'first lines\\'s sentence-transformers embedding')\n\n# compare the last lines' embeddings\nmatch(sentence_embeddings.iloc[i:], wrangled_data[4], 'last lines\\'s sentence-transformers embedding')",
   "execution_count": 44
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Check out the other tutorials for more advanced data wrangling functions!"
   ]
  },
  {
   "cell_type": "code",
   "source": "# Wrangle data using Polars backend for high performance\nimport polars as pl\n\n# Convert array to Polars DataFrame\npolars_df = dw.wrangle(array, backend='polars')\nprint(f\"Polars DataFrame type: {type(polars_df)}\")\nprint(f\"Shape: {polars_df.shape}\")\npolars_df.head()",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "### Cross-Backend Conversion\n\nYou can convert between pandas and Polars DataFrames seamlessly:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "source": "# Convert pandas DataFrame to Polars\npandas_df = wrangled_df  # Our original pandas DataFrame\npolars_from_pandas = dw.wrangle(pandas_df, backend='polars')\n\nprint(f\"Original: {type(pandas_df)}\")\nprint(f\"Converted to Polars: {type(polars_from_pandas)}\")\n\n# Convert Polars DataFrame back to pandas\npandas_from_polars = dw.wrangle(polars_from_pandas, backend='pandas')\nprint(f\"Converted back to pandas: {type(pandas_from_polars)}\")\n\n# Verify data is preserved\nimport numpy as np\nprint(f\"Data preserved: {np.allclose(pandas_df.values, pandas_from_polars.values)}\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "### Global Backend Configuration\n\nYou can set a global preference for DataFrame backend:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "source": "# Configure global backend preference\nfrom datawrangler.core.configurator import set_dataframe_backend, get_dataframe_backend\n\n# Check current default\nprint(f\"Current default backend: {get_dataframe_backend()}\")\n\n# Set global preference to Polars\nset_dataframe_backend('polars')\nprint(f\"New default backend: {get_dataframe_backend()}\")\n\n# Now all operations use Polars by default\nglobal_polars_df = dw.wrangle(array)  # No need to specify backend='polars'\nprint(f\"Global setting result: {type(global_polars_df)}\")\n\n# Reset to pandas for rest of tutorial\nset_dataframe_backend('pandas')\nprint(f\"Reset to: {get_dataframe_backend()}\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "### Text Processing with Polars\n\nText processing also supports the Polars backend for high-performance embeddings:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "source": "# Text embeddings with Polars backend for better performance\nsample_texts = [\"Machine learning is fascinating\", \n                \"Data science combines statistics and programming\",\n                \"Polars is a fast DataFrame library\"]\n\n# Process text with Polars backend\npolars_text_df = dw.wrangle(sample_texts, backend='polars')\nprint(f\"Text embeddings with Polars: {type(polars_text_df)}\")\nprint(f\"Shape: {polars_text_df.shape}\")\n\n# Compare with pandas backend\npandas_text_df = dw.wrangle(sample_texts, backend='pandas')\nprint(f\"Text embeddings with pandas: {type(pandas_text_df)}\")\nprint(f\"Shape: {pandas_text_df.shape}\")\n\n# Both should have the same shape\nprint(f\"Same embedding dimensions: {polars_text_df.shape == pandas_text_df.shape}\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "### Performance Benefits\n\nPolars offers significant performance advantages, especially for:\n\n- **Large datasets**: 2-10x faster operations on datasets with millions of rows\n- **Aggregations**: Group-by operations and statistical computations\n- **Memory efficiency**: Lower memory usage with columnar data format\n- **Parallel processing**: Built-in parallelization for multi-core systems\n\nThe choice between pandas and Polars depends on your specific needs:\n\n- **Use pandas** for: Familiarity, ecosystem compatibility, complex transformations\n- **Use Polars** for: Performance, large datasets, memory efficiency, parallel processing\n\n### Automatic Type Preservation\n\n`data-wrangler` automatically preserves your DataFrame type when no backend is specified:",
   "metadata": {}
  },
  {
   "cell_type": "markdown",
   "source": "### Performance Benchmark Example\n\nHere's a practical example showing the performance difference between pandas and Polars for array conversion:",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "source": "# Demonstrate automatic type preservation\nimport pandas as pd\nimport polars as pl\n\n# Create DataFrames of each type\npandas_input = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\npolars_input = pl.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n\n# Wrangle without specifying backend - type is preserved\npandas_output = dw.wrangle(pandas_input)\npolars_output = dw.wrangle(polars_input)\n\nprint(f\"Pandas input: {type(pandas_input)} -> Output: {type(pandas_output)}\")\nprint(f\"Polars input: {type(polars_input)} -> Output: {type(polars_output)}\")\nprint(\"\u2705 Types automatically preserved!\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "source": "import time\nimport numpy as np\n\n# Create a moderately sized array for benchmarking\nlarge_array = np.random.rand(10000, 50)\nprint(f\"Array shape: {large_array.shape}\")\n\n# Benchmark pandas backend\nstart_time = time.time()\npandas_result = dw.wrangle(large_array, backend='pandas')\npandas_time = time.time() - start_time\n\n# Benchmark Polars backend\nstart_time = time.time()\npolars_result = dw.wrangle(large_array, backend='polars')\npolars_time = time.time() - start_time\n\nprint(f\"\\n\ud83d\udcca Performance Comparison:\")\nprint(f\"Pandas backend: {pandas_time:.4f} seconds\")\nprint(f\"Polars backend: {polars_time:.4f} seconds\")\nprint(f\"Speedup: {pandas_time/polars_time:.1f}x faster with Polars\")\n\n# Verify results are equivalent\nprint(f\"\\n\u2705 Results equivalent: {np.allclose(pandas_result.values, polars_result.to_pandas().values)}\")",
   "metadata": {},
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "source": "## Summary: Choosing the Right Backend\n\n`data-wrangler` now provides flexible DataFrame backend support:\n\n| Feature | pandas | Polars |\n|---------|--------|--------|\n| **Performance** | Standard | 2-100x faster |\n| **Memory Usage** | Higher | Lower (columnar) |\n| **Ecosystem** | Mature, extensive | Growing rapidly |\n| **Learning Curve** | Familiar to most | Similar API |\n| **Best For** | General use, prototyping | Large data, production |\n\n### Quick Start Guide\n\n```python\n# Basic usage - specify backend per operation\nimport datawrangler as dw\n\n# Use pandas (default)\ndf_pandas = dw.wrangle(data)\n\n# Use Polars for performance  \ndf_polars = dw.wrangle(data, backend='polars')\n\n# Set global preference\nfrom datawrangler.core.configurator import set_dataframe_backend\nset_dataframe_backend('polars')  # All operations use Polars\n```\n\nBoth backends support all `data-wrangler` functionality including text processing, array conversion, and complex data wrangling pipelines. Choose the backend that best fits your performance requirements and workflow preferences!",
   "metadata": {}
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "3.8.10"
  },
  "vscode": {
   "interpreter": {
    "hash": "767d51c1340bd893661ea55ea3124f6de3c7a262a8b4abca0554b478b1e2ff90"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}