电商数据建模
一、分析背景与目的
1.1 背景介绍
| 电商平台数据分析是最为典型的一个数据分析赛道，且电商数据分析有着比较成熟的数据分析模型，比如：人货场模型。此文中我将通过分析国内最大的电商平台——淘宝的用户行为，来巩固数据分析技能以及思维。通过分析用户行为，以此来实现精准营销，总结现有问题，获得业务增长 |
1.2 数据说明
| 该数据包含了20230523用户一天购物行为的所有数据，主要包括人货场三个维度信息。用户维度、商品维度、地区维度构成一个用户下单的行为事实表。 |
1.3数据分析流程
提出业务问题—确认粒度—数据处理和清洗—构建模型—数据可视化——根据数据可视化分析解决问题
业务问题：
1.如何提高品牌销售力度？
2.如何刺激地区市场消费潜力？
3.如何刺激用户消费？
4.如何减少产品成本？
确认粒度：
用户信息表、订单表、订单明细表
商品信息表、品牌信息表、一二三级分类信息表
省份信息表、地区信息表
核心算法代码分享如下：
import sysimport numpy as np
from torch.utils.data import DataLoader
from torch import nn
import torch.nn.functional as F
import torch
from sklearn.metrics import precision_score,recall_score,accuracy_scoreimport dataloaderclass ALS_MLP (nn.Module):def __init__(self, n_users, n_items, dim):super(ALS_MLP, self).__init__()''':param n_users: 用户数量:param n_items: 物品数量:param dim: 向量维度'''# 随机初始化用户的向量,self.users = nn.Embedding( n_users, dim, max_norm=1 )# 随机初始化物品的向量self.items = nn.Embedding( n_items, dim, max_norm=1 )#初始化用户向量的隐层self.u_hidden_layer1 = self.dense_layer(dim, dim // 2)self.u_hidden_layer2 = self.dense_layer(dim//2, dim // 4)#初始化物品向量的隐层self.i_hidden_layer1 = self.dense_layer(dim, dim // 2)self.i_hidden_layer2 = self.dense_layer(dim//2, dim // 4)self.sigmoid = nn.Sigmoid()def dense_layer(self,in_features,out_features):#每一个mlp单元包含一个线性层和激活层，当前代码中激活层采取Tanh双曲正切函数。return nn.Sequential(nn.Linear(in_features, out_features),nn.Tanh())def forward(self, u, v, isTrain=True):''':param u: 用户索引id shape:[batch_size]:param i: 用户索引id shape:[batch_size]:return: 用户向量与物品向量的内积 shape:[batch_size]'''u = self.users(u)v = self.items(v)u = self.u_hidden_layer1(u)u = self.u_hidden_layer2(u)v = self.i_hidden_layer1(v)v = self.i_hidden_layer2(v)#训练时采取dropout来防止过拟合if isTrain:u = F.dropout(u)v = F.dropout(v)uv = torch.sum( u*v, axis = 1)logit = self.sigmoid(uv*3)return logitdef doEva(net, d):d = torch.LongTensor(d)u, i, r = d[:, 0], d[:, 1], d[:, 2]with torch.no_grad():out = net(u,i,False)y_pred = np.array([1 if i >= 0.5 else 0 for i in out])y_true = r.detach().numpy()p = precision_score(y_true, y_pred)r = recall_score(y_true, y_pred)acc = accuracy_score(y_true,y_pred)return p,r,accdef train( epochs = 10, batchSize = 1024, lr = 0.001, dim = 256, eva_per_epochs = 1):''':param epochs: 迭代次数:param batchSize: 一批次的数量:param lr: 学习率:param dim: 用户物品向量的维度:param eva_per_epochs: 设定每几次进行一次验证'''#读取数据user_set, item_set, train_set, test_set = \dataloader.readRecData(test_ratio = 0.1)#初始化ALS模型net = ALS_MLP(len(user_set), len(item_set), dim)#定义优化器optimizer = torch.optim.AdamW( net.parameters(), lr = lr, weight_decay=0.2)#定义损失函数criterion = torch.nn.BCELoss()#开始迭代for e in range(epochs):all_lose = 0#每一批次地读取数据for u, i, r in DataLoader(train_set,batch_size = batchSize, shuffle = True):optimizer.zero_grad()r = torch.FloatTensor(r.detach().numpy())result = net(u,i)loss = criterion(result,r)all_lose += lossloss.backward()optimizer.step()print('epoch {}, avg_loss = {:.4f}'.format(e,all_lose/(len(train_set)//batchSize)))#评估模型if e % eva_per_epochs==0:p, r, acc = doEva(net, train_set)print('train: Precision {:.4f} | Recall {:.4f} | accuracy {:.4f}'.format(p, r, acc))p, r, acc = doEva(net, test_set)print('test: Precision {:.4f} | Recall {:.4f} | accuracy {:.4f}'.format(p, r, acc))def als_mlp_predict(userId=1, itemSize=100, count=4, dim=64):# 读取数据user_set, item_set, train_set, test_set = \dataloader.readRecData( test_ratio=0.1)# 预测一个用户的所有的评分形成一个元祖train_set = []for i in range(1, itemSize):train_set.append((userId, i, 0))# print(train_set)# print(train_set)# 初始化ALS模型net = ALS_MLP(len(user_set), len(item_set), dim)d = torch.LongTensor(train_set)u, i, r = d[:, 0], d[:, 1], d[:, 2]with torch.no_grad():out = net(u, i)predict = []preds = out.tolist()# print(len(preds))# 找出最大值,通过这种方式可以求出多个for i in range(0, count):m = max(preds)idx = preds.index(m)predict.append(dict(iid=idx, score=m))del preds[idx]# print(predict)return predictdef test(dim = 64):result = als_mlp_predict(1, 2000, 5)print(result)if __name__ == '__main__':# train()# test()param1 = sys.argv[1]# param1 = "1"result = als_mlp_predict(int(param1), 55, 4)list = []# print(result)for r in result:list.append(dict(iid=r['iid'], rate=r['score']))print(list)