{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as pgo\n",
    "import scipy as sp\n",
    "from pymongo import MongoClient\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "client = MongoClient(\"mongodb://stats_user:%40z%5EVFhN7q%25vzit@192.168.86.120:27017/?authSource=statistics\")\n",
    "db = client.statistics\n",
    "\n",
    "formatted_date = lambda date: {\n",
    "    \"unix\": {\"$toLong\": date},\n",
    "    \"iso\": {\"$toString\": date},\n",
    "}\n",
    "\n",
    "pipeline = [\n",
    "    {\"$sort\": {\"timestamp\": 1}},\n",
    "    {\n",
    "        \"$group\": {\n",
    "            \"_id\": \"$tags.session\",\n",
    "            \"host\": {\"$first\": \"$tags.host\"},\n",
    "            \"firstTimestamp\": {\"$first\": \"$timestamp\"},\n",
    "            \"lastTimestamp\": {\"$last\": \"$timestamp\"},\n",
    "            \"firstTimestampWithPeers\": {\n",
    "                \"$min\": {\n",
    "                    \"$cond\": {\n",
    "                        \"if\": {\"$gt\": [{\"$size\": {\"$ifNull\": [\"$peers\", []]}}, 0]},\n",
    "                        \"then\": \"$timestamp\",\n",
    "                        \"else\": None,\n",
    "                    }\n",
    "                }\n",
    "            },\n",
    "            \"maxNumberOfPeers\": {\n",
    "                \"$max\": {\"$size\": {\"$ifNull\": [\"$peers\", []]}},\n",
    "            },\n",
    "            \"minNumberOfPeers\": {\n",
    "                \"$min\": {\"$size\": {\"$ifNull\": [\"$peers\", []]}},\n",
    "            },\n",
    "        }\n",
    "    },\n",
    "    {\n",
    "        \"$lookup\": {\n",
    "            \"from\": \"peertube_ts\",\n",
    "            \"let\": {\"currentSession\": \"$_id\", \"ftp\": \"$firstTimestampWithPeers\", \"fst\": \"$firstTimestamp\"},\n",
    "            \"pipeline\": [\n",
    "                {\n",
    "                    \"$match\": {\n",
    "                        \"$expr\": {\n",
    "                            \"$and\": [\n",
    "                                {\"$ne\": [\"$tags.session\", \"$$currentSession\"]},\n",
    "                                {\"$lt\": [\"$timestamp\", \"$$ftp\"]},\n",
    "                                {\"$gte\": [\"$timestamp\", \"$$fst\"]},\n",
    "                                {\"$gt\": [{\"$size\": {\"$ifNull\": [\"$peers\", []]}}, 0]},\n",
    "                            ]\n",
    "                        }\n",
    "                    }\n",
    "                }\n",
    "            ],\n",
    "            \"as\": \"concurrentSessions\",\n",
    "        }\n",
    "    },\n",
    "    {\n",
    "        \"$addFields\": {\n",
    "            \"concurrentSessions\": {\"$gt\": [{\"$size\": \"$concurrentSessions\"}, 0]}\n",
    "        }\n",
    "    },\n",
    "    {\n",
    "        \"$group\": {\n",
    "            \"_id\": \"$host\",\n",
    "            \"sessions\": {\n",
    "                \"$push\": {\n",
    "                    \"id\": \"$_id\",\n",
    "                    \"startTime\": formatted_date(\"$firstTimestamp\"),\n",
    "                    \"endTime\": formatted_date(\"$lastTimestamp\"),\n",
    "                    \"duration\": {\n",
    "                        \"$divide\": [\n",
    "                            {\"$subtract\": [\"$lastTimestamp\", \"$firstTimestamp\"]},\n",
    "                            1000,\n",
    "                        ]\n",
    "                    },\n",
    "                    \"firstPeerConnection\": {\n",
    "                        \"$cond\": {\n",
    "                            \"if\": {\"$eq\": [\"$firstTimestampWithPeers\", None]},\n",
    "                            \"then\": None,\n",
    "                            \"else\": {\n",
    "                                \"time\": {\n",
    "                                    \"date\": formatted_date(\"$firstTimestampWithPeers\"),\n",
    "                                    \"elapsedFromStart\": {\n",
    "                                        \"$divide\": [\n",
    "                                            {\"$subtract\": [\"$firstTimestampWithPeers\", \"$firstTimestamp\"]},\n",
    "                                            1000,\n",
    "                                        ]\n",
    "                                    }\n",
    "                                },\n",
    "                                \"concurrentSessions\": \"$concurrentSessions\",\n",
    "                            }\n",
    "                        }\n",
    "                    },\n",
    "                    \"maxPeers\": {\"$max\": \"$maxNumberOfPeers\"},\n",
    "                    \"minPeers\": {\"$min\": \"$minNumberOfPeers\"},\n",
    "                }\n",
    "            }\n",
    "        }\n",
    "    },\n",
    "    {\n",
    "        \"$set\": {\n",
    "            \"sessions\": {\n",
    "                \"$sortArray\": {\n",
    "                    \"input\": \"$sessions\",\n",
    "                    \"sortBy\": {\"id\": 1},\n",
    "                }\n",
    "            }\n",
    "        }\n",
    "    },\n",
    "    {\n",
    "        \"$project\": {\n",
    "            \"_id\": 0,\n",
    "            \"host\": \"$_id\",\n",
    "            \"sessions\": \"$sessions\",\n",
    "        }\n",
    "    },\n",
    "    {\"$sort\": {\"host\": 1}},\n",
    "]\n",
    "\n",
    "result = db.peertube_ts.aggregate(pipeline)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Extract data from the result cursor\n",
    "data = []\n",
    "for host in result:\n",
    "    for session in host['sessions']:\n",
    "        if session['firstPeerConnection'] and session['firstPeerConnection']['time']:\n",
    "            elapsed = session['firstPeerConnection']['time']['elapsedFromStart']\n",
    "            concurrent_sessions = session['firstPeerConnection']['concurrentSessions']\n",
    "            data.append((elapsed, concurrent_sessions))\n",
    "\n",
    "# Convert to a DataFrame for easier plotting\n",
    "df = pd.DataFrame(data, columns=['Elapsed', 'ConcurrentSessions'])\n",
    "\n",
    "# Convert boolean column to integers\n",
    "df['ConcurrentSessions'] = df['ConcurrentSessions'].astype(int)\n",
    "\n",
    "# Print some statistics\n",
    "print(\"Mean time until first peer connection: {:.2f}s\".format(df['Elapsed'].mean()))\n",
    "print(\"Median time until first peer connection: {:.2f}s\".format(df['Elapsed'].median()))\n",
    "print(\"Number of sessions with concurrent sessions: {}\".format(df['ConcurrentSessions'].sum()))\n",
    "print(\"Number of sessions without concurrent sessions: {}\".format(df['ConcurrentSessions'].count() - df['ConcurrentSessions'].sum()))\n",
    "\n",
    "# Revert concurrent sessions column to boolean for plotting\n",
    "df['ConcurrentSessions'] = df['ConcurrentSessions'].astype(bool)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot the histogram of the elapsed time until first peer connection\n",
    "# Color the bars based on the number of concurrent sessions and add a legend\n",
    "fig = px.histogram(df, x='Elapsed', color='ConcurrentSessions', barmode='overlay', nbins=100)\n",
    "fig.update_layout(\n",
    "    title='Elapsed time until first peer connection',\n",
    "    xaxis_title='Elapsed time (s)',\n",
    "    yaxis_title='Count',\n",
    "    legend_title='Had concurrent sessions',\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "# Plot the line chart of the elapsed time until first peer connection\n",
    "fig = px.line(df, x=df.index, y='Elapsed', markers=True)\n",
    "fig.update_layout(\n",
    "    title='Elapsed time until first peer connection',\n",
    "    xaxis_title='Session index',\n",
    "    yaxis_title='Elapsed time (s)',\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "# Plot the cumulative distribution of the elapsed time until first peer connection\n",
    "# Color the lines based on the number of concurrent sessions and add a legend\n",
    "fig = px.ecdf(df, x='Elapsed', color='ConcurrentSessions')\n",
    "fig.update_layout(\n",
    "    title='Cumulative distribution of elapsed time until first peer connection',\n",
    "    xaxis_title='Elapsed time (s)',\n",
    "    yaxis_title='Cumulative probability',\n",
    "    legend_title='Had concurrent sessions',\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "# Plot the histogram of the number of concurrent sessions\n",
    "fig = px.histogram(df, x='ConcurrentSessions', histnorm='percent')\n",
    "fig.update_layout(\n",
    "    title='Number of concurrent sessions',\n",
    "    xaxis_title='Had concurrent sessions',\n",
    "    yaxis_title='Percentage',\n",
    ")\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot the histogram of the elapsed time until first peer connection using seaborn\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.histplot(df, x='Elapsed', hue='ConcurrentSessions', multiple='stack', bins=100)\n",
    "plt.title('Elapsed time until first peer connection')\n",
    "plt.xlabel('Elapsed time (s)')\n",
    "plt.ylabel('Count')\n",
    "plt.legend(title='Had concurrent sessions', labels=['True', 'False'])\n",
    "plt.show()\n",
    "\n",
    "# Plot the line chart of the elapsed time until first peer connection using seaborn\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.lineplot(data=df, x=df.index, y='Elapsed', marker='o')\n",
    "plt.title('Elapsed time until first peer connection')\n",
    "plt.xlabel('Session index')\n",
    "plt.ylabel('Elapsed time (s)')\n",
    "plt.show()\n",
    "\n",
    "# Plot the cumulative distribution of the elapsed time until first peer connection using seaborn\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.ecdfplot(df, x='Elapsed', hue='ConcurrentSessions')\n",
    "plt.title('Cumulative distribution of elapsed time until first peer connection')\n",
    "plt.xlabel('Elapsed time (s)')\n",
    "plt.ylabel('Cumulative probability')\n",
    "plt.legend(title='Had concurrent sessions', labels=['True', 'False'])\n",
    "plt.show()\n",
    "\n",
    "# Plot the histogram of the number of concurrent sessions using seaborn\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.histplot(df, x='ConcurrentSessions', stat='percent', discrete=True)\n",
    "plt.title('Number of concurrent sessions')\n",
    "plt.xlabel('Had concurrent sessions')\n",
    "plt.ylabel('Percentage')\n",
    "plt.legend(title='Had concurrent sessions', labels=['True', 'False'])\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.13.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}