|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "metadata": { |
| 7 | + "collapsed": true |
| 8 | + }, |
| 9 | + "outputs": [], |
| 10 | + "source": [ |
| 11 | + "# -*- coding:utf-8 -*-\n", |
| 12 | + "# 属性规约：确定模型构建中需要的属性\n", |
| 13 | + "import pandas as pd\n", |
| 14 | + "import numpy as np\n", |
| 15 | + "from pandas import Series,DataFrame\n", |
| 16 | + "from sqlalchemy import create_engine\n", |
| 17 | + "import MySQLdb as msd" |
| 18 | + ] |
| 19 | + }, |
| 20 | + { |
| 21 | + "cell_type": "code", |
| 22 | + "execution_count": null, |
| 23 | + "metadata": {}, |
| 24 | + "outputs": [ |
| 25 | + { |
| 26 | + "name": "stderr", |
| 27 | + "output_type": "stream", |
| 28 | + "text": [ |
| 29 | + "D:\\Anaconda2\\lib\\site-packages\\pymysql-0.7.11-py2.7.egg\\pymysql\\cursors.py:165: Warning: (1366, u\"Incorrect string value: '\\\\xD6\\\\xD0\\\\xB9\\\\xFA\\\\xB1\\\\xEA...' for column 'VARIABLE_VALUE' at row 480\")\n", |
| 30 | + " result = self._query(query)\n", |
| 31 | + "D:\\Anaconda2\\lib\\site-packages\\pandas\\io\\sql.py:1168: UserWarning: The provided table name 'Allformodel_realIP' is not found exactly as such in the database after writing the table, possibly due to case sensitivity issues. Consider using lower case table names.\n", |
| 32 | + " warnings.warn(msg, UserWarning)\n" |
| 33 | + ] |
| 34 | + } |
| 35 | + ], |
| 36 | + "source": [ |
| 37 | + "engine = create_engine('mysql+pymysql://root:@127.0.0.1:3306/jing?charset=utf8')\n", |
| 38 | + "sql = pd.read_sql('changed_six', engine, chunksize = 10000)\n", |
| 39 | + "\n", |
| 40 | + "for i in sql:\n", |
| 41 | + " j = i[['realIP','fullURL']].copy()\n", |
| 42 | + " j.to_sql('Allformodel_realIP', engine, index=False,if_exists = 'append')\n" |
| 43 | + ] |
| 44 | + }, |
| 45 | + { |
| 46 | + "cell_type": "code", |
| 47 | + "execution_count": null, |
| 48 | + "metadata": {}, |
| 49 | + "outputs": [], |
| 50 | + "source": [ |
| 51 | + "# 获取后续建模需要的数据 咨询（ask）和婚姻（hunyin）数据\n", |
| 52 | + "# 读取数据库数据 \n", |
| 53 | + "engine = create_engine('mysql+pymysql://root:@127.0.0.1:3306/jing?charset=utf8')\n", |
| 54 | + "sql = pd.read_sql('changed_six', engine, chunksize = 10000)\n", |
| 55 | + "l1 = 0\n", |
| 56 | + "l2 = 0\n", |
| 57 | + "for i in sql:\n", |
| 58 | + " zixun = i[['realIP','fullURL']][i['fullURL'].str.contains('(ask)|(askzt)')].copy()\n", |
| 59 | + "# l1 = len(zixun) + l1\n", |
| 60 | + " hunyin = i[['realIP','fullURL']][i['fullURL'].str.contains('hunyin')].copy() \n", |
| 61 | + "# l2 = len(hunyin) + l2\n", |
| 62 | + " zixun.to_sql('zixunformodel', engine, index=False,if_exists = 'append')\n", |
| 63 | + " hunyin.to_sql('hunyinformodel', engine, index=False,if_exists = 'append')\n", |
| 64 | + "# print l1,l2" |
| 65 | + ] |
| 66 | + }, |
| 67 | + { |
| 68 | + "cell_type": "code", |
| 69 | + "execution_count": null, |
| 70 | + "metadata": { |
| 71 | + "collapsed": true |
| 72 | + }, |
| 73 | + "outputs": [], |
| 74 | + "source": [] |
| 75 | + } |
| 76 | + ], |
| 77 | + "metadata": { |
| 78 | + "kernelspec": { |
| 79 | + "display_name": "Python 2", |
| 80 | + "language": "python", |
| 81 | + "name": "python2" |
| 82 | + }, |
| 83 | + "language_info": { |
| 84 | + "codemirror_mode": { |
| 85 | + "name": "ipython", |
| 86 | + "version": 2 |
| 87 | + }, |
| 88 | + "file_extension": ".py", |
| 89 | + "mimetype": "text/x-python", |
| 90 | + "name": "python", |
| 91 | + "nbconvert_exporter": "python", |
| 92 | + "pygments_lexer": "ipython2", |
| 93 | + "version": "2.7.13" |
| 94 | + } |
| 95 | + }, |
| 96 | + "nbformat": 4, |
| 97 | + "nbformat_minor": 2 |
| 98 | +} |
0 commit comments