{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from utils.gtools import MySQLconnect\n",
    "categories = '94 - Office Desks'\n",
    "with MySQLconnect('ods') as db:\n",
    "    engine = db.engine()\n",
    "    sql = f\"\"\"\n",
    "WITH a AS (\n",
    "\tSELECT\n",
    "\t\tt1.SPU,\n",
    "\t\tt2.SKU,\n",
    "\t\tt1.产品分类,\n",
    "\t\tt1.添加时间,\n",
    "\t\torder_date,\n",
    "\t\tt2.成本价,\n",
    "\t\topl.product_price_dollar,\n",
    "\t\topl.product_num,\n",
    "\t\tTIMESTAMPDIFF( MONTH, t1.添加时间, order_date ) AS month_diff \n",
    "\tFROM\n",
    "\t\tods.stg_bayshop_litfad_spu t1\n",
    "\t\tLEFT JOIN ods.stg_bayshop_litfad_sku t2 ON t2.产品PID = t1.产品PID\n",
    "\t\tLEFT JOIN dws.order_product_list opl ON t2.SKU = opl.SKU \n",
    "\tWHERE\n",
    "\t\tt1.添加时间 BETWEEN '2023-01-01' \n",
    "\t\tAND '2024-12-31 23:59:59' \n",
    "\t\tAND 产品分类 = '{categories}'\n",
    "\t\tAND t2.SKU IS NOT NULL \n",
    "\t),\n",
    "\tb AS (\n",
    "\tSELECT\n",
    "\t\tSPU,\n",
    "\t\tSKU,添加时间,产品分类,成本价,\n",
    "\t\tb.erp_package_vol,\n",
    "\t\torder_date,\n",
    "\tIF\n",
    "\t\t( month_diff >= 6, NULL, month_diff ) AS month_diff,\n",
    "\t\tROW_NUMBER() over ( PARTITION BY SKU ORDER BY order_date DESC ) AS ranking \n",
    "\tFROM\n",
    "\t\ta\n",
    "\t\tLEFT JOIN dwd.dim_erp_sku_package_vol_info b ON a.SKU = b.erp_sku \n",
    "\t) SELECT\n",
    "\tSPU,\n",
    "\tSKU,添加时间,产品分类,成本价,\n",
    "\tb.erp_package_vol \n",
    "FROM\n",
    "\tb \n",
    "WHERE\n",
    "\tranking = 1 \n",
    "\tAND month_diff IS NULL\n",
    "\"\"\"\n",
    "    df = pd.read_sql(sql, engine)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "得到每个SKU的最长边，围长，总重量，6000抛重，采购体积比（采购/6000抛重）"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import re\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "from sell.sell_price import call_sell_and_order_price\n",
    "def extract_number(value):\n",
    "    # 提取字符串中的第一个数字\n",
    "        match = re.search(r\"[-+]?\\d*\\.\\d+|\\d+\", str(value))\n",
    "        return float(match.group()) if match else 0.0\n",
    "for index, row in df.iterrows():\n",
    "    package_dict = json.loads(row['erp_package_vol'])\n",
    "    max_length = 0 # 最长边\n",
    "    max_girth = 0 # 最大围长\n",
    "    all_weight = 0 # 总重量\n",
    "    all_vol_weight = 0 # 总抛重\n",
    "    for key, package in package_dict.items():\n",
    "        package['长'] = extract_number(package['长'])\n",
    "        package['宽'] = extract_number(package['宽'])\n",
    "        package['高'] = extract_number(package['高'])\n",
    "        package['重量'] = extract_number(package['重量'])\n",
    "        size =sorted([package['长'],package['宽'],package['高']])\n",
    "        fst_size = size[2]\n",
    "        snd_size = size[1]\n",
    "        thd_size = size[0]\n",
    "        max_length=max(max_length,fst_size)\n",
    "        max_girth=max(max_girth,fst_size+(snd_size+thd_size)*2)\n",
    "        all_weight+=package['重量']/1000\n",
    "        all_vol_weight+=package['长']*package['宽']*package['高']/6000\n",
    "    sell_price,order_price,order_type = call_sell_and_order_price(row['成本价'], row['erp_package_vol'],\"海运\")\n",
    "    df.loc[index,'网站售价'] = sell_price[0]\n",
    "    df.loc[index,'物流分摊费'] = sell_price[1]\n",
    "    df.loc[index,'订单物流费'] = order_price\n",
    "    df.loc[index,'尾端类型'] = order_type\n",
    "    df.loc[index,'最长边'] = max_length\n",
    "    df.loc[index,'最大围长'] = max_girth\n",
    "    df.loc[index,'总重量'] = all_weight\n",
    "    df.loc[index,'总抛重'] = all_vol_weight\n",
    "    print(index)\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 按照那个分组，按照总抛重，每5总抛重为一组，最长边取大，最短边取小，最大实重取大，最小实重取小，网站售价求和，物流分摊费求和，订单物流费求和，尾端类型不要，\n",
    "cost_bins = list(range(0, 4000, 10)) +[28700]\n",
    "df['成本价分组'] = pd.cut(df['成本价'], bins=cost_bins, right=True, labels=cost_bins[1:])\n",
    "\n",
    "# 2. 总抛重分组（按5为一组，0-5 为一组，5.01-10 为一组，等）\n",
    "df['总抛重分组'] = (np.ceil(df['总抛重'] / 5) * 5).astype(int)\n",
    "df = df.dropna(subset=['成本价分组'])\n",
    "# 3. 分组聚合\n",
    "agg_df = df.groupby(['成本价分组', '总抛重分组'], observed=True).agg({\n",
    "    '最长边': ['max', 'min'],      # 每组最大 每组最小\n",
    "    '最大围长': 'max',\n",
    "    '总重量': ['max', 'min','sum'],  # 分别取最大/最小实重\n",
    "    '网站售价': 'sum',\n",
    "    '物流分摊费': 'sum',\n",
    "    '订单物流费': 'sum',\n",
    "    'SKU': 'count'\n",
    "}).reset_index()\n",
    "\n",
    "# 4. 重命名列\n",
    "agg_df.columns = [\n",
    "    '成本价分组', '总抛重分组',\n",
    "    '最长边max', '最长边min', '最大围长',\n",
    "    '总重量max', '总重量min','总重量',\n",
    "    '网站售价', '物流分摊费', '订单物流费','SKU种类'\n",
    "]\n",
    "agg_df.to_clipboard(index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}