二分类算法比赛的文档描述

数据来源：

选自UCI机器学习库中的「银行营销数据集(Bank Marketing Data Set)」

算法完成目标：

 这些数据与葡萄牙银行机构的营销活动相关。这些营销活动以电话为基础，一般，银行的客服人员需要联系客户至少一次，以此确认客户是否将认购该银行的产品（定期存款）。我们的目的是预测研究客户定期存款业务的概率，可能性。

代码输出的示例：

ID表示客户唯一标识，pred表示预测客户订购定期存款业务的概率。

ID	Pred
25318	0.123456
25319	0.654321
25320	0.799212

代码中的主要思路：

首先对数据进行预处理，将数据进行分割，进行归一化处理，将数据划分为训练集和测试集，
在数据中将“'job','marital','education','default','housing','loan',
'contact','poutcome','month'”的字符型数据进行编码，然后运用K近邻的方法
建立模型，然后完成对数据的预测分析。

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: './model/encoder0.pkl'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-3-4e2fb6df1a4a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     92\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m__name__\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'__main__'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     93\u001b[0m     \u001b[0;31m# train()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 94\u001b[0;31m     \u001b[0mloader\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mModel_Loader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     95\u001b[0m     \u001b[0mpredict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mloader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfetch_predict_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     96\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-3-4e2fb6df1a4a>\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     54\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoder_list\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     55\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m9\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 56\u001b[0;31m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoder_list\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjoblib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'./model/encoder'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;34m'.pkl'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     57\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjoblib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'./model/ss.pkl'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     58\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0malgo\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjoblib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'./model/svm.pkl'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/sklearn/externals/joblib/numpy_pickle.py\u001b[0m in \u001b[0;36mload\u001b[0;34m(filename, mmap_mode)\u001b[0m\n\u001b[1;32m    568\u001b[0m             \u001b[0mobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_unpickle\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    569\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 570\u001b[0;31m         \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    571\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0m_read_fileobject\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmmap_mode\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mfobj\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    572\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_basestring\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: './model/encoder0.pkl'"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "import pandas as pd\n",
    "from sklearn.preprocessing import StandardScaler,LabelEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "import numpy as np\n",
    "from sklearn.externals import joblib\n",
    "\n",
    "#设定随机种子 防止模型效果不稳定\n",
    "np.random.seed(50)\n",
    "def train():\n",
    "    #1.加载数据\n",
    "    path='.//train_set.csv'\n",
    "    reader = pd.read_csv(path, sep=',',iterator=True,engine='python')\n",
    "    df = reader.get_chunk(25318)\n",
    "\n",
    "    #2.数据处理\n",
    "    #对数据进行分割处理 划分x,y\n",
    "    X=df.iloc[:,1:-1]\n",
    "    Y=df.iloc[:,-1]\n",
    "    # print(Y.shape)\n",
    "\n",
    "    # 3.特征工程\n",
    "    #对x 中的字符型数据进行编码 变成数值型数据 1,2,3,....\n",
    "    encoder=LabelEncoder()\n",
    "    X_list=['job','marital','education','default','housing','loan','contact','poutcome','month']\n",
    "    for index,e in enumerate(X_list):\n",
    "        X[e] = encoder.fit_transform(X[e])   #对每一个属性列进行操作\n",
    "        joblib.dump(encoder, './model/encoder'+str(index)+'.pkl')   #将每次的参数保存\n",
    "    #对各行文本进行归一化\n",
    "    ss=StandardScaler()  #将每列数据归一化\n",
    "    X=ss.fit_transform(X)\n",
    "\n",
    "    #划分训练集和测试集\n",
    "    x_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.2)  #测试集占比0.2\n",
    "\n",
    "    #构建模型\n",
    "    svm=SVC(kernel='rbf',gamma=0.16,C=1.68,probability=True)  #不断调参 得出的参数\n",
    "    svm.fit(x_train,y_train)\n",
    "\n",
    "    #查看模型效果\n",
    "    print('测试集分类效果:{}'.format(svm.score(x_test,y_test)))\n",
    "    print('训练集分类效果:{}'.format(svm.score(x_train,y_train)))\n",
    "\n",
    "    print(\"测试集每个客户的概率{}\".format(svm.predict_proba(x_test)))\n",
    "    #模型持久化\n",
    "    joblib.dump(ss, './model/ss.pkl')  #保存模型参数\n",
    "    joblib.dump(svm, './model/svm.pkl')\n",
    "\n",
    "\n",
    "#建立加载模型函数\n",
    "class Model_Loader(object):\n",
    "    def __init__(self):\n",
    "        # 1. 加载恢复模型\n",
    "        self.encoder_list=[]\n",
    "        for i in range(9):\n",
    "           self.encoder_list.append(joblib.load('./model/encoder'+str(i)+'.pkl'))\n",
    "        self.ss = joblib.load('./model/ss.pkl')\n",
    "        self.algo = joblib.load('./model/svm.pkl')\n",
    "    def fetch_predict_value(self):\n",
    "        #导入预测数据\n",
    "        path1='.//test_set.csv'\n",
    "        reader = pd.read_csv(path1, sep=',', iterator=True, engine='python')\n",
    "        df = reader.get_chunk(10000)\n",
    "        x_test = df.iloc[:, 1:]\n",
    "        #下面是对每个列属性的数据进行数值化操作\n",
    "        # X_list = ['job', 'marital', 'education', 'default', 'housing', 'loan', 'contact', 'poutcome', 'month']\n",
    "        x_test['job']=self.encoder_list[0].transform(x_test['job'])\n",
    "        x_test['marital']=self.encoder_list[1].transform(x_test['marital'])\n",
    "        x_test['education']=self.encoder_list[2].transform(x_test['education'])\n",
    "        x_test['default']=self.encoder_list[3].transform(x_test['default'])\n",
    "        x_test['housing']=self.encoder_list[4].transform(x_test['housing'])\n",
    "        x_test['loan']=self.encoder_list[5].transform(x_test['loan'])\n",
    "        x_test['contact']=self.encoder_list[6].transform(x_test['contact'])\n",
    "        x_test['poutcome']=self.encoder_list[7].transform(x_test['poutcome'])\n",
    "        x_test['month'] = self.encoder_list[8].transform(x_test['month'])\n",
    "\n",
    "        #将每一个属性列进行归一化操作\n",
    "        x_test=self.ss.transform(x_test)\n",
    "        #预测数据\n",
    "        predict_proba=self.algo.predict_proba(x_test)\n",
    "        _predict_proba=[]\n",
    "        #将每个预测为成功的概率取出\n",
    "        for i in predict_proba:\n",
    "            _predict_proba.append(i[1])\n",
    "        #将x_test的ID值与x_test的预测值拼接在一起\n",
    "        x_predict=pd.concat([df.iloc[:,0],pd.DataFrame(_predict_proba)],axis=1)\n",
    "        return x_predict\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    # train()\n",
    "    loader=Model_Loader()\n",
    "    predict=loader.fetch_predict_value()\n",
    "    \n",
    "    test=pd.DataFrame(data =predict)\n",
    "    test.to_csv('F:/test2.csv')\n",
    "    print(predict)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}