master
/ generate_data.ipynb

generate_data.ipynb @master

d2be75f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
{
 "cells": [
  {
   "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>指 标</th>\n",
       "      <th>2017</th>\n",
       "      <th>2016</th>\n",
       "      <th>2015</th>\n",
       "      <th>2014</th>\n",
       "      <th>2013</th>\n",
       "      <th>2012</th>\n",
       "      <th>2011</th>\n",
       "      <th>2010</th>\n",
       "      <th>2009</th>\n",
       "      <th>2008</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>行政区域面积</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "      <td>1467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>第一产业增加值</td>\n",
       "      <td>282590</td>\n",
       "      <td>276808</td>\n",
       "      <td>254933</td>\n",
       "      <td>230741</td>\n",
       "      <td>203721</td>\n",
       "      <td>196012</td>\n",
       "      <td>177808</td>\n",
       "      <td>157023</td>\n",
       "      <td>130424</td>\n",
       "      <td>123354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>第二产业增加值</td>\n",
       "      <td>756832</td>\n",
       "      <td>785238</td>\n",
       "      <td>779507</td>\n",
       "      <td>741551</td>\n",
       "      <td>673699</td>\n",
       "      <td>607700</td>\n",
       "      <td>537500</td>\n",
       "      <td>479300</td>\n",
       "      <td>411956</td>\n",
       "      <td>417242</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>居民储蓄存款余额</td>\n",
       "      <td>993018</td>\n",
       "      <td>870944</td>\n",
       "      <td>840324</td>\n",
       "      <td>738858</td>\n",
       "      <td>645667</td>\n",
       "      <td>571882</td>\n",
       "      <td>526651</td>\n",
       "      <td>445659</td>\n",
       "      <td>383279</td>\n",
       "      <td>317078</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>年末金融机构各项贷款余额</td>\n",
       "      <td>767371</td>\n",
       "      <td>644153</td>\n",
       "      <td>582445</td>\n",
       "      <td>502392</td>\n",
       "      <td>427285</td>\n",
       "      <td>345973</td>\n",
       "      <td>281859</td>\n",
       "      <td>237260</td>\n",
       "      <td>199415</td>\n",
       "      <td>143451</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            指 标    2017    2016    2015    2014    2013    2012    2011  \\\n",
       "0        行政区域面积    1467    1467    1467    1467    1467    1467    1467   \n",
       "1       第一产业增加值  282590  276808  254933  230741  203721  196012  177808   \n",
       "2       第二产业增加值  756832  785238  779507  741551  673699  607700  537500   \n",
       "3      居民储蓄存款余额  993018  870944  840324  738858  645667  571882  526651   \n",
       "4  年末金融机构各项贷款余额  767371  644153  582445  502392  427285  345973  281859   \n",
       "\n",
       "     2010    2009    2008  \n",
       "0    1467    1467    1467  \n",
       "1  157023  130424  123354  \n",
       "2  479300  411956  417242  \n",
       "3  445659  383279  317078  \n",
       "4  237260  199415  143451  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "yes_data_path = './mydata/Yes/'\n",
    "no_data_path  = './mydata/No/'\n",
    "yes_root_csv = pd.read_csv(yes_data_path+'长乐区.csv')\n",
    "no_root_csv = pd.read_csv(no_data_path+'闽清县.csv')\n",
    "no_root_csv.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "gen_num = 1000\n",
    "\n",
    "def generate_csv(input_csv, gen_num, data_path):\n",
    "    for i in range(gen_num):\n",
    "        # for each row\n",
    "        num_row = input_csv.shape[0]\n",
    "        num_col = input_csv.shape[1]\n",
    "        for row in range(num_row):\n",
    "            col = random.randint(1,num_col - 1)\n",
    "            #print('%d,%d'%(row,col))\n",
    "            #print('previous %d'%input_csv.iloc[row,col])\n",
    "            input_csv.iloc[row,col] = input_csv.iloc[row,col]*(1.0 + random.randint(-100,100)/1000.)\n",
    "            #print('previous %d'%input_csv.iloc[row,col])\n",
    "        input_csv.to_csv(data_path + str(i)+'.csv', index=False)\n",
    "\n",
    "generate_csv(yes_root_csv, gen_num, yes_data_path)\n",
    "generate_csv(no_root_csv,  gen_num, no_data_path)\n",
    "\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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}