sinchoku.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import re"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ログの読み込み\n",
    "\n",
    "ログの出力は下記のコマンドで行った。\n",
    "\n",
    "```\n",
    "git log --numstat --pretty=\"%ad\" --date=iso *.tex > thesis_log.txt\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "log = open(\"./thesis_log.txt\").read().strip()\n",
    "pattern = re.compile(r\"\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2} \\+\\d{4}\")\n",
    "\n",
    "# ログをコミットごとに分ける\n",
    "dates = pattern.findall(log)             # コミットの日時\n",
    "commits = pattern.split(log)[1:]    # コミットの中身"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ログからDataFrameへ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def parse_commit(cm):\n",
    "    lines = cm.strip().split(\"\\n\")\n",
    "    df = pd.DataFrame(index=[\"plus\", \"minus\"], dtype=int)\n",
    "    for line in lines:\n",
    "        splited = line.split(\"\\t\")\n",
    "        if len(splited) != 3:\n",
    "            continue\n",
    "        plus, minus, filename = splited\n",
    "        plus = int(plus)\n",
    "        minus = int(minus)\n",
    "        df.loc[\"plus\", filename] = plus\n",
    "        df.loc[\"minus\", filename] = minus\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>masterthesis/appendix_A.tex</th>\n",
       "      <th>masterthesis/discussion.tex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>plus</th>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>minus</th>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       masterthesis/appendix_A.tex  masterthesis/discussion.tex\n",
       "plus                           4.0                          1.0\n",
       "minus                          4.0                          1.0"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parse_commit(commits[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## コミットの中身をDataFrameに変換する"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "table = pd.concat([parse_commit(cm) for cm in commits]).fillna(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 日付をindexに加える"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "dt = pd.to_datetime(dates)\n",
    "mindex = pd.MultiIndex.from_product([dt, [\"plus\", \"minus\"]])\n",
    "\n",
    "table.index = mindex\n",
    "\n",
    "# 重複の削除\n",
    "table = table[~table.index.duplicated()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>masterthesis/appendix_A.tex</th>\n",
       "      <th>masterthesis/appendix_B.tex</th>\n",
       "      <th>masterthesis/conclusion.tex</th>\n",
       "      <th>masterthesis/discussion.tex</th>\n",
       "      <th>masterthesis/intro.tex</th>\n",
       "      <th>masterthesis/main.tex</th>\n",
       "      <th>masterthesis/method.tex</th>\n",
       "      <th>masterthesis/result.tex</th>\n",
       "      <th>masterthesis/term.tex</th>\n",
       "      <th>masterthesis/thank.tex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2016-01-22 07:02:29</th>\n",
       "      <th>plus</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>minus</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2016-01-22 06:27:08</th>\n",
       "      <th>plus</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>minus</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           masterthesis/appendix_A.tex  \\\n",
       "2016-01-22 07:02:29 plus                           4.0   \n",
       "                    minus                          4.0   \n",
       "2016-01-22 06:27:08 plus                           0.0   \n",
       "                    minus                          0.0   \n",
       "\n",
       "                           masterthesis/appendix_B.tex  \\\n",
       "2016-01-22 07:02:29 plus                           0.0   \n",
       "                    minus                          0.0   \n",
       "2016-01-22 06:27:08 plus                           0.0   \n",
       "                    minus                          2.0   \n",
       "\n",
       "                           masterthesis/conclusion.tex  \\\n",
       "2016-01-22 07:02:29 plus                           0.0   \n",
       "                    minus                          0.0   \n",
       "2016-01-22 06:27:08 plus                           0.0   \n",
       "                    minus                          0.0   \n",
       "\n",
       "                           masterthesis/discussion.tex  \\\n",
       "2016-01-22 07:02:29 plus                           1.0   \n",
       "                    minus                          1.0   \n",
       "2016-01-22 06:27:08 plus                           0.0   \n",
       "                    minus                          0.0   \n",
       "\n",
       "                           masterthesis/intro.tex  masterthesis/main.tex  \\\n",
       "2016-01-22 07:02:29 plus                      0.0                    0.0   \n",
       "                    minus                     0.0                    0.0   \n",
       "2016-01-22 06:27:08 plus                      0.0                    0.0   \n",
       "                    minus                     0.0                    0.0   \n",
       "\n",
       "                           masterthesis/method.tex  masterthesis/result.tex  \\\n",
       "2016-01-22 07:02:29 plus                       0.0                      0.0   \n",
       "                    minus                      0.0                      0.0   \n",
       "2016-01-22 06:27:08 plus                       0.0                      0.0   \n",
       "                    minus                      0.0                      0.0   \n",
       "\n",
       "                           masterthesis/term.tex  masterthesis/thank.tex  \n",
       "2016-01-22 07:02:29 plus                     0.0                     0.0  \n",
       "                    minus                    0.0                     0.0  \n",
       "2016-01-22 06:27:08 plus                     0.0                     0.0  \n",
       "                    minus                    0.0                     0.0  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table.head(4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 集計\n",
    "\n",
    "追加・削除と累計をプロットする。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 日付ごとにリサンプリング"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "per_day = table.unstack().resample(\"d\").sum().stack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>masterthesis/appendix_A.tex</th>\n",
       "      <th>masterthesis/appendix_B.tex</th>\n",
       "      <th>masterthesis/conclusion.tex</th>\n",
       "      <th>masterthesis/discussion.tex</th>\n",
       "      <th>masterthesis/intro.tex</th>\n",
       "      <th>masterthesis/main.tex</th>\n",
       "      <th>masterthesis/method.tex</th>\n",
       "      <th>masterthesis/result.tex</th>\n",
       "      <th>masterthesis/term.tex</th>\n",
       "      <th>masterthesis/thank.tex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2016-01-07</th>\n",
       "      <th>minus</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>plus</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>53.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>332.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2016-01-08</th>\n",
       "      <th>minus</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>plus</th>\n",
       "      <td>86.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>322.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  masterthesis/appendix_A.tex  masterthesis/appendix_B.tex  \\\n",
       "2016-01-07 minus                          0.0                          0.0   \n",
       "           plus                           0.0                          0.0   \n",
       "2016-01-08 minus                          1.0                          0.0   \n",
       "           plus                          86.0                          0.0   \n",
       "\n",
       "                  masterthesis/conclusion.tex  masterthesis/discussion.tex  \\\n",
       "2016-01-07 minus                          1.0                          0.0   \n",
       "           plus                          12.0                          0.0   \n",
       "2016-01-08 minus                          0.0                          0.0   \n",
       "           plus                           4.0                         10.0   \n",
       "\n",
       "                  masterthesis/intro.tex  masterthesis/main.tex  \\\n",
       "2016-01-07 minus                     5.0                    1.0   \n",
       "           plus                     53.0                   32.0   \n",
       "2016-01-08 minus                     0.0                    0.0   \n",
       "           plus                      0.0                    2.0   \n",
       "\n",
       "                  masterthesis/method.tex  masterthesis/result.tex  \\\n",
       "2016-01-07 minus                      1.0                      1.0   \n",
       "           plus                     332.0                     49.0   \n",
       "2016-01-08 minus                    155.0                      0.0   \n",
       "           plus                     322.0                      0.0   \n",
       "\n",
       "                  masterthesis/term.tex  masterthesis/thank.tex  \n",
       "2016-01-07 minus                    0.0                     1.0  \n",
       "           plus                     0.0                    12.0  \n",
       "2016-01-08 minus                    0.0                     1.0  \n",
       "           plus                     0.0                    18.0  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "per_day.head(4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 累計の計算"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "tot = per_day.sum(axis=1).unstack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>minus</th>\n",
       "      <th>plus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>10.0</td>\n",
       "      <td>490.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>157.0</td>\n",
       "      <td>442.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            minus   plus\n",
       "2016-01-07   10.0  490.0\n",
       "2016-01-08  157.0  442.0"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tot.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "tot[\"total\"] = tot[\"plus\"].cumsum() - tot[\"minus\"].cumsum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 可視化"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1081ca358>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhYAAAGSCAYAAAC/joiAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDJ1O376XFQgAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10819ab00>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tot.ix[:, [\"plus\", \"minus\", \"total\"]].plot(color=[\"g\", \"r\", \"b\"], title=\"Sinchoku Doudesuka\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}