多路召回+DeepFM实时更新

moiveRe/DeepFMcopy.py

@@ -0,0 +1,77 @@
+import django
+import os
+import torch
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "moiveRe.settings")
+django.setup()
+
+
+
+
+
+
+
+
+
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, MinMaxScaler
+import torch
+from deepctr_torch.models import DeepFM
+from deepctr_torch.inputs import SparseFeat, DenseFeat, get_feature_names
+
+# 生成示例数据
+np.random.seed(2024)
+data_size = 10000
+
+# 假设有 26 个离散特征 C1, C2, ..., C26
+sparse_features = ['C' + str(i) for i in range(1,4)]
+# 假设有 13 个连续特征 I1, I2, ..., I13
+dense_features = ['I' + str(i) for i in range(1,3)]
+
+data = {feat: np.random.choice([0, 1, 2, 3, 4], data_size) for feat in sparse_features}
+data.update({feat: np.random.rand(data_size) for feat in dense_features})
+data['label'] = np.random.randint(0, 2, data_size)
+
+# 转换为 DataFrame
+df = pd.DataFrame(data)
+print(df)
+
+
+#预处理部分:
+# 对离散特征进行标签编码,转为数值的意思
+for feat in sparse_features:
+    lbe = LabelEncoder()
+    df[feat] = lbe.fit_transform(df[feat])
+# 对连续特征进行归一化
+mms = MinMaxScaler()
+df[dense_features] = mms.fit_transform(df[dense_features])
+
+train, test = train_test_split(df, test_size=0.2)
+
+# deepctr模型输入
+fixlen_feature_columns = [SparseFeat(feat, df[feat].nunique(), embedding_dim=4) for feat in sparse_features] + [DenseFeat(feat, 1,) for feat in dense_features]
+
+
+
+
+# DeepFM 模型，开导！
+model = DeepFM(fixlen_feature_columns, fixlen_feature_columns, task='binary') # 重复传入相同的列~ 这里因为是根据CTR来对召回进行排序所以就是binary任务
+
+# 编译模型
+model.compile("adam", "binary_crossentropy",
+              metrics=["binary_crossentropy"], ) #优化器选择balabala，这里直接看库里给的文档
+
+# 训练模型
+train_model_input = {name: train[name].values for name in get_feature_names(fixlen_feature_columns)}
+test_model_input = {name: test[name].values for name in get_feature_names(fixlen_feature_columns)}
+label_distribution = train['label'].value_counts()
+print('label_dis:',label_distribution)
+history = model.fit(train_model_input, train['label'].values,
+                    batch_size=50, epochs=4, verbose=2, validation_split=0, ) #fit开始train
+
+
+
+
+

moiveRe/DeepFm.py

@@ -1,50 +0,0 @@
-import numpy as np
-import pandas as pd
-import torch
-import torch.nn as nn
-import torch.optim as optim
-from sklearn.model_selection import train_test_split
-from deepctr.models import DeepFM
-from deepctr.feature_column import SparseFeat, get_feature_names
-
-# 假设有一个包含广告特征和点击情况的数据集
-data = {
-    'user_id': [1, 2, 3, 4, 5],
-    'ad_id': [101, 102, 103, 104, 105],
-    'age': [25, 30, 35, 40, 45],
-    'gender': ['M', 'F', 'M', 'F', 'M'],
-    'click': [1, 0, 1, 0, 1]
-}
-df = pd.DataFrame(data)
-
-# 定义特征列
-sparse_features = ['user_id', 'ad_id', 'gender']
-dense_features = ['age']
-
-# 将特征列转换为SparseFeat和DenseFeat类型
-feature_columns = [SparseFeat(feat, vocabulary_size=df[feat].nunique(), embedding_dim=4)
-                   for feat in sparse_features] + [DenseFeat(feat, 1) for feat in dense_features]
-
-# 划分训练集和测试集
-train, test = train_test_split(df, test_size=0.2)
-
-# 创建模型
-model = DeepFM(feature_columns, feature_columns, task='binary')
-
-# 编译模型
-model.compile("adam", "binary_crossentropy", metrics=['binary_crossentropy'])
-
-# 将数据转换为模型所需的输入格式
-train_model_input = {name: train[name] for name in sparse_features + dense_features}
-test_model_input = {name: test[name] for name in sparse_features + dense_features}
-train_target = train['click'].values
-test_target = test['click'].values
-
-# 训练模型
-history = model.fit(train_model_input, train_target, batch_size=256, epochs=10, verbose=2, validation_split=0.2)
-
-# 预测
-preds = model.predict(test_model_input, batch_size=256)
-
-# 输出预测结果
-print("预测点击率：", preds)

moiveRe/UserExperienceUpdate.py

@@ -0,0 +1,26 @@
+
+
+import django
+from django.conf import settings
+import os
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "moiveRe.settings")  # 替换 "yourproject.settings" 为你的项目的 settings 模块路径
+django.setup()
+
+from moiveReApp.models import UserExperience
+
+
+# 兴趣标签集合
+experience_tags = [
+    'NewtoGame','Middle','Experienced'
+]
+
+# 将标签添加到数据库中
+for tag_name in experience_tags:
+    tag, created = UserExperience.objects.get_or_create(name=tag_name)
+
+    # 如果标签是新创建的，则打印一条消息
+    if created:
+        print(f'Created tag: {tag_name}')
+    else:
+        print(f'Tag already exists: {tag_name}')

moiveRe/moiveReApp/models.py

@@ -68,10 +68,19 @@ class Userinterests(models.Model):
     def __str__(self):
         return self.name
 
+class UserExperience(models.Model):
+    name = models.CharField(max_length=100, unique=True)
+
+    def __str__(self):
+        return self.name
+
+
+
 
 class UserProfile(models.Model):
     # 与用户关联的一对一字段，这里假设你使用了Django内置的User模型
     user = models.OneToOneField(User, on_delete=models.CASCADE)
+    userExperience = models.ManyToManyField(UserExperience, related_name='user_experience')
     interests = models.ManyToManyField(Userinterests, related_name='interested_users')
     liked_items = models.ManyToManyField(Question, blank=True, related_name='liked_users')
     click_items = models.ManyToManyField(Question, blank=True, related_name='clicked_users')