{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "取数据,SKU多次订单的情况下取最新的订单数据" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from utils.gtools import MySQLconnect\n", "\n", "# 读取需要计算的包裹信息\n", "with MySQLconnect('ods') as db:\n", " sql = r\"\"\" \n", " # 限制范围是测量时间，取得SKU种类为1且数量为1的订单，且重复SKU只取最近的订单\n", "# 测量时间D +2 天进行汇总数据\n", "# 订单汇总产品数和取出\n", "WITH\n", "t1 AS (\n", "SELECT\n", "order_id,\n", "SKU,\n", "order_date,\n", "sum(CASE WHEN opl.order_product_id REGEXP \"[0-9]{15}_[0-9]*$\"\n", " THEN product_num END) AS product_num,\n", "DATE_FORMAT(order_date,\"%Y-%m-%d\") AS 订单时间,\n", "count(DISTINCT opl.SKU) AS 产品种类\n", "FROM\n", "dws.order_product_list opl\n", "WHERE\n", " NOT EXISTS (\n", " SELECT 1 \n", " FROM dws.log_order_reissue_detail AS r \n", " WHERE left(r.order_product_id,15) = opl.order_id\n", " \n", " )\n", "AND order_date >= \"2025-10-01\"\n", "AND order_date < \"2025-11-01\"\n", "AND SKU <> \"\"\n", "GROUP BY order_id\n", ")\n", ",\n", "t2 AS (\n", "SELECT \n", " a.`包裹测量时间`,\n", " t1.order_id,\n", " t1.SKU,\n", " t1.order_date,\n", " a.包裹号,\n", " a.快递公司,\n", " a.运输方式,\n", " a.`目的国`,\n", " d.postcode,\n", " CONCAT(\n", " '\"', b.package, '\": {',\n", " '\"长\": ', length, ', ',\n", " '\"宽\": ', width, ', ',\n", " '\"高\": ', hight, ', ',\n", " '\"重量\": ', weight, '}'\n", " ) AS package_json\n", " FROM\n", " t1\n", " LEFT JOIN order_express a ON t1.order_id = a.单号\n", " JOIN package_vol_info b ON a.`包裹号` = b.package\n", " JOIN order_list d ON a.`单号` = d.order_id \n", " WHERE\n", " a.`包裹状态` != '--'\n", " AND b.hight > 0 \n", " AND b.length > 0 \n", " AND b.width > 0 \n", " AND b.hight > 0 \n", " AND b.weight > 0\n", " AND t1.product_num = 1\n", " AND t1.产品种类=1\n", "-- AND a.`包裹测量时间` >= '2025-09-01'\n", "-- AND a.`包裹测量时间` < '2025-10-01'\n", "),\n", "t3 AS (\n", "SELECT\n", "t2.*,\n", "SPU,\n", "sku.成本价 AS ERP采购价,\n", "CONCAT('{', GROUP_CONCAT(package_json SEPARATOR ','), '}') AS 实际包裹数据,\n", "count(package_json) AS 包裹数,\n", "ROW_NUMBER() OVER (PARTITION BY SKU ORDER BY 包裹测量时间 DESC) as rn\n", "FROM\n", "t2\n", "LEFT JOIN stg_bayshop_litfad_sku sku ON t2.SKU=sku.SKU\n", "left JOIN stg_bayshop_litfad_spu spu ON sku.产品PID=spu.产品PID\n", "\n", "GROUP BY order_id\n", ")\n", "SELECT\n", "包裹测量时间,\n", "order_id,\n", "SPU,\n", "SKU,\n", "DATE_FORMAT(order_date,\"%Y-%m-%d\") AS 订单时间,\n", "包裹号,\n", "`快递公司`,\n", "`运输方式`,\n", "`目的国`,\n", "postcode,\n", "ERP采购价,\n", "实际包裹数据,\n", "包裹数,\n", "rn AS 从新到旧\n", "FROM\n", "t3\n", "\n", " \"\"\"\n", " df=pd.read_sql(sql,db.con)\n", " df.to_clipboard(index=False)\n", "\n", "# df=df[df['实际包裹数量']==1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 取这些SPU下的所有SKU及其现在售价" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "# from sell.sell_price import call_sell_and_order_price\n", "import json\n", "from utils.gtools import MySQLconnect\n", "import pandas as pd\n", "\n", "base_df = df[df['从新到旧']==1]\n", "spu_list = (\n", " base_df['SPU']\n", " .apply(pd.to_numeric, errors='coerce')\n", " .dropna()\n", " .astype(int)\n", " .astype(str)\n", " .drop_duplicates() # 加这一行\n", " .tolist()\n", ")\n", "\n", "def chunk_list(lst, size):\n", " for i in range(0, len(lst), size):\n", " yield lst[i:i+size]\n", "\n", "result_list = []\n", "with MySQLconnect('ods') as db:\n", " enginal = db.engine()\n", " for chunk in chunk_list(spu_list, 5000):\n", " quoted_spus = ','.join([f\"'{spu}'\" for spu in chunk]) # 加引号防止 SQL 错误\n", " sql = f\"\"\"\n", " SELECT\n", " 产品品类,\n", " 产品分类,\n", " SPU,\n", " SKU,\n", " sku.成本价,\n", " spvi.erp_package_vol AS ERP包裹数据,\n", " 物流分摊,\n", " 产品售价\n", " from stg_bayshop_litfad_spu spu \n", " LEFT JOIN stg_bayshop_litfad_sku sku ON sku.产品PID = spu.产品PID\n", " LEFT JOIN dwd.dim_erp_sku_package_vol_info spvi ON sku.SKU = spvi.erp_sku\n", " WHERE spu.SPU IN ({quoted_spus})\n", " \"\"\"\n", " df_chunk = pd.read_sql(sql, enginal)\n", " result_list.append(df_chunk)\n", " print(f\"已处理 {len(result_list) * 5000} 个SPU\")\n", "\n", "result = pd.concat(result_list, ignore_index=True)\n", "\n", "# 合并df\n", "all_df = pd.merge(result,base_df, on=['SPU','SKU'], how='left')\n", "all_df = all_df.drop_duplicates(subset=['SKU'])\n", "all_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "len(all_df[all_df['产品品类'] == \"66 - Furniture\"])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "给SPU下的SKU分层级打标签，# 按 SPU 分组；在组内按 成本价升序 排序；成本价相同的 SKU 属于同一个层次；层次号就是「第几种不同的成本价」。从小到大排序\n", " " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 取出产品品类为 66 - Furniture 的数据\n", "\n", "furniture_df = all_df[all_df['产品品类'] == \"66 - Furniture\"]\n", "# 根据品类拿到对应表的队友SKU的标准/预设属性集\n", "furniture_df['SKU'] = furniture_df['SKU'].astype(str)\n", "with MySQLconnect('ods') as ods:\n", " sku_list = furniture_df['SKU'].tolist()\n", " placeholders = ','.join(['%s'] * len(sku_list))\n", " sql = f\"\"\"\n", " SELECT SKU,`标准/预设属性集` FROM erp_furniture_sku where SKU in ({placeholders})\"\"\"\n", " sku_df = pd.read_sql(sql, ods.engine(), params=tuple(sku_list))\n", "sku_df['SKU'] = sku_df['SKU'].astype(str)\n", "# 合并数据\n", "furniture_df = pd.merge(furniture_df, sku_df, on='SKU', how='left')\n", "\n", "# \n", "furniture_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "cl_df = furniture_df.drop_duplicates(subset=['SKU'])\n", "property_df = pd.read_excel(r'D:\\\\test\\\\logistics\\\\test_excel\\\\furniture-规格属性映射.xlsx')\n", "# 筛选是否有效列为1的属性集，并以规格属性映射\t是否有效做成数据\n", "property_df = property_df[property_df['是否有效'] == 1]\n", "property_dict = {row['规格属性映射']: row['是否有效'] for index, row in property_df.iterrows()}\n", "\n", "# 属性统计\n", "def parse_attr_set(attr_set_str):\n", " \"\"\"解析属性集，返回排序后的 {属性值: 属性名} 的数据\"\"\"\n", " mapping = {}\n", " for item in attr_set_str.split(\";\"):\n", " item = item.strip()\n", " if not item:\n", " continue\n", " try:\n", " left, value = item.split(\"~\", 1) # \"231012:大小~23206184:140*80*75\"\n", " attr_name = left.split(\":\")[1]\n", " value = value.split(\":\")[1]\n", " if attr_name in property_dict.keys():\n", " # 有效属性集\n", " mapping[attr_name] = value\n", " except Exception:\n", " continue\n", " \n", " # 对数据按键进行排序，返回有序数据\n", " return dict(sorted(mapping.items()))\n", "\n", "# 1. 为每个SKU解析有效属性集并创建新列\n", "cl_df['有效属性集'] = cl_df['标准/预设属性集'].apply(\n", " lambda x: parse_attr_set(x) if pd.notna(x) else {}\n", ")\n", "\n", "# 2. 将有效属性集转换为可比较的格式（排序后的元组）\n", "cl_df['属性集签名'] = cl_df['有效属性集'].apply(\n", " lambda x: tuple(sorted(x.items())) # 转换为排序后的元组，便于比较\n", ")\n", "\n", "cl_df['分组码'] = ''\n", "\n", "for spu in cl_df['SPU'].unique():\n", " spu_indices = cl_df[cl_df['SPU'] == spu].index\n", " spu_data = cl_df.loc[spu_indices]\n", " \n", " # 按属性集签名分组\n", " signature_groups = {}\n", " group_num = 1\n", " \n", " for idx in spu_indices:\n", " signature = cl_df.loc[idx, '属性集签名']\n", " \n", " if signature not in signature_groups:\n", " signature_groups[signature] = f\"{spu}_{group_num:03d}\"\n", " group_num += 1\n", " \n", " cl_df.loc[idx, '分组码'] = signature_groups[signature]\n", "cl_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 哪几个层级有实际数据，估算其他没有数据的层级的数据\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 直接在原数据框添加组内编号\n", "cl_df['组内编号'] = cl_df.groupby('SPU')['产品售价'].rank(method='dense').astype(int)\n", "\n", "cl_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def dict_to_json_str(data_dict):\n", " \"\"\"将字典转换为JSON字符串\"\"\"\n", " if not data_dict or pd.isna(data_dict):\n", " return None\n", " try:\n", " return json.dumps(data_dict, ensure_ascii=False)\n", " except (TypeError, ValueError):\n", " return None\n", "\n", "def json_str_to_dict(json_str):\n", " \"\"\"将JSON字符串转换为字典\"\"\"\n", " if not json_str or pd.isna(json_str):\n", " return {}\n", " try:\n", " return json.loads(json_str)\n", " except (json.JSONDecodeError, TypeError):\n", " return {}" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import re\n", "def split_packages(package_dict_str):\n", " \"\"\"\n", " 处理包裹数据，按体积排序并重新排列长宽高\n", " Args:\n", " package_dict_str: 包裹数据的JSON字符串或数据\n", " \n", " Returns:\n", " dict: 排序后的包裹数据，键为1,2,3...（按体积降序）\n", " \"\"\"\n", " # 处理空值和非字符串/数据类型\n", " if package_dict_str is None or pd.isna(package_dict_str):\n", " return {}\n", " \n", " if isinstance(package_dict_str, (int, float)):\n", " return {}\n", " # 如果输入是字符串，先转换为数据\n", " if isinstance(package_dict_str, str):\n", " try:\n", " package_dict = json.loads(package_dict_str)\n", " except json.JSONDecodeError:\n", " return {}\n", " else:\n", " package_dict = package_dict_str\n", "\n", " # 提取并处理每个包裹的数据\n", " packages = []\n", " for package_name, package_data in package_dict.items():\n", " item = {}\n", " for key, value in package_data.items():\n", " try:\n", " # 使用正则表达式提取数字部分\n", " number_str = re.findall(r\"[-+]?\\d*\\.\\d+|\\d+\", str(value))\n", " if number_str:\n", " item[key] = float(number_str[0])\n", " else:\n", " item[key] = value\n", " except ValueError:\n", " item[key] = value\n", " # 确保有长宽高数据\n", " if all(k in item for k in ['长', '宽', '高']):\n", " # 将长宽高按实际尺寸重新排序：最长边作为长，次长边作为宽，最短边作为高\n", " dimensions = [item['长'], item['宽'], item['高']]\n", " dimensions.sort(reverse=True) # 降序排列\n", " # 重新赋值\n", " item['长'] = dimensions[0] # 最长边\n", " item['宽'] = dimensions[1] # 次长边\n", " item['高'] = dimensions[2] # 最短边\n", " # 计算体积\n", " item['体积'] = dimensions[0] * dimensions[1] * dimensions[2]\n", " packages.append(item)\n", " # 按体积降序排序\n", " packages.sort(key=lambda x: x.get('体积', 0), reverse=True)\n", " # 构建结果数据\n", " result = {}\n", " for i, package in enumerate(packages, 1):\n", " # 只保留长宽高和重量信息\n", " result_package = {\n", " '长': package.get('长', 0),\n", " '宽': package.get('宽', 0),\n", " '高': package.get('高', 0)\n", " }\n", " # 如果有重量信息也保留\n", " if '重量' in package:\n", " result_package['重量'] = package['重量']\n", " result[i] = result_package\n", " return dict_to_json_str(result)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 先把包裹数据拆成数据且排序\n", "result_df = cl_df.copy()\n", "for index, row in result_df.iterrows():\n", " if row['ERP包裹数据'] is not None:\n", " result_df.at[index, 'ERP包裹数据'] = split_packages(row['ERP包裹数据'])\n", " result_df.at[index, '实际包裹数据'] = split_packages(row['实际包裹数据'])\n", " print(result_df.at[index, '实际包裹数据'])\n", " else:\n", " result_df.at[index, 'ERP包裹数据'] = []\n", " result_df.at[index, '实际包裹数据'] = []\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 确保订单时间是datetime类型\n", "result_df['订单时间'] = pd.to_datetime(result_df['订单时间'])\n", "\n", "# 先找到每个SPU的最大订单时间\n", "max_order_time = result_df.groupby('SPU')['订单时间'].transform('max')\n", "\n", "# 然后设置is_first\n", "result_df['is_first'] = 0\n", "result_df.loc[result_df['实际包裹数据'].notna() & (result_df['订单时间'] == max_order_time), 'is_first'] = 1\n", "result_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 根据SPU基准SKU计算系数\n", "import numpy as np\n", "\n", "def cal_size_coefficients(erp_packages, actual_packages):\n", " \"\"\"\n", " 计算每个SPU的尺寸系数\n", " \n", " Args:\n", " erp_packages: ERP包裹数据\n", " actual_packages: 实际包裹数据\n", " Returns:\n", " dict: 尺寸系数数据\n", " \"\"\"\n", " # 检查输入是否有效\n", " if not erp_packages or not actual_packages:\n", " return {}\n", " \n", " # 获取包裹数量\n", " erp_count = len(erp_packages)\n", " actual_count = len(actual_packages)\n", " \n", " # 如果包裹数量不相等，取较小的数量\n", " min_count = min(erp_count, actual_count)\n", " \n", " coefficients = {}\n", " \n", " for i in range(1, min_count + 1):\n", " erp_pkg = erp_packages.get(str(i), {})\n", " actual_pkg = actual_packages.get(str(i), {})\n", " \n", " # 检查必要的维度是否存在\n", " if not all(k in erp_pkg for k in ['长', '宽', '高']) or not all(k in actual_pkg for k in ['长', '宽', '高']):\n", " continue\n", " \n", " pkg_coefficients = {}\n", " \n", " # 计算长宽高系数\n", " for dimension in ['长', '宽', '高']:\n", " old_val = erp_pkg.get(dimension, 0)\n", " new_val = actual_pkg.get(dimension, 0)\n", " pkg_coefficients[f'{dimension}系数'] = cal_size(old_val, new_val)\n", " \n", " # 计算重量系数（如果存在）\n", " if '重量' in erp_pkg and '重量' in actual_pkg:\n", " old_weight = erp_pkg.get('重量', 0)\n", " new_weight = actual_pkg.get('重量', 0)\n", " pkg_coefficients['重量系数'] = cal_size(old_weight, new_weight)\n", " \n", " coefficients[i] = pkg_coefficients\n", " \n", " return dict_to_json_str(coefficients)\n", "\n", "def cal_size(old, new):\n", " \"\"\"\n", " 计算单个维度的系数\n", " \"\"\"\n", " try:\n", " old = float(old)\n", " new = float(new)\n", " if old == 0:\n", " return None\n", " return (new - old) / old\n", " except (ValueError, TypeError):\n", " return None\n", "\n", "# 应用计算\n", "# 首先筛选出is_first=1的行作为基准\n", "first_rows = result_df[result_df['is_first'] == 1].copy()\n", "\n", "# 计算每个SPU的尺寸系数\n", "for index, row in first_rows.iterrows():\n", " erp_packages = json_str_to_dict(row['ERP包裹数据'])\n", " actual_packages = json_str_to_dict(row['实际包裹数据'])\n", " first_rows.at[index, '尺寸系数'] = cal_size_coefficients(erp_packages, actual_packages)\n", " print(first_rows.at[index, '尺寸系数'])\n", "\n", "# 创建SPU到尺寸系数的映射\n", "spu_coefficient_map = first_rows.set_index('SPU')['尺寸系数'].to_dict()\n", "\n", "# 将尺寸系数应用到所有相同SPU的行\n", "result_df['尺寸系数'] = result_df['SPU'].map(spu_coefficient_map)\n", "result_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\"\"\"\n", "根据SPU尺寸系数,计算预测包裹数据，\n", "1.如果分组码相同，筛选有实际数据的行，按分组码分组，在每个组内按订单时间降序排列，然后取每个组的第一条数据作为全组的估算包裹尺寸\n", "2.如果分组码不同，则按照尺寸系数计算估算包裹尺寸\n", " 2.1.如果尺寸系数为{}，则跳过\n", " 2.2.如果ERP包裹数>尺寸系数的数量，前面对应的ERP包裹根据尺寸系数计算得到新的ERP包裹尺寸（（1+尺寸系数）*ERP包裹尺寸），多出来的包裹就取ERP包裹（也可以理解为尺寸系数都是0）\n", " 2.3.如果ERP包裹数<=尺寸系数的数量，则按ERP包裹数计算估算包裹尺寸\n", "\"\"\"\n", "# 先筛选出order_id不为空的行，然后按分组码分组，在每个组内按订单时间降序排列，取每个组的第一条\n", "latest_actual_data = (result_df\n", " [result_df['order_id'].notna() & \n", " result_df['实际包裹数据'].notna() & \n", " (result_df['实际包裹数据'] != '')]\n", " .sort_values(['分组码', '订单时间'], ascending=[True, False])\n", " .groupby('分组码')\n", " .first()\n", " ['实际包裹数据'])\n", "\n", "# 映射回原DataFrame\n", "result_df['估算包裹尺寸'] = result_df['分组码'].map(latest_actual_data)\n", "\n", "print(f\"order_id不为空的分组码数量: {len(latest_actual_data)}\")\n", "print(f\"映射后估算包裹尺寸不为空的行数: {result_df['估算包裹尺寸'].notna().sum()}\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "from math import ceil\n", "import math\n", "\n", "\n", "def cal_est_package(erp_packages, size_coefficient_str):\n", " \"\"\"\n", " 根据ERP包裹数据和尺寸系数计算估算包裹尺寸\n", " \"\"\"\n", " # 如果尺寸系数为空，返回None\n", " if not size_coefficient_str or size_coefficient_str == '{}':\n", " return None\n", " \n", " if not erp_packages or not size_coefficient_str:\n", " return None\n", " \n", " erp_count = len(erp_packages)\n", " coefficient_count = len(size_coefficient_str)\n", " \n", " estimated_packages = {}\n", " \n", " # 2.2 如果ERP包裹数 > 尺寸系数的数量\n", " if erp_count > coefficient_count:\n", " for i in range(1, erp_count + 1):\n", " erp_pkg = erp_packages.get(str(i), {})\n", " if not erp_pkg:\n", " continue\n", " \n", " estimated_pkg = {}\n", " \n", " # 前面对应的包裹使用尺寸系数计算\n", " if i <= coefficient_count:\n", " coeff_pkg = size_coefficient_str.get(str(i), {})\n", " for dimension in ['长', '宽', '高']:\n", " erp_value = erp_pkg.get(dimension, 0)\n", " coeff = coeff_pkg.get(f'{dimension}系数', 0)\n", " if coeff is not None and erp_value is not None:\n", " estimated_pkg[dimension] = (1 + coeff) * erp_value\n", " else:\n", " estimated_pkg[dimension] = erp_value\n", " \n", " # 处理重量\n", " if '重量' in erp_pkg:\n", " erp_weight = erp_pkg.get('重量', 0)\n", " weight_coeff = coeff_pkg.get('重量系数', 0)\n", " if weight_coeff is not None and erp_weight is not None:\n", " estimated_pkg['重量'] = (1 + weight_coeff) * erp_weight\n", " else:\n", " estimated_pkg['重量'] = erp_weight\n", " else:\n", " # 多出来的包裹直接取ERP包裹数据（尺寸系数为0）\n", " estimated_pkg = erp_pkg.copy()\n", " \n", " estimated_packages[str(i)] = estimated_pkg\n", " \n", " # 2.3 如果ERP包裹数 <= 尺寸系数的数量\n", " else:\n", " for i in range(1, erp_count + 1):\n", " erp_pkg = erp_packages.get(str(i), {})\n", " coeff_pkg = size_coefficient_str.get(str(i), {})\n", " \n", " if not erp_pkg:\n", " continue\n", " \n", " estimated_pkg = {}\n", " for dimension in ['长', '宽', '高']:\n", " erp_value = erp_pkg.get(dimension, 0)\n", " coeff = coeff_pkg.get(f'{dimension}系数', 0)\n", " if coeff is not None and erp_value is not None:\n", " estimated_pkg[dimension] = math.ceil((1 + coeff) * erp_value)\n", " else:\n", " estimated_pkg[dimension] = math.ceil(erp_value)\n", " \n", " # 处理重量\n", " if '重量' in erp_pkg:\n", " erp_weight = erp_pkg.get('重量', 0)\n", " weight_coeff = coeff_pkg.get('重量系数', 0)\n", " if weight_coeff is not None and erp_weight is not None:\n", " estimated_pkg['重量'] = math.ceil((1 + weight_coeff) * erp_weight)\n", " else:\n", " estimated_pkg['重量'] = math.ceil(erp_weight)\n", " \n", " estimated_packages[str(i)] = estimated_pkg\n", " \n", " return dict_to_json_str(estimated_packages)\n", "\n", "\n", "# 第二步：对于估算包裹尺寸为空字典或空列表的行，使用尺寸系数计算\n", "different_group_rows = result_df[\n", " result_df['估算包裹尺寸'].isna() \n", "].copy()\n", "print(f\"找到 {len(different_group_rows)} 行需要计算估算包裹尺寸\")\n", "\n", "# 对筛选出来的行进行计算\n", "for index, row in different_group_rows.iterrows():\n", " if not row['ERP包裹数据'] or not row['尺寸系数']:\n", " continue\n", " erp_packages = json_str_to_dict(row['ERP包裹数据'])\n", " size_coefficients = json_str_to_dict(row['尺寸系数'])\n", " estimated_packages = cal_est_package(erp_packages, size_coefficients)\n", " different_group_rows.at[index, '估算包裹尺寸'] = estimated_packages\n", " print(f\"处理第 {index} 行， SKU: {row['SKU']}, 估算结果: {estimated_packages}\")\n", "\n", "# 创建预估尺寸映射\n", "est_map = different_group_rows.set_index('SKU')['估算包裹尺寸'].to_dict()\n", "\n", "# 只更新那些原来为空的行的估算包裹尺寸，保留第一步的结果\n", "result_df.loc[result_df['估算包裹尺寸'].isna(), '估算包裹尺寸'] = result_df.loc[result_df['估算包裹尺寸'].isna(), 'SKU'].map(est_map)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "different_group_rows = result_df[\n", " result_df['估算包裹尺寸'].isna() \n", "].copy()\n", "print(f\"找到 {len(different_group_rows)} 行需要计算估算包裹尺寸\")\n", "result_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "result_df.to_excel(f\"D:\\\\test\\\\logistics\\\\test_excel\\\\估算尺寸\\\\furniture.xlsx\", 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 }