356 lines
17 KiB
Plaintext
356 lines
17 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# nonghangzhidao_filter 说明\n",
|
|
"0. **下载地址:** [百度网盘](https://pan.baidu.com/s/1n-jT9SKkt6cwI_PjCd7i_g)\n",
|
|
"1. **数据概览:** 4万 条农业银行问答数据\n",
|
|
"2. **推荐实验:** FAQ 问答系统\n",
|
|
"3. **数据来源:** 百度知道\n",
|
|
"4. **加工处理:**\n",
|
|
" 1. 过滤了id、url、qid、reply_t、user字段\n",
|
|
" 2. 对question、reply做了脱敏处理"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"path = 'nonghangzhidao_文件夹_所在_路径'"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# 1. nonghangzhidao_filter.csv"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 加载数据"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"pd_all = pd.read_csv(path + 'nonghangzhidao_filter.csv')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 字段说明\n",
|
|
"\n",
|
|
"| 字段 | 说明 |\n",
|
|
"| ---- | ---- |\n",
|
|
"| title | 问题的标题 |\n",
|
|
"| question | 问题内容(可为空) |\n",
|
|
"| reply| 回复内容 |\n",
|
|
"| is_best| 是否为页面上显示的最佳回答 |"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"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>title</th>\n",
|
|
" <th>question</th>\n",
|
|
" <th>reply</th>\n",
|
|
" <th>is_best</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>31655</th>\n",
|
|
" <td>广东农行转账到江苏农行,几天可以到账?1月4日晚上10点多转的!</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>这么久还没有到账的话,建议查询一下是否被退回了,如果未退回的话,需要联系银行查询原因。</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>20349</th>\n",
|
|
" <td>惠水哪里有小额贷款的,而且抵押的东西能方</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>留vx..</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>20303</th>\n",
|
|
" <td>想问一下重庆分行的体检通知还有第二批吗</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>若客户申请的是农行招聘,则可以参考以下信息:1、请登录农行官网,在“关于农行”栏目下选择点击...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>18420</th>\n",
|
|
" <td>现在有什么软件借钱可以秒过的没。江湖救急</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>资料真实有效二十分钟放款</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>39804</th>\n",
|
|
" <td>想找高利贷怎么找?</td>\n",
|
|
" <td>武*那里有高利贷啊?接个几千块就行年后还?有吗</td>\n",
|
|
" <td>留你联系方式</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>23242</th>\n",
|
|
" <td>别人用建行卡往我农行卡转了20万,一天了怎么还不到账?</td>\n",
|
|
" <td>别人用建行卡往我农行卡转了20万,一天了怎么还不到账?肯定是</td>\n",
|
|
" <td>如果是昨天下午五点后就要等到中午以后</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>30656</th>\n",
|
|
" <td>我问银行了,说消不了户、只能刷掉</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>如果使用的是农行信用卡,可以致电信用卡客服40######99反馈核实一下。</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>8</th>\n",
|
|
" <td>贷的太少了,可以提前还清贷款,然后多贷点他用吗</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>建议客户选择正规渠道申请贷款,例如农行“网捷贷”。网捷贷是指农业银行向符合特定条件的农业银行...</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2961</th>\n",
|
|
" <td>银行理财和证券公司理财一样吗</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>不太一样,产品的种类风险不同</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>10837</th>\n",
|
|
" <td>农行提额喜欢刷大额是还是小额</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>老农现在是印头与时俱进哦比其他银行都大方。</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>34726</th>\n",
|
|
" <td>存折可以异地取款吗存折取钱一定要本人吗</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>农行个人活期存折支取方式里如果有凭证件支取,此类存折必须户主本人办理;没有密码的存折只能到开...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2381</th>\n",
|
|
" <td>住房公积金可以首付么</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>不能用公积金来付首付。这个贷款是在购房付了首付款后才能给贷的,也就是说公积金使用只能是与房屋...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>21717</th>\n",
|
|
" <td>农行有银联标识的社会保障卡能开通网银吗?</td>\n",
|
|
" <td>如题</td>\n",
|
|
" <td>由农业银行发行的有银联标识的社会保障卡,上面如果有农业银行卡号的话,是可以用本人由身份证和银...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>35871</th>\n",
|
|
" <td>求告知宁*装修贷款条件有哪些</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>以建行家装贷为例:“家装贷”是建设银行所有具有装修融资服务功能的个人贷款产品,包括个人住房抵...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3417</th>\n",
|
|
" <td>重*公积金中介能代取的吗</td>\n",
|
|
" <td>重*公积金中介能代取的吗个人公积金代取</td>\n",
|
|
" <td>一般来说,公积金套现主要存在几个方面的风险:一、中介机构提取完公积金后,有可能会携款潜逃,竹...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>25763</th>\n",
|
|
" <td>农行的理财产品能买吗</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>农行理财业务与国内同业同步,迄今为止,已经形成了制度体系较为完善、系统开发不断前进、产品系列...</td>\n",
|
|
" <td>1</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>13381</th>\n",
|
|
" <td>出大事了,出大事了,急用钱,请问我</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>需要多少呢</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>7448</th>\n",
|
|
" <td>向钱贷会跑路吗?</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>不会,放心。</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2617</th>\n",
|
|
" <td>我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有影响吗</td>\n",
|
|
" <td>我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有...</td>\n",
|
|
" <td>我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有...</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>24669</th>\n",
|
|
" <td>朋友晚上8点半转账给我到现在还没到帐</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>现在外面ATM机都是24小时才到帐</td>\n",
|
|
" <td>0</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" title \\\n",
|
|
"31655 广东农行转账到江苏农行,几天可以到账?1月4日晚上10点多转的! \n",
|
|
"20349 惠水哪里有小额贷款的,而且抵押的东西能方 \n",
|
|
"20303 想问一下重庆分行的体检通知还有第二批吗 \n",
|
|
"18420 现在有什么软件借钱可以秒过的没。江湖救急 \n",
|
|
"39804 想找高利贷怎么找? \n",
|
|
"23242 别人用建行卡往我农行卡转了20万,一天了怎么还不到账? \n",
|
|
"30656 我问银行了,说消不了户、只能刷掉 \n",
|
|
"8 贷的太少了,可以提前还清贷款,然后多贷点他用吗 \n",
|
|
"2961 银行理财和证券公司理财一样吗 \n",
|
|
"10837 农行提额喜欢刷大额是还是小额 \n",
|
|
"34726 存折可以异地取款吗存折取钱一定要本人吗 \n",
|
|
"2381 住房公积金可以首付么 \n",
|
|
"21717 农行有银联标识的社会保障卡能开通网银吗? \n",
|
|
"35871 求告知宁*装修贷款条件有哪些 \n",
|
|
"3417 重*公积金中介能代取的吗 \n",
|
|
"25763 农行的理财产品能买吗 \n",
|
|
"13381 出大事了,出大事了,急用钱,请问我 \n",
|
|
"7448 向钱贷会跑路吗? \n",
|
|
"2617 我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有影响吗 \n",
|
|
"24669 朋友晚上8点半转账给我到现在还没到帐 \n",
|
|
"\n",
|
|
" question \\\n",
|
|
"31655 NaN \n",
|
|
"20349 NaN \n",
|
|
"20303 NaN \n",
|
|
"18420 NaN \n",
|
|
"39804 武*那里有高利贷啊?接个几千块就行年后还?有吗 \n",
|
|
"23242 别人用建行卡往我农行卡转了20万,一天了怎么还不到账?肯定是 \n",
|
|
"30656 NaN \n",
|
|
"8 NaN \n",
|
|
"2961 NaN \n",
|
|
"10837 NaN \n",
|
|
"34726 NaN \n",
|
|
"2381 NaN \n",
|
|
"21717 如题 \n",
|
|
"35871 NaN \n",
|
|
"3417 重*公积金中介能代取的吗个人公积金代取 \n",
|
|
"25763 NaN \n",
|
|
"13381 NaN \n",
|
|
"7448 NaN \n",
|
|
"2617 我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有... \n",
|
|
"24669 NaN \n",
|
|
"\n",
|
|
" reply is_best \n",
|
|
"31655 这么久还没有到账的话,建议查询一下是否被退回了,如果未退回的话,需要联系银行查询原因。 0 \n",
|
|
"20349 留vx.. 0 \n",
|
|
"20303 若客户申请的是农行招聘,则可以参考以下信息:1、请登录农行官网,在“关于农行”栏目下选择点击... 1 \n",
|
|
"18420 资料真实有效二十分钟放款 0 \n",
|
|
"39804 留你联系方式 0 \n",
|
|
"23242 如果是昨天下午五点后就要等到中午以后 0 \n",
|
|
"30656 如果使用的是农行信用卡,可以致电信用卡客服40######99反馈核实一下。 0 \n",
|
|
"8 建议客户选择正规渠道申请贷款,例如农行“网捷贷”。网捷贷是指农业银行向符合特定条件的农业银行... 0 \n",
|
|
"2961 不太一样,产品的种类风险不同 0 \n",
|
|
"10837 老农现在是印头与时俱进哦比其他银行都大方。 0 \n",
|
|
"34726 农行个人活期存折支取方式里如果有凭证件支取,此类存折必须户主本人办理;没有密码的存折只能到开... 1 \n",
|
|
"2381 不能用公积金来付首付。这个贷款是在购房付了首付款后才能给贷的,也就是说公积金使用只能是与房屋... 1 \n",
|
|
"21717 由农业银行发行的有银联标识的社会保障卡,上面如果有农业银行卡号的话,是可以用本人由身份证和银... 1 \n",
|
|
"35871 以建行家装贷为例:“家装贷”是建设银行所有具有装修融资服务功能的个人贷款产品,包括个人住房抵... 1 \n",
|
|
"3417 一般来说,公积金套现主要存在几个方面的风险:一、中介机构提取完公积金后,有可能会携款潜逃,竹... 1 \n",
|
|
"25763 农行理财业务与国内同业同步,迄今为止,已经形成了制度体系较为完善、系统开发不断前进、产品系列... 1 \n",
|
|
"13381 需要多少呢 0 \n",
|
|
"7448 不会,放心。 0 \n",
|
|
"2617 我想开通农业掌上银行提示要开通短信,可以先开通短信把掌上银行开通后,取消短信服务吗?对其他有... 0 \n",
|
|
"24669 现在外面ATM机都是24小时才到帐 0 "
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"pd_all.sample(n=20)"
|
|
]
|
|
},
|
|
{
|
|
"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
|
|
}
|