rq2-survival.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pymongo\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from dateutil import parser\n",
    "from collections import Counter\n",
    "\n",
    "from tqdm import tqdm\n",
    "from sksurv.nonparametric import kaplan_meier_estimator\n",
    "\n",
    "from scripts import MONGO_URL, END_DATE\n",
    "from scripts.analysis import data, plot\n",
    "\n",
    "W, H = 5.5, 2.5\n",
    "plot.init_matplotlib()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "repos = data.get_fake_star_repos()\n",
    "stars = data.get_fake_stars_by_month()\n",
    "repos_with_campaign = data.get_repos_with_campaign()\n",
    "repos = repos[repos.repo_name.isin(repos_with_campaign)]\n",
    "deleted = set(repos[repos.repo_id.isna()].repo_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "repos[\"deleted\"] = repos.repo_id.isna()\n",
    "repos[\"n_stars_fake\"] = repos.n_stars_low_activity + repos.n_stars_clustered\n",
    "repo_to_len_campaign = Counter(stars[stars.anomaly].repo)\n",
    "repos[\"length_campaign\"] = repos.repo_name.map(lambda x: repo_to_len_campaign[x])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 18617/18617 [01:25<00:00, 218.96it/s]\n",
      "10000it [00:06, 1571.79it/s]\n"
     ]
    }
   ],
   "source": [
    "survival_repo = []\n",
    "with pymongo.MongoClient(MONGO_URL) as client:\n",
    "    for repo in tqdm(repos_with_campaign):\n",
    "        events = list(\n",
    "            client.fake_stars.fake_repo_events.find({\"repo\": repo}).sort(\n",
    "                \"created_at\", pymongo.ASCENDING\n",
    "            )\n",
    "        )\n",
    "        if len(events) != 0:\n",
    "            start_date = parser.parse(events[0][\"created_at\"])\n",
    "            end_date = parser.parse(events[-1][\"created_at\"])\n",
    "            survival_repo.append(\n",
    "                {\n",
    "                    \"repo\": repo,\n",
    "                    \"category\": \"deleted-re\" if repo in deleted else \"fake-re\",\n",
    "                    \"fake\": True,\n",
    "                    \"start_date\": start_date,\n",
    "                    \"end_date\": end_date,\n",
    "                    \"active_days\": (end_date - start_date).days + 1,\n",
    "                }\n",
    "            )\n",
    "\n",
    "    for group in tqdm(\n",
    "        client.fake_stars.sample_repo_events.aggregate(\n",
    "            [{\"$group\": {\"_id\": \"$repo\", \"created_at\": {\"$push\": \"$created_at\"}}}]\n",
    "        )\n",
    "    ):\n",
    "        repo = group[\"_id\"]\n",
    "        events = sorted(group[\"created_at\"])\n",
    "        start_time = parser.parse(events[0])\n",
    "        end_time = parser.parse(events[-1])\n",
    "        survival_repo.append(\n",
    "            {\n",
    "                \"repo\": repo,\n",
    "                \"category\": \"sample-re\",\n",
    "                \"fake\": False,\n",
    "                \"start_time\": start_time,\n",
    "                \"end_time\": end_time,\n",
    "                \"active_days\": (end_time - start_time).days + 1,\n",
    "            }\n",
    "        )\n",
    "survival_repo = pd.DataFrame(survival_repo)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "10000it [00:01, 6722.20it/s]\n",
      "10087it [00:01, 7072.99it/s]\n"
     ]
    }
   ],
   "source": [
    "survival_user = []\n",
    "fake_user_info = pd.read_csv(f\"data/{END_DATE}/fake_user_info.csv\")\n",
    "deleted_users = set(fake_user_info[fake_user_info.error.notnull()].actor)\n",
    "clustered_users = data.get_unique_actors_in_campaign(\"clustered\")\n",
    "low_activity_users = data.get_unique_actors_in_campaign(\"low_activity\")\n",
    "pipeline = [\n",
    "    {\n",
    "        \"$group\": {\n",
    "            \"_id\": \"$actor\",\n",
    "            \"start_time\": {\"$min\": \"$created_at\"},\n",
    "            \"end_time\": {\"$max\": \"$created_at\"},\n",
    "        }\n",
    "    }\n",
    "]\n",
    "with pymongo.MongoClient(MONGO_URL) as client:\n",
    "    for group in tqdm(client.fake_stars.sample_actor_events.aggregate(pipeline)):\n",
    "        actor = group[\"_id\"]\n",
    "        start_time = parser.parse(group[\"start_time\"])\n",
    "        end_time = parser.parse(group[\"end_time\"])\n",
    "        survival_user.append(\n",
    "            {\n",
    "                \"actor\": actor,\n",
    "                \"category\": \"sample-ac\",\n",
    "                \"fake\": False,\n",
    "                \"clustered\": False,\n",
    "                \"start_time\": start_time,\n",
    "                \"end_time\": end_time,\n",
    "                \"active_days\": (end_time - start_time).days + 1,\n",
    "            }\n",
    "        )\n",
    "    for group in tqdm(client.fake_stars.fake_actor_events.aggregate(pipeline)):\n",
    "        actor = group[\"_id\"]\n",
    "        start_time = parser.parse(group[\"start_time\"])\n",
    "        end_time = parser.parse(group[\"end_time\"])\n",
    "        if actor in low_activity_users or actor in clustered_users:\n",
    "            survival_user.append(\n",
    "                {\n",
    "                    \"actor\": actor,\n",
    "                    \"category\": \"deleted-ac\" if actor in deleted_users else \"fake-ac\",\n",
    "                    \"fake\": True,\n",
    "                    \"clustered\": actor in clustered_users,\n",
    "                    \"start_time\": start_time,\n",
    "                    \"end_time\": end_time,\n",
    "                    \"active_days\": (end_time - start_time).days + 1,\n",
    "                }\n",
    "            )\n",
    "survival_user = pd.DataFrame(survival_user)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({False: 10638, True: 1151})"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(survival_user.clustered)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "18617 15620\n",
      "1789 1051\n"
     ]
    }
   ],
   "source": [
    "print(\n",
    "    len(survival_repo[survival_repo.fake]),\n",
    "    len(survival_repo[survival_repo.fake & (survival_repo.active_days <= 10)]),\n",
    ")\n",
    "print(\n",
    "    len(survival_user[survival_user.fake]),\n",
    "    len(survival_user[survival_user.fake & (survival_user.active_days <= 10)]),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 275x150 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 275x150 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(W / 2, H - 1))\n",
    "sns.ecdfplot(\n",
    "    data=survival_repo,\n",
    "    x=\"active_days\",\n",
    "    hue=\"fake\",\n",
    "    complementary=True,\n",
    "    ax=ax,\n",
    "    palette=[\"C0\", \"C2\"],\n",
    ")\n",
    "ax.set_xscale(\"log\")\n",
    "ax.set_xlim(0.9)\n",
    "ax.set_xlabel(\"Activity Duration (Days)\")\n",
    "ax.set_ylabel(\"\")\n",
    "ax.legend([\"w. Fake Star Campaigns\", \"Sample Repositories\"], loc=\"upper right\")\n",
    "plot.remove_spines(ax)\n",
    "fig.savefig(\"plots/survival_repo.pdf\", bbox_inches=\"tight\")\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(W / 2, H - 1))\n",
    "sns.ecdfplot(\n",
    "    data=survival_user[survival_user.clustered | ~survival_user.fake],\n",
    "    x=\"active_days\",\n",
    "    hue=\"fake\",\n",
    "    complementary=True,\n",
    "    ax=ax,\n",
    "    palette=[\"C0\", \"C2\"],\n",
    ")\n",
    "ax.legend([\"w. Lockstep Signature\", \"Sample Stargazers\"], loc=\"upper right\")\n",
    "ax.set_xscale(\"log\")\n",
    "ax.set_xlim(0.9)\n",
    "ax.set_xlabel(\"Activity Duration (Days)\")\n",
    "ax.set_ylabel(\"\")\n",
    "plot.remove_spines(ax)\n",
    "fig.savefig(\"plots/survival_user.pdf\", bbox_inches=\"tight\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Could not interpret value `active_days` for `x`. An entry with this name does not appear in `data`.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[9], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m fig, ax \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39msubplots(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m1\u001b[39m, figsize\u001b[38;5;241m=\u001b[39m(W, H))\n\u001b[0;32m----> 2\u001b[0m \u001b[43msns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mviolinplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepos\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mactive_days\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mhue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdeleted\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43max\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43max\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      3\u001b[0m ax\u001b[38;5;241m.\u001b[39mset_xlim(\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m      4\u001b[0m plot\u001b[38;5;241m.\u001b[39mremove_spines(ax)\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/categorical.py:1725\u001b[0m, in \u001b[0;36mviolinplot\u001b[0;34m(data, x, y, hue, order, hue_order, orient, color, palette, saturation, fill, inner, split, width, dodge, gap, linewidth, linecolor, cut, gridsize, bw_method, bw_adjust, density_norm, common_norm, hue_norm, formatter, log_scale, native_scale, legend, scale, scale_hue, bw, inner_kws, ax, **kwargs)\u001b[0m\n\u001b[1;32m   1714\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mviolinplot\u001b[39m(\n\u001b[1;32m   1715\u001b[0m     data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m, x\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, hue\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, hue_order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1716\u001b[0m     orient\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, color\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, palette\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, saturation\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m.75\u001b[39m, fill\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1722\u001b[0m     inner_kws\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, ax\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m   1723\u001b[0m ):\n\u001b[0;32m-> 1725\u001b[0m     p \u001b[38;5;241m=\u001b[39m \u001b[43m_CategoricalPlotter\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1726\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1727\u001b[0m \u001b[43m        \u001b[49m\u001b[43mvariables\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mdict\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mhue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhue\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1728\u001b[0m \u001b[43m        \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1729\u001b[0m \u001b[43m        \u001b[49m\u001b[43morient\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morient\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1730\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1731\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlegend\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlegend\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1732\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1734\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ax \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m   1735\u001b[0m         ax \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39mgca()\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/categorical.py:67\u001b[0m, in \u001b[0;36m_CategoricalPlotter.__init__\u001b[0;34m(self, data, variables, order, orient, require_numeric, color, legend)\u001b[0m\n\u001b[1;32m     56\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\n\u001b[1;32m     57\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m     58\u001b[0m     data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     64\u001b[0m     legend\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     65\u001b[0m ):\n\u001b[0;32m---> 67\u001b[0m     \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvariables\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvariables\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     69\u001b[0m     \u001b[38;5;66;03m# This method takes care of some bookkeeping that is necessary because the\u001b[39;00m\n\u001b[1;32m     70\u001b[0m     \u001b[38;5;66;03m# original categorical plots (prior to the 2021 refactor) had some rules that\u001b[39;00m\n\u001b[1;32m     71\u001b[0m     \u001b[38;5;66;03m# don't fit exactly into VectorPlotter logic. It may be wise to have a second\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     76\u001b[0m     \u001b[38;5;66;03m# default VectorPlotter rules. If we do decide to make orient part of the\u001b[39;00m\n\u001b[1;32m     77\u001b[0m     \u001b[38;5;66;03m# _base variable assignment, we'll want to figure out how to express that.\u001b[39;00m\n\u001b[1;32m     78\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_format \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwide\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m orient \u001b[38;5;129;01min\u001b[39;00m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mh\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/_base.py:634\u001b[0m, in \u001b[0;36mVectorPlotter.__init__\u001b[0;34m(self, data, variables)\u001b[0m\n\u001b[1;32m    629\u001b[0m \u001b[38;5;66;03m# var_ordered is relevant only for categorical axis variables, and may\u001b[39;00m\n\u001b[1;32m    630\u001b[0m \u001b[38;5;66;03m# be better handled by an internal axis information object that tracks\u001b[39;00m\n\u001b[1;32m    631\u001b[0m \u001b[38;5;66;03m# such information and is set up by the scale_* methods. The analogous\u001b[39;00m\n\u001b[1;32m    632\u001b[0m \u001b[38;5;66;03m# information for numeric axes would be information about log scales.\u001b[39;00m\n\u001b[1;32m    633\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_var_ordered \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mx\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28;01mFalse\u001b[39;00m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28;01mFalse\u001b[39;00m}  \u001b[38;5;66;03m# alt., used DefaultDict\u001b[39;00m\n\u001b[0;32m--> 634\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43massign_variables\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvariables\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    636\u001b[0m \u001b[38;5;66;03m# TODO Lots of tests assume that these are called to initialize the\u001b[39;00m\n\u001b[1;32m    637\u001b[0m \u001b[38;5;66;03m# mappings to default values on class initialization. I'd prefer to\u001b[39;00m\n\u001b[1;32m    638\u001b[0m \u001b[38;5;66;03m# move away from that and only have a mapping when explicitly called.\u001b[39;00m\n\u001b[1;32m    639\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m var \u001b[38;5;129;01min\u001b[39;00m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhue\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstyle\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/_base.py:679\u001b[0m, in \u001b[0;36mVectorPlotter.assign_variables\u001b[0;34m(self, data, variables)\u001b[0m\n\u001b[1;32m    674\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    675\u001b[0m     \u001b[38;5;66;03m# When dealing with long-form input, use the newer PlotData\u001b[39;00m\n\u001b[1;32m    676\u001b[0m     \u001b[38;5;66;03m# object (internal but introduced for the objects interface)\u001b[39;00m\n\u001b[1;32m    677\u001b[0m     \u001b[38;5;66;03m# to centralize / standardize data consumption logic.\u001b[39;00m\n\u001b[1;32m    678\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_format \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlong\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 679\u001b[0m     plot_data \u001b[38;5;241m=\u001b[39m \u001b[43mPlotData\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvariables\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    680\u001b[0m     frame \u001b[38;5;241m=\u001b[39m plot_data\u001b[38;5;241m.\u001b[39mframe\n\u001b[1;32m    681\u001b[0m     names \u001b[38;5;241m=\u001b[39m plot_data\u001b[38;5;241m.\u001b[39mnames\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/_core/data.py:58\u001b[0m, in \u001b[0;36mPlotData.__init__\u001b[0;34m(self, data, variables)\u001b[0m\n\u001b[1;32m     51\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\n\u001b[1;32m     52\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m     53\u001b[0m     data: DataSource,\n\u001b[1;32m     54\u001b[0m     variables: \u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, VariableSpec],\n\u001b[1;32m     55\u001b[0m ):\n\u001b[1;32m     57\u001b[0m     data \u001b[38;5;241m=\u001b[39m handle_data_source(data)\n\u001b[0;32m---> 58\u001b[0m     frame, names, ids \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_assign_variables\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvariables\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     60\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mframe \u001b[38;5;241m=\u001b[39m frame\n\u001b[1;32m     61\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnames \u001b[38;5;241m=\u001b[39m names\n",
      "File \u001b[0;32m~/anaconda3/envs/fake-stars/lib/python3.12/site-packages/seaborn/_core/data.py:232\u001b[0m, in \u001b[0;36mPlotData._assign_variables\u001b[0;34m(self, data, variables)\u001b[0m\n\u001b[1;32m    230\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    231\u001b[0m         err \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAn entry with this name does not appear in `data`.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 232\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(err)\n\u001b[1;32m    234\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    235\u001b[0m \n\u001b[1;32m    236\u001b[0m     \u001b[38;5;66;03m# Otherwise, assume the value somehow represents data\u001b[39;00m\n\u001b[1;32m    237\u001b[0m \n\u001b[1;32m    238\u001b[0m     \u001b[38;5;66;03m# Ignore empty data structures\u001b[39;00m\n\u001b[1;32m    239\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(val, Sized) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(val) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
      "\u001b[0;31mValueError\u001b[0m: Could not interpret value `active_days` for `x`. An entry with this name does not appear in `data`."
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 550x250 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(1, 1, figsize=(W, H))\n",
    "sns.violinplot(data=repos, x=\"active_days\", hue=\"deleted\", ax=ax)\n",
    "ax.set_xlim(0)\n",
    "plot.remove_spines(ax)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'time $t$')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "time, survival_prob, conf_int = kaplan_meier_estimator(\n",
    "    repos[repos.active_days.notna()][\"deleted\"],\n",
    "    repos[repos.active_days.notna()][\"active_days\"],\n",
    "    conf_type=\"log-log\",\n",
    ")\n",
    "plt.step(time, survival_prob, where=\"post\")\n",
    "plt.fill_between(time, conf_int[0], conf_int[1], alpha=0.25, step=\"post\")\n",
    "plt.ylabel(r\"est. probability of survival $\\hat{S}(t)$\")\n",
    "plt.xlabel(\"time $t$\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "fake-stars",
   "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": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}