soracom.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import requests\n",
    "import time\n",
    "from datetime import datetime\n",
    "from pandas import *\n",
    "from pylab import *\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "plt.style.use('ggplot') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "operator_id = os.environ['operatorId']\n",
    "credentials = pandas.io.json.dumps({\n",
    "    \"authKeyId\":os.environ[\"authKeyId\"],\n",
    "    \"authKey\":os.environ['authKey']\n",
    "})\n",
    "\n",
    "api_url_base = \"https://api.soracom.io/v1\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datetime import datetime\n",
    "\n",
    "# API認証トークンを取得するための関数\n",
    "def auth():\n",
    "    url = api_url_base + \"/auth\"\n",
    "    r = requests.post(url, data=credentials, headers={'Content-Type': 'application/json'})\n",
    "    return r.json()\n",
    "\n",
    "# SIMごとの利用状況を日別データとして取得するための関数\n",
    "def getAirStatsByDay(days):\n",
    "    url = api_url_base + \"/stats/air/operators/\" + operator_id + \"/export\"\n",
    "    api_credentials = auth()\n",
    "\n",
    "    headers = {\n",
    "        \"Content-Type\":\"application/json\",\n",
    "        \"X-Soracom-API-Key\":api_credentials[\"apiKey\"],\n",
    "        \"X-Soracom-Token\":api_credentials[\"token\"]\n",
    "    }\n",
    "\n",
    "    params = {\n",
    "        \"export_mode\":\"sync\"\n",
    "    }\n",
    "\n",
    "    now =  int(time.time())\n",
    "    body = {\n",
    "        \"from\": now - 86400*days,\n",
    "        \"to\": now,\n",
    "        \"period\":\"day\"\n",
    "    }\n",
    "\n",
    "    f = requests.post(url,data=pandas.io.json.dumps(body),params=params,headers=headers)\n",
    "    f = f.json()\n",
    "    traffic = pandas.read_csv(f['url'])\n",
    "    traffic['dates'] = traffic['date'].apply(lambda x:  datetime.strptime(str(x),'%Y%m%d'))\n",
    "    traffic.index = traffic['dates']\n",
    "    return traffic\n",
    "\n",
    "# エラーログを取得するための関数\n",
    "def getLogs(days):\n",
    "    url = api_url_base + \"/logs\"\n",
    "    api_credentials = auth()\n",
    "    headers = {\n",
    "        \"Content-Type\":\"application/json\",\n",
    "        \"X-Soracom-API-Key\":api_credentials[\"apiKey\"],\n",
    "        \"X-Soracom-Token\":api_credentials[\"token\"]\n",
    "    }\n",
    "    \n",
    "    now =  int(time.time())\n",
    "    params = {\n",
    "        \"from\": now - 86400*days,\n",
    "        \"to\":now,\n",
    "        \"limit\":10000\n",
    "    }\n",
    "    \n",
    "    f = requests.get(url,params=params,headers=headers)\n",
    "    logs = f.json()\n",
    "    for log in logs:\n",
    "        log['time'] = datetime.fromtimestamp(log['time']/1000)\n",
    "        log['message'] = log['body']['message']\n",
    "\n",
    "    logs = DataFrame(data=logs)\n",
    "    logs.index = logs['time']\n",
    "    return logs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Traffic analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "過去7日分の、当該SORACOMアカウントのすべてのSIMの日毎の利用状況をDataFrameとして取得します"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "traffic = getAirStatsByDay(7)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "まずは速度クラスごとにダウンロード通信の利用量合計を可視化してみましょう"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "traffic['downloadMB'] = traffic['downloadByteSizeTotal'].apply(lambda x: x/1024/1024)\n",
    "traffic.groupby(['dates','type'])['downloadMB'].sum().unstack().plot(figsize=(20,10))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "次に利用量Top10の回線をグラフ化してみます。同時に「downloadMB」という名前で、すべての回線の平均値もグラフに一緒にプロットします。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "topN = traffic.groupby(['imsi'])['downloadMB'].sum().head(10).index.tolist()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "traffic[traffic['imsi'].isin(topN)].groupby(['dates','imsi'])['downloadMB'].sum().unstack().plot(figsize=(20,10),ax=ax)\n",
    "traffic.groupby(['dates'])['downloadMB'].mean().plot(figsize=(20,10),ax=ax,legend=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "回線IDではなく、SIMの名前をキーにグラフを描画しなおします。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "topN = traffic.groupby(['imsi'])['downloadMB'].sum().head(10).index.tolist()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "traffic[traffic['imsi'].isin(topN)].groupby(['dates','name'])['downloadMB'].sum().unstack().plot(figsize=(20,10),ax=ax)\n",
    "traffic.groupby(['dates'])['downloadMB'].mean().plot(figsize=(20,10),ax=ax,legend=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Error analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "今後はエラーログの分析を行います。先程と同様にまずは過去7日分のデータをDataFrameに読み込みます。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "logs = getLogs(7)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "そしてまずはエラーメッセージ毎に回数をカウントしてみます。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "logs.groupby(['message'])['message'].count().plot(kind='bar',figsize=(20,10))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "次に「エラーメッセージx回線ID」でグラフを描画しなおします。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "logs.groupby(['message','resourceId'])['message'].count().plot(kind='bar',figsize=(20,10))"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}