Files
F6--/其它系统脚本/期初材料属性清洗数据分析.ipynb
T
2026-01-30 11:28:35 +08:00

1301 lines
49 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pandas as pd\n",
"\n",
"all_files = []\n",
"for root, dirs, files in os.walk(r\"C:\\Users\\admin\\Desktop\\数据清洗\"):\n",
" for file in files:\n",
" if file.endswith('.xlsx') or file.endswith('.xls'):\n",
" all_files.append(os.path.join(root, file))\n",
"\n",
"merged_data = pd.DataFrame()\n",
"for file in all_files:\n",
" data = pd.read_excel(file)\n",
" merged_data = merged_data._append(data, ignore_index=True)\n",
"\n",
"merged_data"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"merged_data_copy = merged_data.copy()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"df_unique = merged_data_copy.drop_duplicates(subset=['材料名称', '品牌', '零件号', '规格型号', '材料编码', '康众编码', '[云材料反馈2'])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: []\n",
"Index: []"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged_data_copy"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"df_yun = pd.read_excel(r\"C:\\Users\\admin\\Desktop\\云材料明细2022-11-15 11-22-50完整.xlsx\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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>Unnamed: 0</th>\n",
" <th>材料编码</th>\n",
" <th>材料名称</th>\n",
" <th>品牌</th>\n",
" <th>材料分类</th>\n",
" <th>零件号</th>\n",
" <th>单位</th>\n",
" <th>业务分类</th>\n",
" <th>oe</th>\n",
" <th>Unnamed: 9</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>91029</td>\n",
" <td>燃油滤清器密封罩</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>A0009981122</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>000 998 11 22</td>\n",
" <td>原厂A0009981122</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>95027</td>\n",
" <td>燃油滤清器支架</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>16127231598</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>1612 7231 598</td>\n",
" <td>原厂16127231598</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>95353</td>\n",
" <td>汽油滤芯上盖</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>A1644700230</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>164 470 02 30</td>\n",
" <td>原厂A1644700230</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>107559</td>\n",
" <td>刹车盘通风口(不分前后)</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>51747180624</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>5174 7180 624</td>\n",
" <td>原厂51747180624</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>107576</td>\n",
" <td>刹车盘通风口(不分前后)</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>51747210486</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>5174 7210 486</td>\n",
" <td>原厂51747210486</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540115</th>\n",
" <td>267324</td>\n",
" <td>705443</td>\n",
" <td>前杠通风口</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>31455707</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>31455707</td>\n",
" <td>原厂31455707</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540116</th>\n",
" <td>267379</td>\n",
" <td>706006</td>\n",
" <td>前杠下饰板</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>T2R3562</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>T2R3562</td>\n",
" <td>原厂T2R3562</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540117</th>\n",
" <td>267583</td>\n",
" <td>716406</td>\n",
" <td>前保险杠</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>39841777</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>39841777</td>\n",
" <td>原厂39841777</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540118</th>\n",
" <td>267601</td>\n",
" <td>722335</td>\n",
" <td>前杠支架</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>A2466280229</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>246 628 02 29</td>\n",
" <td>原厂A2466280229</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540119</th>\n",
" <td>267685</td>\n",
" <td>726500</td>\n",
" <td>前杠下饰板</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>LR099377</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>LR099377</td>\n",
" <td>原厂LR099377</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>540120 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 材料编码 材料名称 品牌 材料分类 零件号 单位 业务分类 \n",
"0 0 91029 燃油滤清器密封罩 原厂 车身附件 A0009981122 只 维修 \\\n",
"1 1 95027 燃油滤清器支架 原厂 车身附件 16127231598 只 维修 \n",
"2 2 95353 汽油滤芯上盖 原厂 车身附件 A1644700230 只 维修 \n",
"3 3 107559 刹车盘通风口(不分前后) 原厂 车身附件 51747180624 只 维修 \n",
"4 4 107576 刹车盘通风口(不分前后) 原厂 车身附件 51747210486 只 维修 \n",
"... ... ... ... .. ... ... .. ... \n",
"540115 267324 705443 前杠通风口 原厂 保险杠 31455707 个 维修 \n",
"540116 267379 706006 前杠下饰板 原厂 保险杠 T2R3562 个 维修 \n",
"540117 267583 716406 前保险杠 原厂 保险杠 39841777 个 维修 \n",
"540118 267601 722335 前杠支架 原厂 保险杠 A2466280229 个 维修 \n",
"540119 267685 726500 前杠下饰板 原厂 保险杠 LR099377 个 维修 \n",
"\n",
" oe Unnamed: 9 \n",
"0 000 998 11 22 原厂A0009981122 \n",
"1 1612 7231 598 原厂16127231598 \n",
"2 164 470 02 30 原厂A1644700230 \n",
"3 5174 7180 624 原厂51747180624 \n",
"4 5174 7210 486 原厂51747210486 \n",
"... ... ... \n",
"540115 31455707 原厂31455707 \n",
"540116 T2R3562 原厂T2R3562 \n",
"540117 39841777 原厂39841777 \n",
"540118 246 628 02 29 原厂A2466280229 \n",
"540119 LR099377 原厂LR099377 \n",
"\n",
"[540120 rows x 10 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_yun"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"<ipython-input-24-307bc15a8aa2>:3: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_unique['Unnamed: 9'] = df_unique['品牌'] + df_unique['零件号']\n"
]
}
],
"source": [
"df_unique\n",
"# 创建新的列C,内容是列A和列B的内容的拼接\n",
"df_unique['Unnamed: 9'] = df_unique['品牌'] + df_unique['零件号']"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# 通过A列进行匹配\n",
"result = pd.merge(df_unique, df_yun, on='Unnamed: 9')"
]
},
{
"cell_type": "code",
"execution_count": null,
"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>[云材料反馈1</th>\n",
" <th>材料名称_x</th>\n",
" <th>品牌_x</th>\n",
" <th>零件号_x</th>\n",
" <th>规格型号</th>\n",
" <th>材料编码_x</th>\n",
" <th>材料长码(更新导入使用,勿动)</th>\n",
" <th>康众编码</th>\n",
" <th>[云材料反馈2</th>\n",
" <th>Unnamed: 9</th>\n",
" <th>Unnamed: 0</th>\n",
" <th>材料编码_y</th>\n",
" <th>材料名称_y</th>\n",
" <th>品牌_y</th>\n",
" <th>材料分类</th>\n",
" <th>零件号_y</th>\n",
" <th>单位</th>\n",
" <th>业务分类</th>\n",
" <th>oe</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>自动变速箱油1L(贝尔)8SP</td>\n",
" <td>贝尔</td>\n",
" <td>8SP</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>93</td>\n",
" <td>1131393</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>贝尔8SP</td>\n",
" <td>497445</td>\n",
" <td>1131393</td>\n",
" <td>ATF 8SP 1L</td>\n",
" <td>贝尔</td>\n",
" <td>自动变速箱油</td>\n",
" <td>8SP</td>\n",
" <td>桶</td>\n",
" <td>保养</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>自动变速箱油1L(贝尔)722.9</td>\n",
" <td>贝尔</td>\n",
" <td>ATF-722.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>96</td>\n",
" <td>1131400</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>贝尔ATF-722.9</td>\n",
" <td>497452</td>\n",
" <td>1131400</td>\n",
" <td>ATF 722.9 1L</td>\n",
" <td>贝尔</td>\n",
" <td>自动变速箱油</td>\n",
" <td>ATF-722.9</td>\n",
" <td>桶</td>\n",
" <td>保养</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>火花塞6643NGK</td>\n",
" <td>NGK</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>469</td>\n",
" <td>022349</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>NGKLZKAR6AP-11</td>\n",
" <td>258388</td>\n",
" <td>22349</td>\n",
" <td>单铂金火花塞</td>\n",
" <td>NGK</td>\n",
" <td>火花塞</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>支</td>\n",
" <td>保养</td>\n",
" <td>24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>[云材料反馈_曹伟_2023-06-14 14-08-51_C_Users_admin_De...</td>\n",
" <td>原厂系列-单铂金火花塞</td>\n",
" <td>NGK</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>NaN</td>\n",
" <td>022349</td>\n",
" <td>4195</td>\n",
" <td>022349</td>\n",
" <td>[云材料反馈_曹伟_2023-06-14</td>\n",
" <td>NGKLZKAR6AP-11</td>\n",
" <td>258388</td>\n",
" <td>22349</td>\n",
" <td>单铂金火花塞</td>\n",
" <td>NGK</td>\n",
" <td>火花塞</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>支</td>\n",
" <td>保养</td>\n",
" <td>24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>[云材料反馈_陈晨_2023-06-26 21-19-52_C_Users_小晨_Deskt...</td>\n",
" <td>原厂系列-单铂金火花塞</td>\n",
" <td>NGK</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>214</td>\n",
" <td>022349</td>\n",
" <td>[云材料反馈_陈晨_2023-06-26</td>\n",
" <td>NGKLZKAR6AP-11</td>\n",
" <td>258388</td>\n",
" <td>22349</td>\n",
" <td>单铂金火花塞</td>\n",
" <td>NGK</td>\n",
" <td>火花塞</td>\n",
" <td>LZKAR6AP-11</td>\n",
" <td>支</td>\n",
" <td>保养</td>\n",
" <td>24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124249</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>膨胀阀总成</td>\n",
" <td>原厂</td>\n",
" <td>6461K0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1388</td>\n",
" <td>37696886</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂6461K0</td>\n",
" <td>31362</td>\n",
" <td>37696886</td>\n",
" <td>空调膨胀阀</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>6461K0</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>6461K0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124250</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>卡环20X18.3-2</td>\n",
" <td>原厂</td>\n",
" <td>697929</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1494</td>\n",
" <td>37699219</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂697929</td>\n",
" <td>33391</td>\n",
" <td>37699219</td>\n",
" <td>止动环</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>697929</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>697929</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124251</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>(MUL)支架</td>\n",
" <td>原厂</td>\n",
" <td>7104GT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1531</td>\n",
" <td>37699559</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂7104GT</td>\n",
" <td>33454</td>\n",
" <td>37699559</td>\n",
" <td>风扇支架固定架</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>7104GT</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>7104GT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124252</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>双头螺柱</td>\n",
" <td>原厂</td>\n",
" <td>793475</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1785</td>\n",
" <td>38235077</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂793475</td>\n",
" <td>79982</td>\n",
" <td>38235077</td>\n",
" <td>螺柱</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>793475</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>793475</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124253</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>三元催化器排气管</td>\n",
" <td>原厂</td>\n",
" <td>9809154080</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4093</td>\n",
" <td>88320636</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂9809154080</td>\n",
" <td>29517</td>\n",
" <td>88320636</td>\n",
" <td>三元催化器</td>\n",
" <td>原厂</td>\n",
" <td>发动机系统</td>\n",
" <td>9809154080</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>124254 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" [云材料反馈1 材料名称_x \n",
"0 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 自动变速箱油1L(贝尔)8SP \\\n",
"1 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 自动变速箱油1L(贝尔)722.9 \n",
"2 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 火花塞6643NGK \n",
"3 [云材料反馈_曹伟_2023-06-14 14-08-51_C_Users_admin_De... 原厂系列-单铂金火花塞 \n",
"4 [云材料反馈_陈晨_2023-06-26 21-19-52_C_Users_小晨_Deskt... 原厂系列-单铂金火花塞 \n",
"... ... ... \n",
"124249 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 膨胀阀总成 \n",
"124250 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 卡环20X18.3-2 \n",
"124251 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... (MUL)支架 \n",
"124252 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 双头螺柱 \n",
"124253 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 三元催化器排气管 \n",
"\n",
" 品牌_x 零件号_x 规格型号 材料编码_x 材料长码(更新导入使用,勿动) 康众编码 \n",
"0 贝尔 8SP NaN NaN 93 1131393 \\\n",
"1 贝尔 ATF-722.9 NaN NaN 96 1131400 \n",
"2 NGK LZKAR6AP-11 NaN NaN 469 022349 \n",
"3 NGK LZKAR6AP-11 NaN 022349 4195 022349 \n",
"4 NGK LZKAR6AP-11 NaN NaN 214 022349 \n",
"... ... ... ... ... ... ... \n",
"124249 原厂 6461K0 NaN NaN 1388 37696886 \n",
"124250 原厂 697929 NaN NaN 1494 37699219 \n",
"124251 原厂 7104GT NaN NaN 1531 37699559 \n",
"124252 原厂 793475 NaN NaN 1785 38235077 \n",
"124253 原厂 9809154080 NaN NaN 4093 88320636 \n",
"\n",
" [云材料反馈2 Unnamed: 9 Unnamed: 0 材料编码_y \n",
"0 [云材料反馈_曹伟_2023-02-28 贝尔8SP 497445 1131393 \\\n",
"1 [云材料反馈_曹伟_2023-02-28 贝尔ATF-722.9 497452 1131400 \n",
"2 [云材料反馈_曹伟_2023-02-28 NGKLZKAR6AP-11 258388 22349 \n",
"3 [云材料反馈_曹伟_2023-06-14 NGKLZKAR6AP-11 258388 22349 \n",
"4 [云材料反馈_陈晨_2023-06-26 NGKLZKAR6AP-11 258388 22349 \n",
"... ... ... ... ... \n",
"124249 [云材料反馈_赵旭伟_2023-11-10 原厂6461K0 31362 37696886 \n",
"124250 [云材料反馈_赵旭伟_2023-11-10 原厂697929 33391 37699219 \n",
"124251 [云材料反馈_赵旭伟_2023-11-10 原厂7104GT 33454 37699559 \n",
"124252 [云材料反馈_赵旭伟_2023-11-10 原厂793475 79982 38235077 \n",
"124253 [云材料反馈_赵旭伟_2023-11-10 原厂9809154080 29517 88320636 \n",
"\n",
" 材料名称_y 品牌_y 材料分类 零件号_y 单位 业务分类 \n",
"0 ATF 8SP 1L 贝尔 自动变速箱油 8SP 桶 保养 \\\n",
"1 ATF 722.9 1L 贝尔 自动变速箱油 ATF-722.9 桶 保养 \n",
"2 单铂金火花塞 NGK 火花塞 LZKAR6AP-11 支 保养 \n",
"3 单铂金火花塞 NGK 火花塞 LZKAR6AP-11 支 保养 \n",
"4 单铂金火花塞 NGK 火花塞 LZKAR6AP-11 支 保养 \n",
"... ... ... ... ... .. ... \n",
"124249 空调膨胀阀 原厂 车身附件 6461K0 个 维修 \n",
"124250 止动环 原厂 车身附件 697929 个 维修 \n",
"124251 风扇支架固定架 原厂 车身附件 7104GT 个 维修 \n",
"124252 螺柱 原厂 车身附件 793475 个 维修 \n",
"124253 三元催化器 原厂 发动机系统 9809154080 个 维修 \n",
"\n",
" oe \n",
"0 NaN \n",
"1 NaN \n",
"2 24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1... \n",
"3 24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1... \n",
"4 24401-ED51A,24401-ED51B,24401-ED71B,22401-1HC1... \n",
"... ... \n",
"124249 6461K0 \n",
"124250 697929 \n",
"124251 7104GT \n",
"124252 793475 \n",
"124253 NaN \n",
"\n",
"[124254 rows x 19 columns]"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 总数据:2006992条、原124254条标准数据、最终373906条标准数据:原标准率6.19% 最终18.63% 提升:12.43%"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 124254条标准数据"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"filtered_df = df_unique[df_unique['康众编码'].notna()]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 373906条标准数据"
]
},
{
"cell_type": "code",
"execution_count": 29,
"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>[云材料反馈1</th>\n",
" <th>材料名称</th>\n",
" <th>品牌</th>\n",
" <th>零件号</th>\n",
" <th>规格型号</th>\n",
" <th>材料编码</th>\n",
" <th>材料长码(更新导入使用,勿动)</th>\n",
" <th>康众编码</th>\n",
" <th>[云材料反馈2</th>\n",
" <th>Unnamed: 9</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>[云材料反馈_曹伟_2023-02-09 16-26-29]Sheet1</td>\n",
" <td>点火线圈</td>\n",
" <td>DELPHI(德尔福)</td>\n",
" <td>GN10571-18B1</td>\n",
" <td>36/包</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>82334350</td>\n",
" <td>[云材料反馈_曹伟_2023-02-09</td>\n",
" <td>DELPHI(德尔福)GN10571-18B1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>材料名称</td>\n",
" <td>品牌</td>\n",
" <td>零件号</td>\n",
" <td>规格型号</td>\n",
" <td>材料编码</td>\n",
" <td>材料长码(更新导入使用,勿动)</td>\n",
" <td>康众编码</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>品牌零件号</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>防冻液4kg(欧洲维修)红色</td>\n",
" <td>欧洲维修</td>\n",
" <td>-25度</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>115</td>\n",
" <td>88500786</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>欧洲维修-25度</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>防冻液4kg(欧洲维修)绿色</td>\n",
" <td>欧洲维修</td>\n",
" <td>-25度</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>116</td>\n",
" <td>88500786</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>欧洲维修-25度</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>[云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1</td>\n",
" <td>油底螺丝528013(途曼)</td>\n",
" <td>NaN</td>\n",
" <td>528013</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>184</td>\n",
" <td>056698</td>\n",
" <td>[云材料反馈_曹伟_2023-02-28</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006987</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>膨胀阀总成</td>\n",
" <td>原厂</td>\n",
" <td>6461K0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1388</td>\n",
" <td>37696886</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂6461K0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006988</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>卡环20X18.3-2</td>\n",
" <td>原厂</td>\n",
" <td>697929</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1494</td>\n",
" <td>37699219</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂697929</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006989</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>(MUL)支架</td>\n",
" <td>原厂</td>\n",
" <td>7104GT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1531</td>\n",
" <td>37699559</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂7104GT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006990</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>双头螺柱</td>\n",
" <td>原厂</td>\n",
" <td>793475</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1785</td>\n",
" <td>38235077</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂793475</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006991</th>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D...</td>\n",
" <td>三元催化器排气管</td>\n",
" <td>原厂</td>\n",
" <td>9809154080</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4093</td>\n",
" <td>88320636</td>\n",
" <td>[云材料反馈_赵旭伟_2023-11-10</td>\n",
" <td>原厂9809154080</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>373906 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" [云材料反馈1 材料名称 \n",
"0 [云材料反馈_曹伟_2023-02-09 16-26-29]Sheet1 点火线圈 \\\n",
"1 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 材料名称 \n",
"2 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 防冻液4kg(欧洲维修)红色 \n",
"3 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 防冻液4kg(欧洲维修)绿色 \n",
"4 [云材料反馈_曹伟_2023-02-28 13-32-30]Sheet1 油底螺丝528013(途曼) \n",
"... ... ... \n",
"2006987 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 膨胀阀总成 \n",
"2006988 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 卡环20X18.3-2 \n",
"2006989 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... (MUL)支架 \n",
"2006990 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 双头螺柱 \n",
"2006991 [云材料反馈_赵旭伟_2023-11-10 15-14-05_C_Users_86139_D... 三元催化器排气管 \n",
"\n",
" 品牌 零件号 规格型号 材料编码 材料长码(更新导入使用,勿动) 康众编码 \n",
"0 DELPHI(德尔福) GN10571-18B1 36/包 NaN 1 82334350 \\\n",
"1 品牌 零件号 规格型号 材料编码 材料长码(更新导入使用,勿动) 康众编码 \n",
"2 欧洲维修 -25度 NaN NaN 115 88500786 \n",
"3 欧洲维修 -25度 NaN NaN 116 88500786 \n",
"4 NaN 528013 NaN NaN 184 056698 \n",
"... ... ... ... ... ... ... \n",
"2006987 原厂 6461K0 NaN NaN 1388 37696886 \n",
"2006988 原厂 697929 NaN NaN 1494 37699219 \n",
"2006989 原厂 7104GT NaN NaN 1531 37699559 \n",
"2006990 原厂 793475 NaN NaN 1785 38235077 \n",
"2006991 原厂 9809154080 NaN NaN 4093 88320636 \n",
"\n",
" [云材料反馈2 Unnamed: 9 \n",
"0 [云材料反馈_曹伟_2023-02-09 DELPHI(德尔福)GN10571-18B1 \n",
"1 [云材料反馈_曹伟_2023-02-28 品牌零件号 \n",
"2 [云材料反馈_曹伟_2023-02-28 欧洲维修-25度 \n",
"3 [云材料反馈_曹伟_2023-02-28 欧洲维修-25度 \n",
"4 [云材料反馈_曹伟_2023-02-28 NaN \n",
"... ... ... \n",
"2006987 [云材料反馈_赵旭伟_2023-11-10 原厂6461K0 \n",
"2006988 [云材料反馈_赵旭伟_2023-11-10 原厂697929 \n",
"2006989 [云材料反馈_赵旭伟_2023-11-10 原厂7104GT \n",
"2006990 [云材料反馈_赵旭伟_2023-11-10 原厂793475 \n",
"2006991 [云材料反馈_赵旭伟_2023-11-10 原厂9809154080 \n",
"\n",
"[373906 rows x 10 columns]"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered_df"
]
},
{
"cell_type": "code",
"execution_count": 22,
"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>Unnamed: 0</th>\n",
" <th>材料编码</th>\n",
" <th>材料名称</th>\n",
" <th>品牌</th>\n",
" <th>材料分类</th>\n",
" <th>零件号</th>\n",
" <th>单位</th>\n",
" <th>业务分类</th>\n",
" <th>oe</th>\n",
" <th>Unnamed: 9</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>91029</td>\n",
" <td>燃油滤清器密封罩</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>A0009981122</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>000 998 11 22</td>\n",
" <td>原厂A0009981122</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>95027</td>\n",
" <td>燃油滤清器支架</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>16127231598</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>1612 7231 598</td>\n",
" <td>原厂16127231598</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>95353</td>\n",
" <td>汽油滤芯上盖</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>A1644700230</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>164 470 02 30</td>\n",
" <td>原厂A1644700230</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>107559</td>\n",
" <td>刹车盘通风口(不分前后)</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>51747180624</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>5174 7180 624</td>\n",
" <td>原厂51747180624</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>107576</td>\n",
" <td>刹车盘通风口(不分前后)</td>\n",
" <td>原厂</td>\n",
" <td>车身附件</td>\n",
" <td>51747210486</td>\n",
" <td>只</td>\n",
" <td>维修</td>\n",
" <td>5174 7210 486</td>\n",
" <td>原厂51747210486</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540115</th>\n",
" <td>267324</td>\n",
" <td>705443</td>\n",
" <td>前杠通风口</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>31455707</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>31455707</td>\n",
" <td>原厂31455707</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540116</th>\n",
" <td>267379</td>\n",
" <td>706006</td>\n",
" <td>前杠下饰板</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>T2R3562</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>T2R3562</td>\n",
" <td>原厂T2R3562</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540117</th>\n",
" <td>267583</td>\n",
" <td>716406</td>\n",
" <td>前保险杠</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>39841777</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>39841777</td>\n",
" <td>原厂39841777</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540118</th>\n",
" <td>267601</td>\n",
" <td>722335</td>\n",
" <td>前杠支架</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>A2466280229</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>246 628 02 29</td>\n",
" <td>原厂A2466280229</td>\n",
" </tr>\n",
" <tr>\n",
" <th>540119</th>\n",
" <td>267685</td>\n",
" <td>726500</td>\n",
" <td>前杠下饰板</td>\n",
" <td>原厂</td>\n",
" <td>保险杠</td>\n",
" <td>LR099377</td>\n",
" <td>个</td>\n",
" <td>维修</td>\n",
" <td>LR099377</td>\n",
" <td>原厂LR099377</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>540120 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 材料编码 材料名称 品牌 材料分类 零件号 单位 业务分类 \n",
"0 0 91029 燃油滤清器密封罩 原厂 车身附件 A0009981122 只 维修 \\\n",
"1 1 95027 燃油滤清器支架 原厂 车身附件 16127231598 只 维修 \n",
"2 2 95353 汽油滤芯上盖 原厂 车身附件 A1644700230 只 维修 \n",
"3 3 107559 刹车盘通风口(不分前后) 原厂 车身附件 51747180624 只 维修 \n",
"4 4 107576 刹车盘通风口(不分前后) 原厂 车身附件 51747210486 只 维修 \n",
"... ... ... ... .. ... ... .. ... \n",
"540115 267324 705443 前杠通风口 原厂 保险杠 31455707 个 维修 \n",
"540116 267379 706006 前杠下饰板 原厂 保险杠 T2R3562 个 维修 \n",
"540117 267583 716406 前保险杠 原厂 保险杠 39841777 个 维修 \n",
"540118 267601 722335 前杠支架 原厂 保险杠 A2466280229 个 维修 \n",
"540119 267685 726500 前杠下饰板 原厂 保险杠 LR099377 个 维修 \n",
"\n",
" oe Unnamed: 9 \n",
"0 000 998 11 22 原厂A0009981122 \n",
"1 1612 7231 598 原厂16127231598 \n",
"2 164 470 02 30 原厂A1644700230 \n",
"3 5174 7180 624 原厂51747180624 \n",
"4 5174 7210 486 原厂51747210486 \n",
"... ... ... \n",
"540115 31455707 原厂31455707 \n",
"540116 T2R3562 原厂T2R3562 \n",
"540117 39841777 原厂39841777 \n",
"540118 246 628 02 29 原厂A2466280229 \n",
"540119 LR099377 原厂LR099377 \n",
"\n",
"[540120 rows x 10 columns]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_yun"
]
},
{
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: []\n",
"Index: []"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_unique"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "F6processing",
"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": "3.9.4"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}