feed-generator/Untitled.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c0c52617",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from ipywidgets import widgets\n",
    "from IPython.display import display\n",
    "\n",
    "%matplotlib notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d20f8fbf",
   "metadata": {},
   "outputs": [],
   "source": [
    "posts = pd.read_sql_table('post', 'sqlite:///db.sqlite')\n",
    "likes = pd.read_sql_table('like', 'sqlite:///db.sqlite')\n",
    "reposts = pd.read_sql_table('repost', 'sqlite:///db.sqlite')\n",
    "follows = pd.read_sql_table('follow', 'sqlite:///db.sqlite')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7140b9bd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "169f0c9f67a84aecb38cb8c94336f656",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Tab(children=(Output(), Output(), Output(), Output()), selected_index=0, titles=('posts', 'likes', 'reposts', …"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tabs = []\n",
    "for tab in (posts, likes, reposts, follows):\n",
    "    widg = widgets.Output()\n",
    "    with widg:\n",
    "        display(tab)\n",
    "    tabs.append(widg)\n",
    "        \n",
    "tab = widgets.Tab(children=tabs, titles = ['posts', 'likes', 'reposts', 'follows'])\n",
    "tab"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc1b5a30",
   "metadata": {},
   "source": [
    "Basic Summaries\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "689b5e00",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Timespan: 1 days 00:29:00.608000\n",
      "Posting Accounts: 134910\n",
      "Liking Accounts: 201814\n",
      "Accounts that only posted: 43655\n",
      "Accounts that only liked: 110559\n",
      "Accounts that posted and liked: 91255\n",
      "\n"
     ]
    }
   ],
   "source": [
    "posts['indexedAt'] = pd.to_datetime(posts['indexedAt'])\n",
    "span = posts['indexedAt'].max() - posts['indexedAt'].min()\n",
    "posting_accounts = set(posts['authorDid'])\n",
    "liking_accounts = set(likes['authorDid'])\n",
    "posters_only = posting_accounts - liking_accounts\n",
    "likers_only = liking_accounts - posting_accounts\n",
    "posts_and_likes = posting_accounts.intersection(liking_accounts)\n",
    "\n",
    "print(f\"\"\"\n",
    "Timespan: {span}\n",
    "Posting Accounts: {len(posting_accounts)}\n",
    "Liking Accounts: {len(liking_accounts)}\n",
    "Accounts that only posted: {len(posters_only)}\n",
    "Accounts that only liked: {len(likers_only)}\n",
    "Accounts that posted and liked: {len(posts_and_likes)}\n",
    "\"\"\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "040f4a01",
   "metadata": {},
   "source": [
    "# Interaction Distributions\n",
    "\n",
    "Likes per post"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3c6a03ff",
   "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>cid</th>\n",
       "      <th>likes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>bafyreia222dxd77nwlefofspvv4zyo4vcyidfm53vxhzl...</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>bafyreia222hs2ffawpplfo3nfs2g4ibqleg7exybmxx4m...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>bafyreia222p4uouja7nmodbin7msvfyky65zd4epn4fqq...</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>bafyreia222tx72zwcfs5mzdtssw4xcpwvmzsan6lk4yrh...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>bafyreia223lumxspphn5wcbw2v65aeon3l2t3frtgrik5...</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637533</th>\n",
       "      <td>bafyreihzzyn6h4roumu7cebt2ywblpxryz42tt4yd66vb...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637534</th>\n",
       "      <td>bafyreihzzyzsfj2qo4lonn3ny6kht6xy4squzfmha4luf...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637535</th>\n",
       "      <td>bafyreihzzzd6jvfod4gmeucp4wgtn2fzxw6lggztkmeum...</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637536</th>\n",
       "      <td>bafyreihzzzfwyi7hxm5wusper7hn6qbi2bx6gibiz4skm...</td>\n",
       "      <td>95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637537</th>\n",
       "      <td>bafyreihzzzgh23q2dplc32rqfuuqn6seimmujmtrq66dc...</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>637538 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                      cid  likes\n",
       "0       bafyreia222dxd77nwlefofspvv4zyo4vcyidfm53vxhzl...     28\n",
       "1       bafyreia222hs2ffawpplfo3nfs2g4ibqleg7exybmxx4m...      1\n",
       "2       bafyreia222p4uouja7nmodbin7msvfyky65zd4epn4fqq...      5\n",
       "3       bafyreia222tx72zwcfs5mzdtssw4xcpwvmzsan6lk4yrh...      1\n",
       "4       bafyreia223lumxspphn5wcbw2v65aeon3l2t3frtgrik5...      3\n",
       "...                                                   ...    ...\n",
       "637533  bafyreihzzyn6h4roumu7cebt2ywblpxryz42tt4yd66vb...      1\n",
       "637534  bafyreihzzyzsfj2qo4lonn3ny6kht6xy4squzfmha4luf...      1\n",
       "637535  bafyreihzzzd6jvfod4gmeucp4wgtn2fzxw6lggztkmeum...      2\n",
       "637536  bafyreihzzzfwyi7hxm5wusper7hn6qbi2bx6gibiz4skm...     95\n",
       "637537  bafyreihzzzgh23q2dplc32rqfuuqn6seimmujmtrq66dc...     19\n",
       "\n",
       "[637538 rows x 2 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "post_likes = likes.groupby('subjectCid'\n",
    "    ).agg(likes=('uri', 'count')\n",
    "    ).reset_index(\n",
    "    ).rename(columns={'subjectCid':'cid'})\n",
    "post_likes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ff9773ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "posts = posts.merge(post_likes, left_on='cid', right_on='cid', how='left')\n",
    "posts.loc[posts['likes'].isna(), 'likes'] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2523ba0a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "y = posts.sort_values(by='likes')['likes'].cumsum()\n",
    "plt.plot(y.reset_index(drop=True))\n",
    "plt.title('Cumulative sum of likes by post')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "ee048235-1d61-4209-8c84-bf51e3f246dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjAAAAGzCAYAAAAxPS2EAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA+RklEQVR4nO3de3wU9b3/8ffmsksCbMIt2UQCjaJAuClBwx6VqqQEjLcjWhAUVITCCVbAAzTn8EPUajx4RRGotRrbggqtV1AwBAheAmJKyk1TVDRU2ATBZAEhIcn394fNyMotCaHLJK/n4zGPBzPzmZnPjOvm/Zj9zq7DGGMEAABgIyHBbgAAAKC+CDAAAMB2CDAAAMB2CDAAAMB2CDAAAMB2CDAAAMB2CDAAAMB2CDAAAMB2CDAAAMB2CDBAM/XVV1/J4XAoOzvbWnb77berVatWwWsKAOqIAAM0QdnZ2XI4HPrkk0+C3Qrq4eGHH9Ybb7wR7DYAWwgLdgMAgqNz5846dOiQwsPDg90K/uXhhx/WTTfdpBtuuCHYrQBnPe7AAM2Uw+FQixYtFBoaGuxWguLgwYPBbgHAaSDAAM3U8cbAHE9hYaE6dOigK664QgcOHJAkffPNN7rzzjsVGxsrl8ulHj166IUXXjhm22eeeUY9evRQZGSk2rRpo379+mnRokUnPd6aNWvkcDj06quv6n/+53/k8XjUsmVLXXfdddq5c+cx9evXr9fgwYMVFRWlyMhI/fznP9eHH34YUDNr1iw5HA5t27ZNI0aMUJs2bXTZZZedsIfaj+DWrl2rX/3qV2rXrp3cbrdGjRql77777pj6efPmqUePHnK5XIqPj1dGRobKysoCarZv366hQ4fK4/GoRYsW6tixo4YPH67y8nJJPwTKgwcP6qWXXpLD4ZDD4dDtt99+0msFNGd8hATghDZs2KC0tDT169dPb775piIiIlRSUqL+/fvL4XBo4sSJ6tChg959912NGTNGfr9fkyZNkiT9/ve/169//WvddNNNuueee3T48GFt2rRJ69ev14gRI0557IceekgOh0PTp09XaWmpnnrqKaWmpqqwsFARERGSpFWrVmnIkCFKTk7Wfffdp5CQEL344ou66qqr9P777+uSSy4J2OfNN9+s888/Xw8//LCMMafsYeLEiYqOjtasWbNUVFSk+fPn6+uvv7ZClvRDOLr//vuVmpqqCRMmWHUbNmzQhx9+qPDwcFVWViotLU0VFRW6++675fF49M0332jp0qUqKytTVFSU/vSnP+muu+7SJZdconHjxkmSzjvvvPr85wKaFwOgyXnxxReNJLNhw4YT1uzYscNIMi+++KK1bPTo0aZly5bGGGM++OAD43a7TXp6ujl8+LBVM2bMGBMXF2e+/fbbgP0NHz7cREVFme+//94YY8z1119vevToUe/eV69ebSSZc845x/j9fmv54sWLjSQzZ84cY4wxNTU15vzzzzdpaWmmpqbGqvv+++9NYmKi+cUvfmEtu++++4wkc8stt9Sph9rrl5ycbCorK63ls2fPNpLMm2++aYwxprS01DidTjNo0CBTXV1t1c2dO9dIMi+88IIxxpiNGzcaSWbJkiUnPW7Lli3N6NGj69Qj0NzxERKAY6xevVppaWkaOHCgXnvtNblcLkmSMUZ//etfde2118oYo2+//daa0tLSVF5err/97W+SpOjoaP3zn//Uhg0bGtTDqFGj1Lp1a2v+pptuUlxcnN555x1JP3y0tX37do0YMUJ79+61+jh48KAGDhyotWvXqqamJmCf48ePr1cP48aNCxjkPGHCBIWFhVk9rFy5UpWVlZo0aZJCQn58Ox07dqzcbreWLVsmSYqKipIkrVixQt9//329egBwfHyEBCDA4cOHlZ6eruTkZC1evFhhYT++TezZs0dlZWV67rnn9Nxzzx13+9LSUknS9OnTtXLlSl1yySXq0qWLBg0apBEjRujSSy+tUx/nn39+wLzD4VCXLl301VdfSfphTIkkjR49+oT7KC8vV5s2baz5xMTEOh37RD20atVKcXFxVg9ff/21JKlr164BdU6nU+eee661PjExUVOmTNETTzyhhQsX6vLLL9d1112nW2+91Qo3AOqHAAMggMvl0tVXX60333xTy5cv1zXXXGOtq72jceutt54wOPTu3VuS1L17dxUVFWnp0qVavny5/vrXv2revHmaOXOm7r///tPus7aXRx99VBdeeOFxa376pXy1Y2eC4fHHH9ftt9+uN998U++9955+/etfKysrS+vWrVPHjh2D1hdgVwQYAAEcDocWLlyo66+/XjfffLPeffddXXHFFZKkDh06qHXr1qqurlZqauop99WyZUsNGzZMw4YNU2VlpW688UY99NBDyszMVIsWLU66be0dllrGGH3++edWQKod4Op2u+vUS0Ns375dV155pTV/4MAB7d69W1dffbWkH75LR5KKiop07rnnWnWVlZXasWPHMX316tVLvXr10owZM/TRRx/p0ksv1YIFC/Tb3/5WkqyBwQBOjTEwAI7hdDr12muv6eKLL9a1116rjz/+WJIUGhqqoUOH6q9//au2bNlyzHZ79uyx/r13795j9pmUlCRjjI4cOXLKHv74xz9q//791vxf/vIX7d69W0OGDJEkJScn67zzztNjjz1mPd59ol4a6rnnngvodf78+aqqqrJ6SE1NldPp1NNPPx3wVNMf/vAHlZeXKz09XZLk9/tVVVUVsO9evXopJCREFRUV1rKWLVse8/g1gOPjDgzQhL3wwgtavnz5McvvueeeU24bERGhpUuX6qqrrtKQIUOUl5ennj176pFHHtHq1auVkpKisWPHKikpSfv27dPf/vY3rVy5Uvv27ZMkDRo0SB6PR5deeqliY2P16aefau7cuUpPTw8YnHsibdu21WWXXaY77rhDJSUleuqpp9SlSxeNHTtWkhQSEqLnn39eQ4YMUY8ePXTHHXfonHPO0TfffKPVq1fL7Xbr7bffrucVC1RZWamBAwfql7/8pYqKijRv3jxddtlluu666yT9cEcqMzNT999/vwYPHqzrrrvOqrv44ot16623Svrhce+JEyfq5ptv1gUXXKCqqir96U9/sgJhreTkZK1cuVJPPPGE4uPjlZiYqJSUlNM6B6DJCuozUADOiNrHgE807dy585SPUdf69ttvTVJSkvF4PGb79u3GGGNKSkpMRkaGSUhIMOHh4cbj8ZiBAwea5557ztrud7/7nRkwYIBp166dcblc5rzzzjNTp0415eXlJ+299jHql19+2WRmZpqYmBgTERFh0tPTzddff31M/caNG82NN95oHadz587ml7/8pcnNzbVqah+j3rNnT72uX15enhk3bpxp06aNadWqlRk5cqTZu3fvMfVz58413bp1M+Hh4SY2NtZMmDDBfPfdd9b6L7/80tx5553mvPPOMy1atDBt27Y1V155pVm5cmXAfj777DMzYMAAExERYSTxSDVwEg5j6vBtTgDwb7JmzRpdeeWVWrJkiW666aag9JCdna077rhDGzZsUL9+/YLSA4CTYwwMAACwHQIMAACwHQIMAACwHcbAAAAA2+EODAAAsB0CDAAAsJ0m+0V2NTU12rVrl1q3bs3XcwMAYBPGGO3fv1/x8fEBv/L+U002wOzatUsJCQnBbgMAADTAzp07T/pDp002wNR+VfnOnTvldruD3A0AAKgLv9+vhISEU/7kSJMNMLUfG7ndbgIMAAA2c6rhHwziBQAAtkOAAQAAtkOAAQAAtnNaAeaRRx6Rw+HQpEmTrGWHDx9WRkaG2rVrp1atWmno0KEqKSkJ2K64uFjp6emKjIxUTEyMpk6dqqqqqoCaNWvWqG/fvnK5XOrSpYuys7NPp1UAANCENDjAbNiwQb/73e/Uu3fvgOWTJ0/W22+/rSVLligvL0+7du3SjTfeaK2vrq5Wenq6Kisr9dFHH+mll15Sdna2Zs6cadXs2LFD6enpuvLKK1VYWKhJkybprrvu0ooVKxraLgAAaEpMA+zfv9+cf/75Jicnx/z85z8399xzjzHGmLKyMhM
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "y = posts.sort_values(by='likes')['likes']\n",
    "plt.plot(y.reset_index(drop=True))\n",
    "plt.title('Likes per post')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1b9264f4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.3944738883046787"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sum(posts['likes'] == 0) / posts.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "6744b53f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6932166446400256"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sum(posts['likes'] <= 1) / posts.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "187f935d",
   "metadata": {},
   "source": [
    "Likes per account"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e9b4f141",
   "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>account</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>did:plc:lhfbzpkdw2jk5i6im5pd2mi5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>did:plc:btaxnpi4resvm2uz4n7tcp3f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>did:plc:ky3xc27d4ct6ntwxsu7tjpx7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>did:plc:z3ds6onyuoyfnx42qgoddhbp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>did:plc:hqzxqh634sd546rfoazslb5h</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269812</th>\n",
       "      <td>did:plc:p6t6ari5h7bcim3iq3zs3fwr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269813</th>\n",
       "      <td>did:plc:omiligdebd4dwcthsxvn2fgi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269814</th>\n",
       "      <td>did:plc:fg6wnip4zgzz3277lz7djpet</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269815</th>\n",
       "      <td>did:plc:5czjjn5zjvkxec6rcvvuidgq</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269816</th>\n",
       "      <td>did:plc:jdiqko5hqd3chtepm4docjsc</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>269817 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 account\n",
       "0       did:plc:lhfbzpkdw2jk5i6im5pd2mi5\n",
       "1       did:plc:btaxnpi4resvm2uz4n7tcp3f\n",
       "2       did:plc:ky3xc27d4ct6ntwxsu7tjpx7\n",
       "3       did:plc:z3ds6onyuoyfnx42qgoddhbp\n",
       "4       did:plc:hqzxqh634sd546rfoazslb5h\n",
       "...                                  ...\n",
       "269812  did:plc:p6t6ari5h7bcim3iq3zs3fwr\n",
       "269813  did:plc:omiligdebd4dwcthsxvn2fgi\n",
       "269814  did:plc:fg6wnip4zgzz3277lz7djpet\n",
       "269815  did:plc:5czjjn5zjvkxec6rcvvuidgq\n",
       "269816  did:plc:jdiqko5hqd3chtepm4docjsc\n",
       "\n",
       "[269817 rows x 1 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accounts = pd.concat([likes['subjectDid'], likes['authorDid'], posts['authorDid']])\n",
    "\n",
    "accounts = pd.DataFrame({'account': accounts.unique()})\n",
    "\n",
    "accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "05c7fe61",
   "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>account</th>\n",
       "      <th>likes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>did:plc:2224x6c53tqc6dpnbamce2yg</td>\n",
       "      <td>64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>did:plc:222ombk5yfjty5jw6r6566tk</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>did:plc:222p42fegwhwfyrc3gqam76j</td>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>did:plc:222qqedb2kgz3ulwbpboltw2</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>did:plc:222rnvnta2lbl364bog2plxw</td>\n",
       "      <td>575</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133639</th>\n",
       "      <td>did:plc:zzz2awwhi7smhg3qn6th37xg</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133640</th>\n",
       "      <td>did:plc:zzza7zo2lho4etts27epjgpc</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133641</th>\n",
       "      <td>did:plc:zzzj2bhzojle3nic4wpwmcsm</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133642</th>\n",
       "      <td>did:plc:zzznrmktdln6qlvsqigd6ubc</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133643</th>\n",
       "      <td>did:plc:zzzzet3m2cnkmtsjyusz7uzs</td>\n",
       "      <td>67</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>133644 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 account  likes\n",
       "0       did:plc:2224x6c53tqc6dpnbamce2yg     64\n",
       "1       did:plc:222ombk5yfjty5jw6r6566tk      4\n",
       "2       did:plc:222p42fegwhwfyrc3gqam76j    119\n",
       "3       did:plc:222qqedb2kgz3ulwbpboltw2      6\n",
       "4       did:plc:222rnvnta2lbl364bog2plxw    575\n",
       "...                                  ...    ...\n",
       "133639  did:plc:zzz2awwhi7smhg3qn6th37xg      2\n",
       "133640  did:plc:zzza7zo2lho4etts27epjgpc      1\n",
       "133641  did:plc:zzzj2bhzojle3nic4wpwmcsm      1\n",
       "133642  did:plc:zzznrmktdln6qlvsqigd6ubc      7\n",
       "133643  did:plc:zzzzet3m2cnkmtsjyusz7uzs     67\n",
       "\n",
       "[133644 rows x 2 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "account_likes = likes.groupby('subjectDid'\n",
    "    ).agg(likes=('uri', 'count')\n",
    "    ).reset_index(\n",
    "    ).rename(columns={'subjectDid':'account'})\n",
    "account_likes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "956aa546",
   "metadata": {},
   "outputs": [],
   "source": [
    "accounts = accounts.merge(account_likes, left_on='account', right_on='account', how='left')\n",
    "accounts.loc[accounts['likes'].isna(), 'likes'] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "152aa08c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "y_accounts = accounts.sort_values(by='likes')['likes'].cumsum().reset_index(drop=True)\n",
    "plt.plot(y_accounts)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "33ec3b44",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00      0.0\n",
       "0.25      0.0\n",
       "0.50      0.0\n",
       "0.75      3.0\n",
       "0.90     13.0\n",
       "0.95     33.0\n",
       "0.99    152.0\n",
       "Name: likes, dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quants = [0, 0.25, 0.5, 0.75, 0.9, .95, .99]\n",
    "quantiles = accounts['likes'].quantile(quants)\n",
    "quantiles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "fe29f683",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 0, 196497, 241490, 256295, 267113]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted_accounts = accounts.sort_values(by='likes')\n",
    "quant_idx = [np.where(sorted_accounts['likes'] >= q)[0][0] for q in quantiles]\n",
    "quant_idx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "36b72cea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([136173, 136174, 136175, ..., 269814, 269815, 269816]),)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.where(sorted_accounts['likes'] > 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c10b03d4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "cumsum_accounts = sorted_accounts['likes'].cumsum().reset_index(drop=True)\n",
    "\n",
    "plt.plot(cumsum_accounts)\n",
    "\n",
    "for q_label, q_idx in zip(quants, quant_idx):\n",
    "    plt.axvline(x=q_idx, color='black', linestyle='--', linewidth=.1)\n",
    "    plt.annotate(text=str(q_label), xy=(q_idx, max(cumsum_accounts)), xycoords='data')\n",
    "\n",
    "plt.title('Cumulative sum of likes received by accounts')    \n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "edbf19cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5046865097454941"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(accounts[accounts['likes']==0]['likes']) / len(accounts)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbf4bf37",
   "metadata": {},
   "source": [
    "Proportion of interactions received by the 99th and 95th percentile of most interacted with accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "da3a792a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.442995115042035"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "percentile = 0.99\n",
    "accounts.loc[accounts['likes'] >= quantiles[percentile], 'likes'].sum() / accounts['likes'].sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "f018a478",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.73839113058112"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "percentile = 0.95\n",
    "accounts.loc[accounts['likes'] >= quantiles[percentile], 'likes'].sum() / accounts['likes'].sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "66961868",
   "metadata": {},
   "source": [
    "Excluding interactions with the top (percentile) accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d6a7119",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "db949eae",
   "metadata": {},
   "outputs": [],
   "source": [
    "top_accounts = accounts.loc[accounts['likes'] >= quantiles[percentile]]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "660122a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "top_posts = posts.loc[posts['authorDid'].isin(top_accounts['account'])]\n",
    "non_top_posts = posts.loc[~posts['authorDid'].isin(top_accounts['account'])]\n",
    "top_threads = posts.loc[np.logical_or(\n",
    "    posts['replyRoot'].isin(top_posts['uri']),\n",
    "    posts['replyParent'].isin(top_posts['uri'])\n",
    ")]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "9bf35229",
   "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>uri</th>\n",
       "      <th>cid</th>\n",
       "      <th>authorDid</th>\n",
       "      <th>indexedAt</th>\n",
       "      <th>createdAt</th>\n",
       "      <th>subjectUri</th>\n",
       "      <th>subjectCid</th>\n",
       "      <th>subjectDid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>at://did:plc:iomleec6ojlmywkrwqjbr57o/app.bsky...</td>\n",
       "      <td>bafyreidgvotn7srwum67gsv5rkjbiybtwjwpei5tvnrws...</td>\n",
       "      <td>did:plc:iomleec6ojlmywkrwqjbr57o</td>\n",
       "      <td>2023-12-27T03:12:43.896Z</td>\n",
       "      <td>2023-12-27T03:12:42.248Z</td>\n",
       "      <td>at://did:plc:btaxnpi4resvm2uz4n7tcp3f/app.bsky...</td>\n",
       "      <td>bafyreifsu35qmmr66fooemrvkke6rdd3qq5mdjvtsqs5y...</td>\n",
       "      <td>did:plc:btaxnpi4resvm2uz4n7tcp3f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>at://did:plc:cakburidjcwro44hweyxazjg/app.bsky...</td>\n",
       "      <td>bafyreiawjvozspsyg5yelmmnb3hs4sp7vsjqddpr6t636...</td>\n",
       "      <td>did:plc:cakburidjcwro44hweyxazjg</td>\n",
       "      <td>2023-12-27T03:12:43.968Z</td>\n",
       "      <td>2023-12-27T03:12:43.705Z</td>\n",
       "      <td>at://did:plc:ky3xc27d4ct6ntwxsu7tjpx7/app.bsky...</td>\n",
       "      <td>bafyreib7r6526nciyilv3ky345zbmbh4w3tsarc74z72c...</td>\n",
       "      <td>did:plc:ky3xc27d4ct6ntwxsu7tjpx7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>at://did:plc:kwmi7ftr3g7hbohzauip3mxn/app.bsky...</td>\n",
       "      <td>bafyreiasf7jxlprpiix6eo4x7ifb7zeaduu2kcftyxpyi...</td>\n",
       "      <td>did:plc:kwmi7ftr3g7hbohzauip3mxn</td>\n",
       "      <td>2023-12-27T03:12:44.068Z</td>\n",
       "      <td>2023-12-27T03:12:45.463Z</td>\n",
       "      <td>at://did:plc:wxj3cnbus6js5f7hjwowoxoq/app.bsky...</td>\n",
       "      <td>bafyreifcftx7xktszbhmylitz34hf66ivmboymshgtchl...</td>\n",
       "      <td>did:plc:wxj3cnbus6js5f7hjwowoxoq</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>at://did:plc:43eonpufv7sg6hglanhbhraw/app.bsky...</td>\n",
       "      <td>bafyreieyyoeepsexamgybk5dun3sqxwiqftas2ent47np...</td>\n",
       "      <td>did:plc:43eonpufv7sg6hglanhbhraw</td>\n",
       "      <td>2023-12-27T03:12:44.287Z</td>\n",
       "      <td>2023-12-27T03:12:44.003Z</td>\n",
       "      <td>at://did:plc:mgsxkvihm65lecdzbavku3tk/app.bsky...</td>\n",
       "      <td>bafyreibyyeobzn34r4edmeiaarancnpjbuesdiuqxkxfy...</td>\n",
       "      <td>did:plc:mgsxkvihm65lecdzbavku3tk</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>at://did:plc:ipepj5vzwwzvggali4tnccwj/app.bsky...</td>\n",
       "      <td>bafyreiht7xdi2cuc6bwoer4qcf5nwzekyt7kvwq6cv4la...</td>\n",
       "      <td>did:plc:ipepj5vzwwzvggali4tnccwj</td>\n",
       "      <td>2023-12-27T03:12:44.369Z</td>\n",
       "      <td>2023-12-27T03:12:43.406Z</td>\n",
       "      <td>at://did:plc:e4r2dxzbadqabu63wne4tosx/app.bsky...</td>\n",
       "      <td>bafyreibk6afarwpw7rdzifkxbi5kgy36tolpe45lxvjzq...</td>\n",
       "      <td>did:plc:e4r2dxzbadqabu63wne4tosx</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>2431516</th>\n",
       "      <td>at://did:plc:feaa5k4utn2gayj2bxsvx3cx/app.bsky...</td>\n",
       "      <td>bafyreifm7bfz6t22liztgjjtnrm3svwiuyno37chgh4ki...</td>\n",
       "      <td>did:plc:feaa5k4utn2gayj2bxsvx3cx</td>\n",
       "      <td>2023-12-28T03:41:47.605Z</td>\n",
       "      <td>2023-12-28T03:41:46.687Z</td>\n",
       "      <td>at://did:plc:q4b6fmgkkrybhf5ejbrgcmgn/app.bsky...</td>\n",
       "      <td>bafyreibl7b6qni2jxir2v4uf5wfcurx3bbsgprvodwb2s...</td>\n",
       "      <td>did:plc:q4b6fmgkkrybhf5ejbrgcmgn</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2431523</th>\n",
       "      <td>at://did:plc:7yeirudvbp5l3lmp4ycgbml5/app.bsky...</td>\n",
       "      <td>bafyreigj5r4j2cmgyops6naxbnk6qsdk7woqtjwy75fh4...</td>\n",
       "      <td>did:plc:7yeirudvbp5l3lmp4ycgbml5</td>\n",
       "      <td>2023-12-28T03:41:47.666Z</td>\n",
       "      <td>2023-12-28T03:41:46.741Z</td>\n",
       "      <td>at://did:plc:fllmcdrrhebd55j4mp43igmb/app.bsky...</td>\n",
       "      <td>bafyreiatd54b5pcpu2f2cysdavzcv2iqtdput7orhgbnt...</td>\n",
       "      <td>did:plc:fllmcdrrhebd55j4mp43igmb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2431524</th>\n",
       "      <td>at://did:plc:qdriunexx3nobe5kpltycouy/app.bsky...</td>\n",
       "      <td>bafyreifncwwa4desh5ju6re2ykvfgchnppxvzlk5spili...</td>\n",
       "      <td>did:plc:qdriunexx3nobe5kpltycouy</td>\n",
       "      <td>2023-12-28T03:41:47.686Z</td>\n",
       "      <td>2023-12-28T03:41:46.886Z</td>\n",
       "      <td>at://did:plc:i3l64jceufl7zcbk3r2sfiyc/app.bsky...</td>\n",
       "      <td>bafyreihyyllfudoppmwlzvir5uvomf4cgxogygba7dt2l...</td>\n",
       "      <td>did:plc:i3l64jceufl7zcbk3r2sfiyc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2431529</th>\n",
       "      <td>at://did:plc:ycdfsvtnosafdvko26fc7i43/app.bsky...</td>\n",
       "      <td>bafyreigvptivi6zu6njihe7wfuii6rdhj5y3l6u2azihw...</td>\n",
       "      <td>did:plc:ycdfsvtnosafdvko26fc7i43</td>\n",
       "      <td>2023-12-28T03:41:47.745Z</td>\n",
       "      <td>2023-12-28T03:41:46.679Z</td>\n",
       "      <td>at://did:plc:gxxkzpo2cw6q2ynee64rxppw/app.bsky...</td>\n",
       "      <td>bafyreicoczktoxoxozi3wurb3shbikgd5tbrukl4goavl...</td>\n",
       "      <td>did:plc:gxxkzpo2cw6q2ynee64rxppw</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2431538</th>\n",
       "      <td>at://did:plc:ct5u4vpg5ajhx6wxihtca6qh/app.bsky...</td>\n",
       "      <td>bafyreiduxg3lwaaibwaxsrsck44rzfpefliil2otfy67z...</td>\n",
       "      <td>did:plc:ct5u4vpg5ajhx6wxihtca6qh</td>\n",
       "      <td>2023-12-28T03:41:48.066Z</td>\n",
       "      <td>2023-12-28T03:41:47.744Z</td>\n",
       "      <td>at://did:plc:4msurte3uoa37puu2ma673t6/app.bsky...</td>\n",
       "      <td>bafyreifmtmvujeeccj4t7trmzof22lhxpkiqk5s5yamty...</td>\n",
       "      <td>did:plc:4msurte3uoa37puu2ma673t6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>546374 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                       uri  \\\n",
       "1        at://did:plc:iomleec6ojlmywkrwqjbr57o/app.bsky...   \n",
       "2        at://did:plc:cakburidjcwro44hweyxazjg/app.bsky...   \n",
       "6        at://did:plc:kwmi7ftr3g7hbohzauip3mxn/app.bsky...   \n",
       "10       at://did:plc:43eonpufv7sg6hglanhbhraw/app.bsky...   \n",
       "11       at://did:plc:ipepj5vzwwzvggali4tnccwj/app.bsky...   \n",
       "...                                                    ...   \n",
       "2431516  at://did:plc:feaa5k4utn2gayj2bxsvx3cx/app.bsky...   \n",
       "2431523  at://did:plc:7yeirudvbp5l3lmp4ycgbml5/app.bsky...   \n",
       "2431524  at://did:plc:qdriunexx3nobe5kpltycouy/app.bsky...   \n",
       "2431529  at://did:plc:ycdfsvtnosafdvko26fc7i43/app.bsky...   \n",
       "2431538  at://did:plc:ct5u4vpg5ajhx6wxihtca6qh/app.bsky...   \n",
       "\n",
       "                                                       cid  \\\n",
       "1        bafyreidgvotn7srwum67gsv5rkjbiybtwjwpei5tvnrws...   \n",
       "2        bafyreiawjvozspsyg5yelmmnb3hs4sp7vsjqddpr6t636...   \n",
       "6        bafyreiasf7jxlprpiix6eo4x7ifb7zeaduu2kcftyxpyi...   \n",
       "10       bafyreieyyoeepsexamgybk5dun3sqxwiqftas2ent47np...   \n",
       "11       bafyreiht7xdi2cuc6bwoer4qcf5nwzekyt7kvwq6cv4la...   \n",
       "...                                                    ...   \n",
       "2431516  bafyreifm7bfz6t22liztgjjtnrm3svwiuyno37chgh4ki...   \n",
       "2431523  bafyreigj5r4j2cmgyops6naxbnk6qsdk7woqtjwy75fh4...   \n",
       "2431524  bafyreifncwwa4desh5ju6re2ykvfgchnppxvzlk5spili...   \n",
       "2431529  bafyreigvptivi6zu6njihe7wfuii6rdhj5y3l6u2azihw...   \n",
       "2431538  bafyreiduxg3lwaaibwaxsrsck44rzfpefliil2otfy67z...   \n",
       "\n",
       "                                authorDid                 indexedAt  \\\n",
       "1        did:plc:iomleec6ojlmywkrwqjbr57o  2023-12-27T03:12:43.896Z   \n",
       "2        did:plc:cakburidjcwro44hweyxazjg  2023-12-27T03:12:43.968Z   \n",
       "6        did:plc:kwmi7ftr3g7hbohzauip3mxn  2023-12-27T03:12:44.068Z   \n",
       "10       did:plc:43eonpufv7sg6hglanhbhraw  2023-12-27T03:12:44.287Z   \n",
       "11       did:plc:ipepj5vzwwzvggali4tnccwj  2023-12-27T03:12:44.369Z   \n",
       "...                                   ...                       ...   \n",
       "2431516  did:plc:feaa5k4utn2gayj2bxsvx3cx  2023-12-28T03:41:47.605Z   \n",
       "2431523  did:plc:7yeirudvbp5l3lmp4ycgbml5  2023-12-28T03:41:47.666Z   \n",
       "2431524  did:plc:qdriunexx3nobe5kpltycouy  2023-12-28T03:41:47.686Z   \n",
       "2431529  did:plc:ycdfsvtnosafdvko26fc7i43  2023-12-28T03:41:47.745Z   \n",
       "2431538  did:plc:ct5u4vpg5ajhx6wxihtca6qh  2023-12-28T03:41:48.066Z   \n",
       "\n",
       "                        createdAt  \\\n",
       "1        2023-12-27T03:12:42.248Z   \n",
       "2        2023-12-27T03:12:43.705Z   \n",
       "6        2023-12-27T03:12:45.463Z   \n",
       "10       2023-12-27T03:12:44.003Z   \n",
       "11       2023-12-27T03:12:43.406Z   \n",
       "...                           ...   \n",
       "2431516  2023-12-28T03:41:46.687Z   \n",
       "2431523  2023-12-28T03:41:46.741Z   \n",
       "2431524  2023-12-28T03:41:46.886Z   \n",
       "2431529  2023-12-28T03:41:46.679Z   \n",
       "2431538  2023-12-28T03:41:47.744Z   \n",
       "\n",
       "                                                subjectUri  \\\n",
       "1        at://did:plc:btaxnpi4resvm2uz4n7tcp3f/app.bsky...   \n",
       "2        at://did:plc:ky3xc27d4ct6ntwxsu7tjpx7/app.bsky...   \n",
       "6        at://did:plc:wxj3cnbus6js5f7hjwowoxoq/app.bsky...   \n",
       "10       at://did:plc:mgsxkvihm65lecdzbavku3tk/app.bsky...   \n",
       "11       at://did:plc:e4r2dxzbadqabu63wne4tosx/app.bsky...   \n",
       "...                                                    ...   \n",
       "2431516  at://did:plc:q4b6fmgkkrybhf5ejbrgcmgn/app.bsky...   \n",
       "2431523  at://did:plc:fllmcdrrhebd55j4mp43igmb/app.bsky...   \n",
       "2431524  at://did:plc:i3l64jceufl7zcbk3r2sfiyc/app.bsky...   \n",
       "2431529  at://did:plc:gxxkzpo2cw6q2ynee64rxppw/app.bsky...   \n",
       "2431538  at://did:plc:4msurte3uoa37puu2ma673t6/app.bsky...   \n",
       "\n",
       "                                                subjectCid  \\\n",
       "1        bafyreifsu35qmmr66fooemrvkke6rdd3qq5mdjvtsqs5y...   \n",
       "2        bafyreib7r6526nciyilv3ky345zbmbh4w3tsarc74z72c...   \n",
       "6        bafyreifcftx7xktszbhmylitz34hf66ivmboymshgtchl...   \n",
       "10       bafyreibyyeobzn34r4edmeiaarancnpjbuesdiuqxkxfy...   \n",
       "11       bafyreibk6afarwpw7rdzifkxbi5kgy36tolpe45lxvjzq...   \n",
       "...                                                    ...   \n",
       "2431516  bafyreibl7b6qni2jxir2v4uf5wfcurx3bbsgprvodwb2s...   \n",
       "2431523  bafyreiatd54b5pcpu2f2cysdavzcv2iqtdput7orhgbnt...   \n",
       "2431524  bafyreihyyllfudoppmwlzvir5uvomf4cgxogygba7dt2l...   \n",
       "2431529  bafyreicoczktoxoxozi3wurb3shbikgd5tbrukl4goavl...   \n",
       "2431538  bafyreifmtmvujeeccj4t7trmzof22lhxpkiqk5s5yamty...   \n",
       "\n",
       "                               subjectDid  \n",
       "1        did:plc:btaxnpi4resvm2uz4n7tcp3f  \n",
       "2        did:plc:ky3xc27d4ct6ntwxsu7tjpx7  \n",
       "6        did:plc:wxj3cnbus6js5f7hjwowoxoq  \n",
       "10       did:plc:mgsxkvihm65lecdzbavku3tk  \n",
       "11       did:plc:e4r2dxzbadqabu63wne4tosx  \n",
       "...                                   ...  \n",
       "2431516  did:plc:q4b6fmgkkrybhf5ejbrgcmgn  \n",
       "2431523  did:plc:fllmcdrrhebd55j4mp43igmb  \n",
       "2431524  did:plc:i3l64jceufl7zcbk3r2sfiyc  \n",
       "2431529  did:plc:gxxkzpo2cw6q2ynee64rxppw  \n",
       "2431538  did:plc:4msurte3uoa37puu2ma673t6  \n",
       "\n",
       "[546374 rows x 8 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_reply_likes = likes.loc[\n",
    "    np.logical_and(\n",
    "        ~likes['subjectUri'].isin(top_threads['uri']),\n",
    "        ~likes['subjectDid'].isin(top_accounts['account'])\n",
    "    )]\n",
    "non_top_account_likes = likes.loc[\n",
    "    ~likes['subjectDid'].isin(top_accounts['account'])\n",
    "]\n",
    "\n",
    "non_top_reply_likes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d7ca01a",
   "metadata": {},
   "source": [
    "Proportion of posts from top posters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "5069cd71",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4083754239690857"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "top_posts.shape[0] / posts.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44fa1058",
   "metadata": {},
   "source": [
    "Proportion of non-top account likes that are not in threads with top accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "79b26b9b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8589246581587577"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_reply_likes.shape[0] / non_top_account_likes.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "455e39bd",
   "metadata": {},
   "source": [
    "Proportion of likes to non-top accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "602921d8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.26160886941888"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_account_likes.shape[0] / likes.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "19ae2594",
   "metadata": {},
   "source": [
    "Proportion of likes to non-top accounts that are not in threads with top accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "a3572f44",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.22470230873691058"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_reply_likes.shape[0] / likes.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f88361b0",
   "metadata": {},
   "source": [
    "Number of top accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "7b0094ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "13522"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "top_accounts.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aae6aa9d",
   "metadata": {},
   "source": [
    "Quantiles of likes received by non-top posts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "3a0c7e8b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00     0.0\n",
       "0.25     0.0\n",
       "0.50     0.0\n",
       "0.75     1.0\n",
       "0.90     3.0\n",
       "0.95     5.0\n",
       "0.99    11.0\n",
       "Name: likes, dtype: float64"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_posts['likes'].quantile(quants)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "f6471c77",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8008732539358548"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(non_top_posts['likes'] <= 1) / non_top_posts.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "1c9f73b5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "32.0"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_top_posts['likes'].max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "1e9d4b13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3928.0"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "top_posts['likes'].max()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9cc66fb2",
   "metadata": {},
   "source": [
    "How many accounts who posted received any likes?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "17f85222",
   "metadata": {},
   "outputs": [],
   "source": [
    "posting_account_likes = posts.groupby('authorDid'\n",
    "    ).agg(\n",
    "      likes=('likes', 'sum'),\n",
    "      posts=('uri', 'count')\n",
    "    ).reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "58fb21bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.31761174116077384"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(posting_account_likes['likes'] == 0) / posting_account_likes.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "ba4a400e",
   "metadata": {},
   "outputs": [],
   "source": [
    "posting_account_likes['likes_per_post'] = \\\n",
    "    posting_account_likes['likes'] / posting_account_likes['posts']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "d67e1705",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00     0.0\n",
       "0.25     0.0\n",
       "0.50     1.0\n",
       "0.75     2.0\n",
       "0.90     5.0\n",
       "0.95     8.3\n",
       "0.99    28.0\n",
       "Name: likes_per_post, dtype: float64"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lpp_quantiles = posting_account_likes['likes_per_post'].quantile(quants)\n",
    "lpp_quantiles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "c1daecca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00     0.000000\n",
       "0.25     0.000000\n",
       "0.50     0.833333\n",
       "0.75     1.625000\n",
       "0.90     3.250000\n",
       "0.95     5.000000\n",
       "0.99    12.000000\n",
       "Name: likes_per_post, dtype: float64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nontop_lpp_quantiles = posting_account_likes[\n",
    "    ~posting_account_likes['authorDid'].isin(top_accounts['account'])\n",
    "]['likes_per_post'].quantile(quants)\n",
    "nontop_lpp_quantiles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "8f14183c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "lpp_sorted = posting_account_likes.sort_values('likes_per_post').reset_index()\n",
    "plt.plot(lpp_sorted['likes_per_post'])\n",
    "plt.title('Mean likes per post for accounts who posted during the sample')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "729e665e",
   "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>account</th>\n",
       "      <th>likes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>did:plc:btaxnpi4resvm2uz4n7tcp3f</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>did:plc:wxj3cnbus6js5f7hjwowoxoq</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>did:plc:acmcckkebktixw6lzhx76fsq</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>did:plc:mgsxkvihm65lecdzbavku3tk</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>did:plc:e4r2dxzbadqabu63wne4tosx</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247965</th>\n",
       "      <td>did:plc:zeau3uhk2sm4bdpeg7cl2hk7</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247966</th>\n",
       "      <td>did:plc:fl4mmwjixqnonmwfxti6tbb7</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247967</th>\n",
       "      <td>did:plc:ylz7ikmlz7kn33s6xfn2hfbr</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247968</th>\n",
       "      <td>did:plc:6dqstbx266mlgjvdmr4u4vbw</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247969</th>\n",
       "      <td>did:plc:qrpae44n3nmwjvm4le6foryx</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>134907 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 account  likes\n",
       "1       did:plc:btaxnpi4resvm2uz4n7tcp3f    2.0\n",
       "6       did:plc:wxj3cnbus6js5f7hjwowoxoq    2.0\n",
       "9       did:plc:acmcckkebktixw6lzhx76fsq   61.0\n",
       "10      did:plc:mgsxkvihm65lecdzbavku3tk    7.0\n",
       "11      did:plc:e4r2dxzbadqabu63wne4tosx    3.0\n",
       "...                                  ...    ...\n",
       "247965  did:plc:zeau3uhk2sm4bdpeg7cl2hk7    0.0\n",
       "247966  did:plc:fl4mmwjixqnonmwfxti6tbb7    0.0\n",
       "247967  did:plc:ylz7ikmlz7kn33s6xfn2hfbr    0.0\n",
       "247968  did:plc:6dqstbx266mlgjvdmr4u4vbw    0.0\n",
       "247969  did:plc:qrpae44n3nmwjvm4le6foryx    0.0\n",
       "\n",
       "[134907 rows x 2 columns]"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_posting_accounts = accounts[~accounts['account'].isin(posting_accounts)]\n",
    "non_posting_accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "a7840d6e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4999944406764585"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_posting_accounts.shape[0] / accounts.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "dab2dfa5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "269817"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accounts.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "03ea581a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2707272417294877"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(non_posting_accounts['likes'] > 0) / non_posting_accounts.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "ab29ccc1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.06262517756192973"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "non_posting_accounts['likes'].sum() / accounts['likes'].sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "d495fad6",
   "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>account</th>\n",
       "      <th>likes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>did:plc:lhfbzpkdw2jk5i6im5pd2mi5</td>\n",
       "      <td>160.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>did:plc:z3ds6onyuoyfnx42qgoddhbp</td>\n",
       "      <td>313.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>did:plc:hqzxqh634sd546rfoazslb5h</td>\n",
       "      <td>103.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>did:plc:ats4shmeia7i7ildqm3denmd</td>\n",
       "      <td>405.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>did:plc:7o55wjsyg2ylsmlr5to6gb67</td>\n",
       "      <td>313.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130508</th>\n",
       "      <td>did:plc:d5torywdns2h4kghsqmil7k6</td>\n",
       "      <td>46.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130569</th>\n",
       "      <td>did:plc:2tdfuxjpemewkkyhi2db7lck</td>\n",
       "      <td>46.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130642</th>\n",
       "      <td>did:plc:en7khbuwadt72huhdyrvhf7s</td>\n",
       "      <td>33.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131261</th>\n",
       "      <td>did:plc:oafrik4tx7nkmqysa4kpnuv5</td>\n",
       "      <td>243.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132789</th>\n",
       "      <td>did:plc:osxrt2mj6274mw4de6duncpu</td>\n",
       "      <td>39.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>13522 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 account  likes\n",
       "0       did:plc:lhfbzpkdw2jk5i6im5pd2mi5  160.0\n",
       "3       did:plc:z3ds6onyuoyfnx42qgoddhbp  313.0\n",
       "4       did:plc:hqzxqh634sd546rfoazslb5h  103.0\n",
       "5       did:plc:ats4shmeia7i7ildqm3denmd  405.0\n",
       "7       did:plc:7o55wjsyg2ylsmlr5to6gb67  313.0\n",
       "...                                  ...    ...\n",
       "130508  did:plc:d5torywdns2h4kghsqmil7k6   46.0\n",
       "130569  did:plc:2tdfuxjpemewkkyhi2db7lck   46.0\n",
       "130642  did:plc:en7khbuwadt72huhdyrvhf7s   33.0\n",
       "131261  did:plc:oafrik4tx7nkmqysa4kpnuv5  243.0\n",
       "132789  did:plc:osxrt2mj6274mw4de6duncpu   39.0\n",
       "\n",
       "[13522 rows x 2 columns]"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "top_accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "77340e08",
   "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>account</th>\n",
       "      <th>likes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>did:plc:nvog7rczakwzh5ckxnjnwqdd</td>\n",
       "      <td>2009.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>did:plc:z3eu4ec7csnznxrrdrabudgj</td>\n",
       "      <td>331.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>did:plc:m2hze6zxa744iberzknpkc3i</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>did:plc:ykzmsemoxmlzmrci2p77eqkm</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>did:plc:afrooick4a2hy2m2eme5ognc</td>\n",
       "      <td>103.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45665</th>\n",
       "      <td>did:plc:efkxngznfeo2onvrjhskmmou</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45666</th>\n",
       "      <td>did:plc:pv4x356soulpp7spindi57gz</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45667</th>\n",
       "      <td>did:plc:w5reveglbupc6sz4txst2v7b</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45668</th>\n",
       "      <td>did:plc:7o6uylwbtcpwk5c5pqa67fsl</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45669</th>\n",
       "      <td>did:plc:uppr7hyd3a2zzss54drq2s5j</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>45670 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                account   likes\n",
       "0      did:plc:nvog7rczakwzh5ckxnjnwqdd  2009.0\n",
       "1      did:plc:z3eu4ec7csnznxrrdrabudgj   331.0\n",
       "2      did:plc:m2hze6zxa744iberzknpkc3i    12.0\n",
       "3      did:plc:ykzmsemoxmlzmrci2p77eqkm    41.0\n",
       "4      did:plc:afrooick4a2hy2m2eme5ognc   103.0\n",
       "...                                 ...     ...\n",
       "45665  did:plc:efkxngznfeo2onvrjhskmmou     0.0\n",
       "45666  did:plc:pv4x356soulpp7spindi57gz     0.0\n",
       "45667  did:plc:w5reveglbupc6sz4txst2v7b     0.0\n",
       "45668  did:plc:7o6uylwbtcpwk5c5pqa67fsl     0.0\n",
       "45669  did:plc:uppr7hyd3a2zzss54drq2s5j     0.0\n",
       "\n",
       "[45670 rows x 2 columns]"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accounts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "75bbb3eb",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}