{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Formats\n",
    "\n",
    "## Import the BipartitePandas package\n",
    "\n",
    "Make sure to install it using `pip install bipartitepandas`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import bipartitepandas as bpd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Get your data ready\n",
    "\n",
    "For this notebook, we simulate data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>i</th>\n",
       "      <th>j</th>\n",
       "      <th>y</th>\n",
       "      <th>t</th>\n",
       "      <th>l</th>\n",
       "      <th>k</th>\n",
       "      <th>alpha</th>\n",
       "      <th>psi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>0.086822</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49995</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>0.967422</td>\n",
       "      <td>1.335178</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49996</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>0.967422</td>\n",
       "      <td>0.348756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49997</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>0.967422</td>\n",
       "      <td>0.348756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49998</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>0.967422</td>\n",
       "      <td>0.908458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49999</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>1.796405</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>0.967422</td>\n",
       "      <td>0.908458</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>50000 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i    j         y  t  l  k     alpha       psi\n",
       "0         0   31 -0.066354  0  2  1  0.000000 -0.908458\n",
       "1         0   24 -1.319229  1  2  1  0.000000 -0.908458\n",
       "2         0   24 -2.141775  2  2  1  0.000000 -0.908458\n",
       "3         0   24 -1.831186  3  2  1  0.000000 -0.908458\n",
       "4         0   24  0.086822  4  2  1  0.000000 -0.908458\n",
       "...     ...  ...       ... .. .. ..       ...       ...\n",
       "49995  9999  188  2.877201  0  4  9  0.967422  1.335178\n",
       "49996  9999  126  1.415829  1  4  6  0.967422  0.348756\n",
       "49997  9999  126  0.772108  2  4  6  0.967422  0.348756\n",
       "49998  9999  176  2.263156  3  4  8  0.967422  0.908458\n",
       "49999  9999  176  1.796405  4  4  8  0.967422  0.908458\n",
       "\n",
       "[50000 rows x 8 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df = bpd.SimBipartite().simulate()\n",
    "display(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Columns\n",
    "\n",
    "BipartitePandas includes seven pre-defined general columns:\n",
    "\n",
    "#### Required\n",
    "- `i`: worker id (any type)\n",
    "- `j`: firm id (any type)\n",
    "- `y`: income (float or int)\n",
    "\n",
    "#### Optional\n",
    "- `t`: time (int)\n",
    "- `g`: firm type (any type)\n",
    "- `w`: weight (float or int)\n",
    "- `m`: move indicator (int)\n",
    "\n",
    "## Formats\n",
    "\n",
    "BipartitePandas includes six formats:\n",
    "\n",
    "- *Long* - each row gives a single observation\n",
    "- *Collapsed Long* - like *Long*, but employment spells at the same firm, or entire worker-firm matches, are collapsed into a single observation (these will differ if there are workers who leave, then return to, a particular firm)\n",
    "- *Event Study* - each row gives two consecutive observations\n",
    "- *Collapsed Event Study* - like *Event Study*, but employment spells at the same firm, or entire worker-firm matches, are collapsed into a single observation (these will differ if there are workers who leave, then return to, a particular firm)\n",
    "- *Extended Event Study* - each row gives arbitrarily many consecutive observations\n",
    "- *Collapsed Extended Event Study* - like *Extended Event Study*, but employment spells at the same firm, or entire worker-firm matches, are collapsed into a single observation (these will differ if there are workers who leave, then return to, a particular firm)\n",
    "\n",
    "These formats divide general columns differently:\n",
    "\n",
    "- *Long* - `i`, `j`, `y`, `t`, `g`, `w`, `m`\n",
    "- *Collapsed Long* - `i`, `j`, `y`, `t1`, `t2`, `g`, `w`, `m`\n",
    "- *Event Study* - `i`, `j1`, `j2`, `y1`, `y2`, `t1`, `t2`, `g1`, `g2`, `w1`, `w2`, `m`\n",
    "- *Collapsed Event Study* - `i`, `j1`, `j2`, `y1`, `y2`, `t11`, `t12`, `t21`, `t22`, `g1`, `g2`, `w1`, `w2`, `m`\n",
    "- *Extended Event Study* - `i`, `j1`, ..., `jp`, `y1`, ..., `yp`, `t1`, ..., `tp`, `g1`, ..., `gp`, `w1`, ..., `wp`, `m`\n",
    "- *Collapsed Extended Event Study* - `i`, `j1`, ..., `jp`, `y1`, ..., `yp`, `t11`, `t12`, ..., `tp1`, `tp2`, `g1`, ..., `gp`, `w1`, ..., `wp`, `m`\n",
    "\n",
    "<div class=\"alert alert-info\">\n",
    "\n",
    "Note\n",
    "\n",
    "*Event Study* and *Extended Event Study* differ even if *Extended Event Study* has 2 periods. This is because *Event Study* treats each stayer observation as a new event study, while *Extended Event Study* treats stayers the same as movers: event studies are based on consecutive observations.\n",
    "\n",
    "In addition to the fact that stayers are treated differently for non-collapsed data, *Collapsed Event Study* will contain stayers, but *Collapsed Extended Event Study* will not.\n",
    "\n",
    "</div>\n",
    "\n",
    "## Constructing DataFrames\n",
    "\n",
    "Our simulated data is in *Long* format. How do we construct a *Long* dataframe?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": false
   },
   "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>i</th>\n",
       "      <th>j</th>\n",
       "      <th>y</th>\n",
       "      <th>t</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>0.086822</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49995</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49996</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49997</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49998</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49999</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>1.796405</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>50000 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i    j         y  t\n",
       "0         0   31 -0.066354  0\n",
       "1         0   24 -1.319229  1\n",
       "2         0   24 -2.141775  2\n",
       "3         0   24 -1.831186  3\n",
       "4         0   24  0.086822  4\n",
       "...     ...  ...       ... ..\n",
       "49995  9999  188  2.877201  0\n",
       "49996  9999  126  1.415829  1\n",
       "49997  9999  126  0.772108  2\n",
       "49998  9999  176  2.263156  3\n",
       "49999  9999  176  1.796405  4\n",
       "\n",
       "[50000 rows x 4 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bdf_long = bpd.BipartiteDataFrame(\n",
    "    i=df['i'], j=df['j'], y=df['y'], t=df['t']\n",
    ")\n",
    "display(bdf_long)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Are we sure this is long? Let's check the datatype:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bipartitepandas.bipartitelong.BipartiteLong"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(bdf_long)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This method works to construct any format! Just make sure not to mix up columns between formats."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Converting between formats\n",
    "\n",
    "Converting between formats is meant to be easy. Methods exist to go from:\n",
    "\n",
    "- *Long* to *Collapsed Long* (`.collapse()`)\n",
    "- *Long* to *Event Study* (`.to_eventstudy()`)\n",
    "- *Long* to *Extended Event Study* (`.to_extendedeventstudy()`)\n",
    "- *Collapsed Long* to *Long* (`.uncollapse()`)\n",
    "- *Collapsed Long* to *Collapsed Event Study* (`.to_eventstudy()`)\n",
    "- *Collapsed Long* to *Collapsed Extended Event Study* (`.to_extendedeventstudy()`)\n",
    "- *Event Study* to *Long* (`.to_long()`)\n",
    "- *Collapsed Event Study* to *Collapsed Long* (`.to_long()`)\n",
    "\n",
    "Let's experiment with these and see what happens. Before we start, we just need to clean our data to make sure the conversions work properly (notice the new `m` column)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "checking required columns and datatypes\n",
      "sorting rows\n",
      "dropping NaN observations\n",
      "generating 'm' column\n",
      "keeping highest paying job for i-t (worker-year) duplicates (how='max')\n",
      "dropping workers who leave a firm then return to it (how=False)\n",
      "making 'i' ids contiguous\n",
      "making 'j' ids contiguous\n",
      "computing largest connected set (how=None)\n",
      "sorting columns\n",
      "resetting index\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>i</th>\n",
       "      <th>j</th>\n",
       "      <th>y</th>\n",
       "      <th>t</th>\n",
       "      <th>m</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>0.086822</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49995</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49996</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49997</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49998</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49999</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>1.796405</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>50000 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i    j         y  t  m\n",
       "0         0   31 -0.066354  0  1\n",
       "1         0   24 -1.319229  1  1\n",
       "2         0   24 -2.141775  2  0\n",
       "3         0   24 -1.831186  3  0\n",
       "4         0   24  0.086822  4  0\n",
       "...     ...  ...       ... .. ..\n",
       "49995  9999  188  2.877201  0  1\n",
       "49996  9999  126  1.415829  1  1\n",
       "49997  9999  126  0.772108  2  1\n",
       "49998  9999  176  2.263156  3  1\n",
       "49999  9999  176  1.796405  4  0\n",
       "\n",
       "[50000 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bdf_long = bdf_long.clean()\n",
    "display(bdf_long)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### *Long* to *Collapsed Long*\n",
    "\n",
    "Notice that:\n",
    "\n",
    "- We specify `level='spell'` to collapse employment spells at the same firm into single observations\n",
    "- `t` splits into `t1` and `t2`, which indicate the start the end of the spell, respectively\n",
    "- `w` is new - it gives the number of observations in the spell"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>i</th>\n",
       "      <th>j</th>\n",
       "      <th>y</th>\n",
       "      <th>t1</th>\n",
       "      <th>t2</th>\n",
       "      <th>w</th>\n",
       "      <th>m</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.301342</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>0.237748</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>-1.098072</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29684</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>0.361819</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29685</th>\n",
       "      <td>9998</td>\n",
       "      <td>30</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29686</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29687</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29688</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>2.029781</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>29689 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i    j         y  t1  t2  w  m\n",
       "0         0   31 -0.066354   0   0  1  1\n",
       "1         0   24 -1.301342   1   4  4  1\n",
       "2         1  140  0.237748   0   1  2  1\n",
       "3         1   81 -1.262375   2   2  1  2\n",
       "4         1    9 -1.098072   3   4  2  1\n",
       "...     ...  ...       ...  ..  .. .. ..\n",
       "29684  9998  139  0.361819   0   3  4  1\n",
       "29685  9998   30 -0.136980   4   4  1  1\n",
       "29686  9999  188  2.877201   0   0  1  1\n",
       "29687  9999  126  1.093969   1   2  2  2\n",
       "29688  9999  176  2.029781   3   4  2  1\n",
       "\n",
       "[29689 rows x 7 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bdf_collapsedlong = bdf_long.collapse(level='spell')\n",
    "display(bdf_collapsedlong)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### *Long* to *Event Study*\n",
    "\n",
    "Notice that:\n",
    "\n",
    "- `j` splits into `j1` and `j2`, which indicate the first and second firm id in the event study, respectively\n",
    "- `y` splits into `y1` and `y2`, which indicate the first and second income in the event study, respectively\n",
    "- `t` splits into `t1` and `t2`, which indicate the first and second period in the event study, respectively\n",
    "\n",
    "<div class=\"alert alert-info\">\n",
    "\n",
    "Note\n",
    "\n",
    "For stayers (individuals who stay at the same firm for all their observations), each row in the event study represents a single observation, since they never move firms.\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>i</th>\n",
       "      <th>j1</th>\n",
       "      <th>j2</th>\n",
       "      <th>y1</th>\n",
       "      <th>y2</th>\n",
       "      <th>t1</th>\n",
       "      <th>t2</th>\n",
       "      <th>m</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>24</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>0.086822</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>140</td>\n",
       "      <td>1.157531</td>\n",
       "      <td>-0.682035</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40637</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>30</td>\n",
       "      <td>-0.256372</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40638</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>126</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40639</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>126</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40640</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>176</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40641</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>176</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>1.796405</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>40642 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i   j1   j2        y1        y2  t1  t2  m\n",
       "0         0   31   24 -0.066354 -1.319229   0   1  1\n",
       "1         0   24   24 -1.319229 -2.141775   1   2  0\n",
       "2         0   24   24 -2.141775 -1.831186   2   3  0\n",
       "3         0   24   24 -1.831186  0.086822   3   4  0\n",
       "4         1  140  140  1.157531 -0.682035   0   1  0\n",
       "...     ...  ...  ...       ...       ...  ..  .. ..\n",
       "40637  9998  139   30 -0.256372 -0.136980   3   4  1\n",
       "40638  9999  188  126  2.877201  1.415829   0   1  1\n",
       "40639  9999  126  126  1.415829  0.772108   1   2  0\n",
       "40640  9999  126  176  0.772108  2.263156   2   3  1\n",
       "40641  9999  176  176  2.263156  1.796405   3   4  0\n",
       "\n",
       "[40642 rows x 8 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bdf_eventstudy = bdf_long.to_eventstudy()\n",
    "display(bdf_eventstudy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### *Collapsed Long* to *Collapsed Event Study*\n",
    "\n",
    "Notice that:\n",
    "\n",
    "- `j` splits into `j1` and `j2`, which indicate the first and second firm id in the event study, respectively\n",
    "- `y` splits into `y1` and `y2`, which indicate the first and second income in the event study, respectively\n",
    "- `t1` splits into `t11` and `t12`, which indicate the start the end of the spell for the first observation in the event study, respectively\n",
    "- `t2` splits into `t21` and `t22`, which indicate the start the end of the spell for the second observation in the event study, respectively\n",
    "- `w` splits into `w1` and `w2`, which indicate number of observations in the first and second spell in the event study, respectively"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>i</th>\n",
       "      <th>j1</th>\n",
       "      <th>j2</th>\n",
       "      <th>y1</th>\n",
       "      <th>y2</th>\n",
       "      <th>t11</th>\n",
       "      <th>t12</th>\n",
       "      <th>t21</th>\n",
       "      <th>t22</th>\n",
       "      <th>w1</th>\n",
       "      <th>w2</th>\n",
       "      <th>m</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>24</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>-1.301342</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>81</td>\n",
       "      <td>0.237748</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "      <td>9</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>-1.098072</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>126</td>\n",
       "      <td>131</td>\n",
       "      <td>0.538577</td>\n",
       "      <td>0.628338</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>131</td>\n",
       "      <td>33</td>\n",
       "      <td>0.628338</td>\n",
       "      <td>-0.646154</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20326</th>\n",
       "      <td>9996</td>\n",
       "      <td>105</td>\n",
       "      <td>156</td>\n",
       "      <td>0.493585</td>\n",
       "      <td>0.097240</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20327</th>\n",
       "      <td>9997</td>\n",
       "      <td>147</td>\n",
       "      <td>98</td>\n",
       "      <td>-0.331835</td>\n",
       "      <td>-1.363738</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20328</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>30</td>\n",
       "      <td>0.361819</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20329</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>126</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20330</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>176</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>2.029781</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20331 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i   j1   j2        y1        y2  t11  t12  t21  t22  w1  w2  m\n",
       "0         0   31   24 -0.066354 -1.301342    0    0    1    4   1   4  1\n",
       "1         1  140   81  0.237748 -1.262375    0    1    2    2   2   1  1\n",
       "2         1   81    9 -1.262375 -1.098072    2    2    3    4   1   2  1\n",
       "3         2  126  131  0.538577  0.628338    0    0    1    2   1   2  1\n",
       "4         2  131   33  0.628338 -0.646154    1    2    3    4   2   2  1\n",
       "...     ...  ...  ...       ...       ...  ...  ...  ...  ...  ..  .. ..\n",
       "20326  9996  105  156  0.493585  0.097240    0    1    2    4   2   3  1\n",
       "20327  9997  147   98 -0.331835 -1.363738    0    1    2    4   2   3  1\n",
       "20328  9998  139   30  0.361819 -0.136980    0    3    4    4   4   1  1\n",
       "20329  9999  188  126  2.877201  1.093969    0    0    1    2   1   2  1\n",
       "20330  9999  126  176  1.093969  2.029781    1    2    3    4   2   2  1\n",
       "\n",
       "[20331 rows x 12 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bdf_collapsedeventstudy = bdf_collapsedlong.to_eventstudy()\n",
    "display(bdf_collapsedeventstudy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We showed how to get from *Long* to any other format, but feel free to experiment and see what happens when you convert in other directions!\n",
    "\n",
    "## Initializing from different formats\n",
    "\n",
    "If your data is saved in a format other than *Long*, it's simple to construct a BipartiteDataFrame.\n",
    "\n",
    "#### Initializing from *Collapsed Long* format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>i</th>\n",
       "      <th>j</th>\n",
       "      <th>y</th>\n",
       "      <th>t1</th>\n",
       "      <th>t2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.301342</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>0.237748</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>-1.098072</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29684</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>0.361819</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29685</th>\n",
       "      <td>9998</td>\n",
       "      <td>30</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29686</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29687</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29688</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>2.029781</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>29689 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i    j         y  t1  t2\n",
       "0         0   31 -0.066354   0   0\n",
       "1         0   24 -1.301342   1   4\n",
       "2         1  140  0.237748   0   1\n",
       "3         1   81 -1.262375   2   2\n",
       "4         1    9 -1.098072   3   4\n",
       "...     ...  ...       ...  ..  ..\n",
       "29684  9998  139  0.361819   0   3\n",
       "29685  9998   30 -0.136980   4   4\n",
       "29686  9999  188  2.877201   0   0\n",
       "29687  9999  126  1.093969   1   2\n",
       "29688  9999  176  2.029781   3   4\n",
       "\n",
       "[29689 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "i = bdf_collapsedlong['i']\n",
    "j = bdf_collapsedlong['j']\n",
    "y = bdf_collapsedlong['y']\n",
    "t1 = bdf_collapsedlong['t1']\n",
    "t2 = bdf_collapsedlong['t2']\n",
    "bdf_collapsedlong = bpd.BipartiteDataFrame(\n",
    "    i=i, j=j, y=y, t1=t1, t2=t2\n",
    ")\n",
    "display(bdf_collapsedlong)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's check the datatype:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bipartitepandas.bipartitelongcollapsed.BipartiteLongCollapsed"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(bdf_collapsedlong)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Initializing from *Event Study* format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>i</th>\n",
       "      <th>j1</th>\n",
       "      <th>j2</th>\n",
       "      <th>y1</th>\n",
       "      <th>y2</th>\n",
       "      <th>t1</th>\n",
       "      <th>t2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>24</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.319229</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-2.141775</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>-1.831186</td>\n",
       "      <td>0.086822</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>140</td>\n",
       "      <td>1.157531</td>\n",
       "      <td>-0.682035</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40637</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>30</td>\n",
       "      <td>-0.256372</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40638</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>126</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40639</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>126</td>\n",
       "      <td>1.415829</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40640</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>176</td>\n",
       "      <td>0.772108</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40641</th>\n",
       "      <td>9999</td>\n",
       "      <td>176</td>\n",
       "      <td>176</td>\n",
       "      <td>2.263156</td>\n",
       "      <td>1.796405</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>40642 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i   j1   j2        y1        y2  t1  t2\n",
       "0         0   31   24 -0.066354 -1.319229   0   1\n",
       "1         0   24   24 -1.319229 -2.141775   1   2\n",
       "2         0   24   24 -2.141775 -1.831186   2   3\n",
       "3         0   24   24 -1.831186  0.086822   3   4\n",
       "4         1  140  140  1.157531 -0.682035   0   1\n",
       "...     ...  ...  ...       ...       ...  ..  ..\n",
       "40637  9998  139   30 -0.256372 -0.136980   3   4\n",
       "40638  9999  188  126  2.877201  1.415829   0   1\n",
       "40639  9999  126  126  1.415829  0.772108   1   2\n",
       "40640  9999  126  176  0.772108  2.263156   2   3\n",
       "40641  9999  176  176  2.263156  1.796405   3   4\n",
       "\n",
       "[40642 rows x 7 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "i = bdf_eventstudy['i']\n",
    "j1 = bdf_eventstudy['j1']\n",
    "j2 = bdf_eventstudy['j2']\n",
    "y1 = bdf_eventstudy['y1']\n",
    "y2 = bdf_eventstudy['y2']\n",
    "t1 = bdf_eventstudy['t1']\n",
    "t2 = bdf_eventstudy['t2']\n",
    "bdf_eventstudy = bpd.BipartiteDataFrame(\n",
    "    i=i, j1=j1, j2=j2, y1=y1, y2=y2, t1=t1, t2=t2\n",
    ")\n",
    "display(bdf_eventstudy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's check the datatype:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bipartitepandas.bipartiteeventstudy.BipartiteEventStudy"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(bdf_eventstudy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Initializing from *Collapsed Event Study* format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>i</th>\n",
       "      <th>j1</th>\n",
       "      <th>j2</th>\n",
       "      <th>y1</th>\n",
       "      <th>y2</th>\n",
       "      <th>t11</th>\n",
       "      <th>t12</th>\n",
       "      <th>t21</th>\n",
       "      <th>t22</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>24</td>\n",
       "      <td>-0.066354</td>\n",
       "      <td>-1.301342</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>81</td>\n",
       "      <td>0.237748</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "      <td>9</td>\n",
       "      <td>-1.262375</td>\n",
       "      <td>-1.098072</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>126</td>\n",
       "      <td>131</td>\n",
       "      <td>0.538577</td>\n",
       "      <td>0.628338</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>131</td>\n",
       "      <td>33</td>\n",
       "      <td>0.628338</td>\n",
       "      <td>-0.646154</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20326</th>\n",
       "      <td>9996</td>\n",
       "      <td>105</td>\n",
       "      <td>156</td>\n",
       "      <td>0.493585</td>\n",
       "      <td>0.097240</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20327</th>\n",
       "      <td>9997</td>\n",
       "      <td>147</td>\n",
       "      <td>98</td>\n",
       "      <td>-0.331835</td>\n",
       "      <td>-1.363738</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20328</th>\n",
       "      <td>9998</td>\n",
       "      <td>139</td>\n",
       "      <td>30</td>\n",
       "      <td>0.361819</td>\n",
       "      <td>-0.136980</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20329</th>\n",
       "      <td>9999</td>\n",
       "      <td>188</td>\n",
       "      <td>126</td>\n",
       "      <td>2.877201</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20330</th>\n",
       "      <td>9999</td>\n",
       "      <td>126</td>\n",
       "      <td>176</td>\n",
       "      <td>1.093969</td>\n",
       "      <td>2.029781</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20331 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          i   j1   j2        y1        y2  t11  t12  t21  t22\n",
       "0         0   31   24 -0.066354 -1.301342    0    0    1    4\n",
       "1         1  140   81  0.237748 -1.262375    0    1    2    2\n",
       "2         1   81    9 -1.262375 -1.098072    2    2    3    4\n",
       "3         2  126  131  0.538577  0.628338    0    0    1    2\n",
       "4         2  131   33  0.628338 -0.646154    1    2    3    4\n",
       "...     ...  ...  ...       ...       ...  ...  ...  ...  ...\n",
       "20326  9996  105  156  0.493585  0.097240    0    1    2    4\n",
       "20327  9997  147   98 -0.331835 -1.363738    0    1    2    4\n",
       "20328  9998  139   30  0.361819 -0.136980    0    3    4    4\n",
       "20329  9999  188  126  2.877201  1.093969    0    0    1    2\n",
       "20330  9999  126  176  1.093969  2.029781    1    2    3    4\n",
       "\n",
       "[20331 rows x 9 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "i = bdf_collapsedeventstudy['i']\n",
    "j1 = bdf_collapsedeventstudy['j1']\n",
    "j2 = bdf_collapsedeventstudy['j2']\n",
    "y1 = bdf_collapsedeventstudy['y1']\n",
    "y2 = bdf_collapsedeventstudy['y2']\n",
    "t11 = bdf_collapsedeventstudy['t11']\n",
    "t12 = bdf_collapsedeventstudy['t12']\n",
    "t21 = bdf_collapsedeventstudy['t21']\n",
    "t22 = bdf_collapsedeventstudy['t22']\n",
    "bdf_collapsedeventstudy = bpd.BipartiteDataFrame(\n",
    "    i=i, j1=j1, j2=j2, y1=y1, y2=y2,\n",
    "    t11=t11, t12=t12, t21=t21, t22=t22\n",
    ")\n",
    "display(bdf_collapsedeventstudy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's check the datatype:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bipartitepandas.bipartiteeventstudycollapsed.BipartiteEventStudyCollapsed"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(bdf_collapsedeventstudy)"
   ]
  }
 ],
 "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}