{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## オープンデータの活用(自転車盗難推測)\n",
    "長野県自転車盗難データを推測する。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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>Unnamed: 0</th>\n",
       "      <th>occurTime</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>isRock</th>\n",
       "      <th>occurMonth</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>6</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1476</th>\n",
       "      <td>1491</td>\n",
       "      <td>10</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1477</th>\n",
       "      <td>1492</td>\n",
       "      <td>6</td>\n",
       "      <td>50</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>1493</td>\n",
       "      <td>17</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1479</th>\n",
       "      <td>1494</td>\n",
       "      <td>16</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1480</th>\n",
       "      <td>1495</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1481 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Unnamed: 0  occurTime  age  occupation  isRock  occurMonth\n",
       "0              0         13   10           1       1           7\n",
       "1              1          6   10           2       1           9\n",
       "2              2         12   10           2       1          10\n",
       "3              3         13   10           2       1          12\n",
       "4              4          7   10           2       1           6\n",
       "...          ...        ...  ...         ...     ...         ...\n",
       "1476        1491         10   10           1       0           6\n",
       "1477        1492          6   50           4       0           6\n",
       "1478        1493         17   10           2       0           7\n",
       "1479        1494         16   10           2       0           8\n",
       "1480        1495          8   10           2       0          11\n",
       "\n",
       "[1481 rows x 6 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import scipy as sc\n",
    "from scipy import linalg\n",
    "from scipy import spatial\n",
    "import scipy.spatial.distance\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.font_manager\n",
    "import pylab\n",
    "trans_data = pd.read_csv(\"./CSV/output/transform_bohan_data.csv\")\n",
    "trans_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 任意の情報を末尾に追加\n",
    "userInfo = pd.Series([1496, 15, 60, 5, 1, 1], index=trans_data.columns)\n",
    "trans_data = trans_data.append( userInfo, ignore_index=True )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>occurTime</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>isRock</th>\n",
       "      <th>occurMonth</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1477</th>\n",
       "      <td>6</td>\n",
       "      <td>50</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>17</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1479</th>\n",
       "      <td>16</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1480</th>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1481</th>\n",
       "      <td>15</td>\n",
       "      <td>60</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1482 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      occurTime  age  occupation  isRock  occurMonth\n",
       "0            13   10           1       1           7\n",
       "1             6   10           2       1           9\n",
       "2            12   10           2       1          10\n",
       "3            13   10           2       1          12\n",
       "4             7   10           2       1           6\n",
       "...         ...  ...         ...     ...         ...\n",
       "1477          6   50           4       0           6\n",
       "1478         17   10           2       0           7\n",
       "1479         16   10           2       0           8\n",
       "1480          8   10           2       0          11\n",
       "1481         15   60           5       1           1\n",
       "\n",
       "[1482 rows x 5 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 不要な列 Unnamed: 0の削除\n",
    "trans_data = trans_data.drop(columns='Unnamed: 0')\n",
    "trans_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 任意情報追加の場合は1482\n",
    "ROW = 1482\n",
    "COLUMN = 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# row:行,column:列,ave:平均,vcm:分散共分散行列\n",
    "row = []\n",
    "column = []\n",
    "ave = [0.0 for i in range(COLUMN)]\n",
    "vcm = np.zeros((ROW, COLUMN, COLUMN))\n",
    "diff = np.zeros((1, COLUMN))\n",
    "mahal = np.zeros(ROW)\n",
    "tmp = np.zeros(COLUMN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1482\n"
     ]
    }
   ],
   "source": [
    "# rowにtrans_dataの行要素(1481件分)を代入\n",
    "for i in range(ROW):\n",
    "    row.append(list(trans_data.iloc[i]))\n",
    "print(len(row))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n"
     ]
    }
   ],
   "source": [
    "# rowにtrans_dataの列要素(5件分)を代入\n",
    "for i in range(COLUMN):\n",
    "    column.append(list(trans_data.iloc[:, i]))\n",
    "print(len(column))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[12.950742240215924, 19.898785425101213, 2.8157894736842106, 0.27800269905533065, 6.922402159244265]\n"
     ]
    }
   ],
   "source": [
    "# 平均ベクトルの計算\n",
    "# 平均値の計算 (各特徴量の平均値を算出) \n",
    "for i in range(COLUMN):\n",
    "    ave[i] = np.average(column[i])\n",
    "print(ave)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[15 60  5  1  1]\n",
      "[12.95074224 19.89878543  2.81578947  0.2780027   6.92240216]\n",
      "[[ 2.83364195e-03  5.54505568e-02  3.02024991e-03  9.98352612e-04\n",
      "  -8.18929054e-03]\n",
      " [ 5.54505568e-02  1.08509272e+00  5.91022233e-02  1.95364161e-02\n",
      "  -1.60253387e-01]\n",
      " [ 3.02024991e-03  5.91022233e-02  3.21914684e-03  1.06409859e-03\n",
      "  -8.72859186e-03]\n",
      " [ 9.98352612e-04  1.95364161e-02  1.06409859e-03  3.51740960e-04\n",
      "  -2.88526206e-03]\n",
      " [-8.18929054e-03 -1.60253387e-01 -8.72859186e-03 -2.88526206e-03\n",
      "   2.36672384e-02]]\n"
     ]
    }
   ],
   "source": [
    "# 分散共分散行列の計算\n",
    "\n",
    "# Numpyのメソッドを使うので，array()でリストを変換した．\n",
    "row = np.array([row])\n",
    "ave = np.array(ave)\n",
    "\n",
    "# 分散共分散行列を求める\n",
    "# np.swapaxes()で軸を変換することができる．\n",
    "for i in range(ROW):\n",
    "    diff = (row[0][i] - ave)\n",
    "    diff = np.array([diff])\n",
    "    vcm[i] = (diff * np.swapaxes(diff, 0, 1)) / ROW\n",
    "\n",
    "print(row[0][1481])\n",
    "print(ave)\n",
    "print(vcm[1481])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# マハラノビス距離\n",
    "# mahalnobis distanceを求める\n",
    "for i in range(ROW):\n",
    "    # 一般逆行列を生成し，計算の都合上転値をかける\n",
    "    vcm[i] = sc.linalg.pinv(vcm[i])\n",
    "    vcm[i] = vcm[i].transpose()\n",
    "    vcm[i] = np.identity(COLUMN)\n",
    "    # 差分ベクトルの生成\n",
    "    diff = (row[0][i] - ave)\n",
    "    for j in range(COLUMN):\n",
    "        tmp[j] = np.dot(diff, vcm[i][j])\n",
    "    mahal[i] = np.dot(tmp, diff)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mahal [10.09023152 12.32079445 10.46653069 ... 10.44930337 11.82647047\n",
      " 40.65309054]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot = pylab.arange(0.0, ROW, 1.0)\n",
    "mahal = np.sqrt(mahal)\n",
    "\n",
    "print(\"mahal\", mahal)\n",
    "plt.bar(range(ROW),mahal)\n",
    "plt.xlabel(\"target data\")\n",
    "plt.ylabel(\"mahal\")\n",
    "plt.savefig(\"mahal.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 最後これにマハラノビス距離の列を追加したい\n",
    "trans_data[\"mahal\"] = mahal\n",
    "# マハラノビス距離を追加したデータをcsv出力\n",
    "trans_data.to_csv('./CSV/output/mahl_bohan_data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>occurTime</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>isRock</th>\n",
       "      <th>occurMonth</th>\n",
       "      <th>mahal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>18</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>40.455992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>10</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>40.351078</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>21</td>\n",
       "      <td>70</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>11</td>\n",
       "      <td>50.926149</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>15</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>40.368499</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>12</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>40.571046</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1456</th>\n",
       "      <td>9</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>40.359522</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1458</th>\n",
       "      <td>17</td>\n",
       "      <td>60</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>40.323561</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1467</th>\n",
       "      <td>18</td>\n",
       "      <td>70</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>50.716676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1474</th>\n",
       "      <td>19</td>\n",
       "      <td>70</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>50.488174</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1481</th>\n",
       "      <td>15</td>\n",
       "      <td>60</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>40.653091</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>79 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      occurTime  age  occupation  isRock  occurMonth      mahal\n",
       "10           18   60           4       1           8  40.455992\n",
       "49           10   60           4       1          10  40.351078\n",
       "60           21   70           4       1          11  50.926149\n",
       "64           15   60           4       1           3  40.368499\n",
       "68           12   60           4       1           1  40.571046\n",
       "...         ...  ...         ...     ...         ...        ...\n",
       "1456          9   60           4       0           5  40.359522\n",
       "1458         17   60           4       0           7  40.323561\n",
       "1467         18   70           4       0           1  50.716676\n",
       "1474         19   70           4       0           6  50.488174\n",
       "1481         15   60           5       1           1  40.653091\n",
       "\n",
       "[79 rows x 6 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 高齢者が多い\n",
    "trans_data[trans_data[\"mahal\"] >= 35] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>occurTime</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>isRock</th>\n",
       "      <th>occurMonth</th>\n",
       "      <th>mahal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>10.090232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>12.320794</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>10.466531</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>11.178424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>11.637650</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1475</th>\n",
       "      <td>18</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>11.300715</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1476</th>\n",
       "      <td>10</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>10.531763</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>17</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>10.729924</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1479</th>\n",
       "      <td>16</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>10.449303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1480</th>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>11.826470</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1230 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      occurTime  age  occupation  isRock  occurMonth      mahal\n",
       "0            13   10           1       1           7  10.090232\n",
       "1             6   10           2       1           9  12.320794\n",
       "2            12   10           2       1          10  10.466531\n",
       "3            13   10           2       1          12  11.178424\n",
       "4             7   10           2       1           6  11.637650\n",
       "...         ...  ...         ...     ...         ...        ...\n",
       "1475         18   10           1       0           6  11.300715\n",
       "1476         10   10           1       0           6  10.531763\n",
       "1478         17   10           2       0           7  10.729924\n",
       "1479         16   10           2       0           8  10.449303\n",
       "1480          8   10           2       0          11  11.826470\n",
       "\n",
       "[1230 rows x 6 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 若者が多い\n",
    "trans_data[trans_data[\"mahal\"] <= 16.0] "
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}