機械学習勉強会用_ランダムデータ作成_20191102.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import scipy.stats\n",
    "\n",
    "CHAR_N = 10\n",
    "COLUMNS_N = 256\n",
    "SAMPLE_1_N = 4\n",
    "SAMPLE_2_N = 4\n",
    "\n",
    "################################################################\n",
    "# Creatre columns\n",
    "################################################################\n",
    "\n",
    "chr_arr = np.random.randint(ord('a'), ord('z'), (COLUMNS_N, CHAR_N))\n",
    "chr_arr = np.vectorize(lambda x: chr(x))(chr_arr)\n",
    "chr_arr = np.apply_along_axis(lambda x: \"\".join(x), 1, chr_arr)\n",
    "columns = chr_arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "################################################################\n",
    "# Creatre data\n",
    "################################################################\n",
    "\n",
    "loc_1 = np.random.normal(loc=0, scale=0.0000001, size=COLUMNS_N)\n",
    "loc_2 = np.random.normal(loc=0, scale=0.0000001, size=COLUMNS_N)\n",
    "\n",
    "# scale has to be positive\n",
    "scale_1 = abs(np.random.normal(loc=0, scale=0.005, size=COLUMNS_N))\n",
    "scale_2 = abs(np.random.normal(loc=0, scale=0.005, size=COLUMNS_N))\n",
    "\n",
    "\n",
    "data_1 = scipy.stats.norm.rvs(loc=loc_1, scale=scale_1, size=(SAMPLE_1_N, COLUMNS_N))\n",
    "data_2 = scipy.stats.norm.rvs(loc=loc_2, scale=scale_2, size=(SAMPLE_2_N, COLUMNS_N))\n",
    "\n",
    "data = np.concatenate((data_1, data_2), axis=0)\n",
    "# convert data to positive\n",
    "data = np.abs(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1.32229705e-03, 5.99904328e-04, 2.49506130e-03, ...,\n",
       "        5.87667118e-04, 3.18150563e-03, 3.33039690e-03],\n",
       "       [4.47743190e-03, 5.92049308e-05, 3.32327023e-03, ...,\n",
       "        4.86150138e-03, 1.08330602e-02, 1.96849081e-03],\n",
       "       [4.92268730e-03, 1.79718973e-03, 2.69555552e-03, ...,\n",
       "        5.21446685e-04, 8.46161948e-03, 4.62577131e-03],\n",
       "       ...,\n",
       "       [2.72425063e-03, 5.39997612e-03, 2.08048487e-04, ...,\n",
       "        8.70130890e-04, 1.28258813e-03, 7.97890361e-04],\n",
       "       [3.45894042e-03, 6.14078139e-03, 1.15085234e-03, ...,\n",
       "        5.75657315e-03, 2.87784050e-03, 9.75414604e-04],\n",
       "       [8.51159723e-03, 9.38825691e-03, 1.79086389e-04, ...,\n",
       "        1.08819659e-03, 5.71551461e-05, 2.67368538e-03]])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "################################################################\n",
    "# Creatre DataFrame\n",
    "################################################################\n",
    "\n",
    "df = pd.DataFrame(data, columns=columns)\n",
    "s = pd.Series(['A']*SAMPLE_1_N + ['B']*SAMPLE_2_N)\n",
    "df.insert(0, 1, s)\n",
    "\n",
    "df.iloc[:, 0].name = 'Cat'\n",
    "df.columns = ['Cat'] + df.columns[1:].tolist()\n",
    "\n",
    "df2 = df.set_index('Cat')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>qipqnmfvng</th>\n",
       "      <th>txahrgpkvi</th>\n",
       "      <th>miyuafrahl</th>\n",
       "      <th>bdefoakoce</th>\n",
       "      <th>bqohvaawef</th>\n",
       "      <th>toijtlfbmd</th>\n",
       "      <th>lxwpcwrrlk</th>\n",
       "      <th>frsxhomjfb</th>\n",
       "      <th>vaocnlbiod</th>\n",
       "      <th>hkcrfqpmwu</th>\n",
       "      <th>...</th>\n",
       "      <th>ihbltbdine</th>\n",
       "      <th>ehmmycvibx</th>\n",
       "      <th>yeagdiukij</th>\n",
       "      <th>kidkdniqvt</th>\n",
       "      <th>xdtyihkheh</th>\n",
       "      <th>aarqvghgpf</th>\n",
       "      <th>xcbikubbmr</th>\n",
       "      <th>ulxsoankwt</th>\n",
       "      <th>yssunmuhxr</th>\n",
       "      <th>rklqskqrya</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cat</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.001322</td>\n",
       "      <td>0.000600</td>\n",
       "      <td>0.002495</td>\n",
       "      <td>0.023099</td>\n",
       "      <td>0.019515</td>\n",
       "      <td>0.000434</td>\n",
       "      <td>0.000786</td>\n",
       "      <td>0.001391</td>\n",
       "      <td>0.000764</td>\n",
       "      <td>0.002436</td>\n",
       "      <td>...</td>\n",
       "      <td>0.001314</td>\n",
       "      <td>0.000041</td>\n",
       "      <td>0.002403</td>\n",
       "      <td>0.001596</td>\n",
       "      <td>0.001745</td>\n",
       "      <td>0.004370</td>\n",
       "      <td>9.362527e-03</td>\n",
       "      <td>0.000588</td>\n",
       "      <td>0.003182</td>\n",
       "      <td>0.003330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.004477</td>\n",
       "      <td>0.000059</td>\n",
       "      <td>0.003323</td>\n",
       "      <td>0.027906</td>\n",
       "      <td>0.006067</td>\n",
       "      <td>0.000169</td>\n",
       "      <td>0.012106</td>\n",
       "      <td>0.002231</td>\n",
       "      <td>0.002371</td>\n",
       "      <td>0.004574</td>\n",
       "      <td>...</td>\n",
       "      <td>0.001692</td>\n",
       "      <td>0.000345</td>\n",
       "      <td>0.005783</td>\n",
       "      <td>0.001131</td>\n",
       "      <td>0.000014</td>\n",
       "      <td>0.003192</td>\n",
       "      <td>1.412481e-02</td>\n",
       "      <td>0.004862</td>\n",
       "      <td>0.010833</td>\n",
       "      <td>0.001968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.004923</td>\n",
       "      <td>0.001797</td>\n",
       "      <td>0.002696</td>\n",
       "      <td>0.001735</td>\n",
       "      <td>0.013736</td>\n",
       "      <td>0.000363</td>\n",
       "      <td>0.001851</td>\n",
       "      <td>0.002505</td>\n",
       "      <td>0.003749</td>\n",
       "      <td>0.002596</td>\n",
       "      <td>...</td>\n",
       "      <td>0.001510</td>\n",
       "      <td>0.000463</td>\n",
       "      <td>0.004083</td>\n",
       "      <td>0.007114</td>\n",
       "      <td>0.000314</td>\n",
       "      <td>0.006574</td>\n",
       "      <td>1.049355e-02</td>\n",
       "      <td>0.000521</td>\n",
       "      <td>0.008462</td>\n",
       "      <td>0.004626</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.014158</td>\n",
       "      <td>0.001891</td>\n",
       "      <td>0.003664</td>\n",
       "      <td>0.004781</td>\n",
       "      <td>0.006898</td>\n",
       "      <td>0.000822</td>\n",
       "      <td>0.004127</td>\n",
       "      <td>0.001055</td>\n",
       "      <td>0.002372</td>\n",
       "      <td>0.002913</td>\n",
       "      <td>...</td>\n",
       "      <td>0.002878</td>\n",
       "      <td>0.000137</td>\n",
       "      <td>0.006288</td>\n",
       "      <td>0.001422</td>\n",
       "      <td>0.001013</td>\n",
       "      <td>0.008737</td>\n",
       "      <td>3.351760e-03</td>\n",
       "      <td>0.001563</td>\n",
       "      <td>0.015539</td>\n",
       "      <td>0.002694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.002575</td>\n",
       "      <td>0.001828</td>\n",
       "      <td>0.000619</td>\n",
       "      <td>0.002462</td>\n",
       "      <td>0.000493</td>\n",
       "      <td>0.000983</td>\n",
       "      <td>0.000419</td>\n",
       "      <td>0.012820</td>\n",
       "      <td>0.008203</td>\n",
       "      <td>0.003039</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000004</td>\n",
       "      <td>0.003297</td>\n",
       "      <td>0.000656</td>\n",
       "      <td>0.015672</td>\n",
       "      <td>0.006815</td>\n",
       "      <td>0.007464</td>\n",
       "      <td>7.131834e-04</td>\n",
       "      <td>0.003105</td>\n",
       "      <td>0.000135</td>\n",
       "      <td>0.002465</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.002724</td>\n",
       "      <td>0.005400</td>\n",
       "      <td>0.000208</td>\n",
       "      <td>0.002328</td>\n",
       "      <td>0.000816</td>\n",
       "      <td>0.002735</td>\n",
       "      <td>0.000066</td>\n",
       "      <td>0.000690</td>\n",
       "      <td>0.006815</td>\n",
       "      <td>0.001542</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000351</td>\n",
       "      <td>0.000690</td>\n",
       "      <td>0.001892</td>\n",
       "      <td>0.001400</td>\n",
       "      <td>0.011279</td>\n",
       "      <td>0.000261</td>\n",
       "      <td>2.737234e-04</td>\n",
       "      <td>0.000870</td>\n",
       "      <td>0.001283</td>\n",
       "      <td>0.000798</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.003459</td>\n",
       "      <td>0.006141</td>\n",
       "      <td>0.001151</td>\n",
       "      <td>0.000678</td>\n",
       "      <td>0.002688</td>\n",
       "      <td>0.000411</td>\n",
       "      <td>0.000780</td>\n",
       "      <td>0.009784</td>\n",
       "      <td>0.002659</td>\n",
       "      <td>0.005530</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000054</td>\n",
       "      <td>0.001322</td>\n",
       "      <td>0.001091</td>\n",
       "      <td>0.001643</td>\n",
       "      <td>0.001309</td>\n",
       "      <td>0.006298</td>\n",
       "      <td>5.208182e-04</td>\n",
       "      <td>0.005757</td>\n",
       "      <td>0.002878</td>\n",
       "      <td>0.000975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.008512</td>\n",
       "      <td>0.009388</td>\n",
       "      <td>0.000179</td>\n",
       "      <td>0.001872</td>\n",
       "      <td>0.000081</td>\n",
       "      <td>0.001894</td>\n",
       "      <td>0.000560</td>\n",
       "      <td>0.008303</td>\n",
       "      <td>0.000932</td>\n",
       "      <td>0.005055</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000632</td>\n",
       "      <td>0.004138</td>\n",
       "      <td>0.000623</td>\n",
       "      <td>0.000271</td>\n",
       "      <td>0.010007</td>\n",
       "      <td>0.003051</td>\n",
       "      <td>3.980333e-07</td>\n",
       "      <td>0.001088</td>\n",
       "      <td>0.000057</td>\n",
       "      <td>0.002674</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 256 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     qipqnmfvng  txahrgpkvi  miyuafrahl  bdefoakoce  bqohvaawef  toijtlfbmd  \\\n",
       "Cat                                                                           \n",
       "A      0.001322    0.000600    0.002495    0.023099    0.019515    0.000434   \n",
       "A      0.004477    0.000059    0.003323    0.027906    0.006067    0.000169   \n",
       "A      0.004923    0.001797    0.002696    0.001735    0.013736    0.000363   \n",
       "A      0.014158    0.001891    0.003664    0.004781    0.006898    0.000822   \n",
       "B      0.002575    0.001828    0.000619    0.002462    0.000493    0.000983   \n",
       "B      0.002724    0.005400    0.000208    0.002328    0.000816    0.002735   \n",
       "B      0.003459    0.006141    0.001151    0.000678    0.002688    0.000411   \n",
       "B      0.008512    0.009388    0.000179    0.001872    0.000081    0.001894   \n",
       "\n",
       "     lxwpcwrrlk  frsxhomjfb  vaocnlbiod  hkcrfqpmwu     ...      ihbltbdine  \\\n",
       "Cat                                                     ...                   \n",
       "A      0.000786    0.001391    0.000764    0.002436     ...        0.001314   \n",
       "A      0.012106    0.002231    0.002371    0.004574     ...        0.001692   \n",
       "A      0.001851    0.002505    0.003749    0.002596     ...        0.001510   \n",
       "A      0.004127    0.001055    0.002372    0.002913     ...        0.002878   \n",
       "B      0.000419    0.012820    0.008203    0.003039     ...        0.000004   \n",
       "B      0.000066    0.000690    0.006815    0.001542     ...        0.000351   \n",
       "B      0.000780    0.009784    0.002659    0.005530     ...        0.000054   \n",
       "B      0.000560    0.008303    0.000932    0.005055     ...        0.000632   \n",
       "\n",
       "     ehmmycvibx  yeagdiukij  kidkdniqvt  xdtyihkheh  aarqvghgpf    xcbikubbmr  \\\n",
       "Cat                                                                             \n",
       "A      0.000041    0.002403    0.001596    0.001745    0.004370  9.362527e-03   \n",
       "A      0.000345    0.005783    0.001131    0.000014    0.003192  1.412481e-02   \n",
       "A      0.000463    0.004083    0.007114    0.000314    0.006574  1.049355e-02   \n",
       "A      0.000137    0.006288    0.001422    0.001013    0.008737  3.351760e-03   \n",
       "B      0.003297    0.000656    0.015672    0.006815    0.007464  7.131834e-04   \n",
       "B      0.000690    0.001892    0.001400    0.011279    0.000261  2.737234e-04   \n",
       "B      0.001322    0.001091    0.001643    0.001309    0.006298  5.208182e-04   \n",
       "B      0.004138    0.000623    0.000271    0.010007    0.003051  3.980333e-07   \n",
       "\n",
       "     ulxsoankwt  yssunmuhxr  rklqskqrya  \n",
       "Cat                                      \n",
       "A      0.000588    0.003182    0.003330  \n",
       "A      0.004862    0.010833    0.001968  \n",
       "A      0.000521    0.008462    0.004626  \n",
       "A      0.001563    0.015539    0.002694  \n",
       "B      0.003105    0.000135    0.002465  \n",
       "B      0.000870    0.001283    0.000798  \n",
       "B      0.005757    0.002878    0.000975  \n",
       "B      0.001088    0.000057    0.002674  \n",
       "\n",
       "[8 rows x 256 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "################################################################\n",
    "# Analysis 1\n",
    "################################################################\n",
    "\n",
    "fig, (ax1, ax2) = plt.subplots(2, 1, sharex=True)\n",
    "\n",
    "for n, aminosan in enumerate(df2.columns, 1):\n",
    "    p1 = df2.loc['A'].loc[:, aminosan]\n",
    "    p2 = df2.loc['B'].loc[:, aminosan]\n",
    "    y_p1 = p1\n",
    "    x_p1 = [n]*len(p1)\n",
    "    y_p2 = p2\n",
    "    x_p2 = [n]*len(p2)\n",
    "    ax1.scatter(x_p1, y_p1)\n",
    "    ax2.scatter(x_p2, -1*y_p2)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "################################################################\n",
    "# Analysis 2\n",
    "################################################################\n",
    "A_mean = df2.loc['A'].mean()\n",
    "B_mean = df2.loc['B'].mean()\n",
    "\n",
    "maxi = max(A_mean.max(), B_mean.max())\n",
    "\n",
    "plt.scatter(A_mean, B_mean, alpha=0.3)\n",
    "plt.plot([0, maxi], [0, maxi], c='orange')\n",
    "plt.gca().set_aspect('equal')\n",
    "plt.gcf().set_size_inches(5, 5)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}