nextrec 0.4.22__py3-none-any.whl → 0.4.23__py3-none-any.whl

nextrec/models/ranking/dcn_v2.py

@@ -45,7 +45,7 @@ DCN v2 在原始 DCN 基础上，将标量交叉权重升级为向量/矩阵参
 
 import torch
 import torch.nn as nn
-
+from typing import Literal
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
 from nextrec.basic.heads import TaskHead
@@ -193,53 +193,32 @@ class DCNv2(BaseModel):
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
         cross_num: int = 3,
-        cross_type: str = "matrix",
-        architecture: str = "parallel",
+        cross_type: Literal["matrix", "mix", "low_rank"] = "matrix",
+        architecture: Literal["parallel", "stacked"] = "parallel",
         low_rank: int = 32,
         num_experts: int = 4,
         mlp_params: dict | None = None,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
         dense_features = dense_features or []
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
+        mlp_params = mlp_params or {}
 
         super(DCNv2, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.all_features = dense_features + sparse_features + sequence_features
         self.embedding = EmbeddingLayer(features=self.all_features)
         input_dim = self.embedding.input_dim
 
-        architecture = architecture.lower()
         if architecture not in {"parallel", "stacked"}:
             raise ValueError("architecture must be 'parallel' or 'stacked'.")
         self.architecture = architecture
 
-        cross_type = cross_type.lower()
         if cross_type == "matrix":
             self.cross_network = CrossNetV2(input_dim=input_dim, num_layers=cross_num)
         elif cross_type in {"mix", "low_rank"}:
@@ -271,20 +250,13 @@ class DCNv2(BaseModel):
             final_input_dim = input_dim
 
         self.final_layer = nn.Linear(final_input_dim, 1)
-        self.prediction_layer = TaskHead(task_type=self.default_task)
+        self.prediction_layer = TaskHead(task_type=self.task)
 
         self.register_regularization_weights(
             embedding_attr="embedding",
             include_modules=["cross_network", "mlp", "final_layer"],
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x) -> torch.Tensor:
         input_flat = self.embedding(x=x, features=self.all_features, squeeze_dim=True)
         cross_out = self.cross_network(input_flat)

nextrec/models/ranking/deepfm.py

@@ -42,8 +42,6 @@ embedding，无需手工构造交叉特征即可端到端训练，常用于 CTR/
 - CTR/CVR 任务的常用强基线
 """
 
-import torch.nn as nn
-
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import FM, LR, MLP, EmbeddingLayer
 from nextrec.basic.heads import TaskHead
@@ -65,16 +63,6 @@ class DeepFM(BaseModel):
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
         mlp_params: dict | None = None,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
@@ -82,24 +70,14 @@ class DeepFM(BaseModel):
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
         mlp_params = mlp_params or {}
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(DeepFM, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
         self.fm_features = sparse_features + sequence_features
         self.deep_features = dense_features + sparse_features + sequence_features
         self.embedding = EmbeddingLayer(features=self.deep_features)
@@ -110,18 +88,13 @@ class DeepFM(BaseModel):
         self.linear = LR(fm_emb_dim_total)
         self.fm = FM(reduce_sum=True)
         self.mlp = MLP(input_dim=mlp_input_dim, **mlp_params)
-        self.prediction_layer = TaskHead(task_type=self.default_task)
+
+        self.prediction_layer = TaskHead(task_type=self.task)
 
         # Register regularization weights
         self.register_regularization_weights(
             embedding_attr="embedding", include_modules=["linear", "mlp"]
         )
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
 
     def forward(self, x):
         input_deep = self.embedding(x=x, features=self.deep_features, squeeze_dim=True)

nextrec/models/ranking/dien.py

@@ -58,6 +58,7 @@ from nextrec.basic.layers import (
 )
 from nextrec.basic.heads import TaskHead
 from nextrec.basic.model import BaseModel
+from nextrec.utils.types import ActivationName
 
 
 class AUGRU(nn.Module):
@@ -211,19 +212,9 @@ class DIEN(BaseModel):
         mlp_params: dict | None = None,
         gru_hidden_size: int = 64,
         attention_hidden_units: list[int] | None = None,
-        attention_activation: str = "sigmoid",
+        attention_activation: ActivationName = "sigmoid",
         use_negsampling: bool = False,
         aux_loss_weight: float = 1.0,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
@@ -232,24 +223,14 @@ class DIEN(BaseModel):
         sequence_features = sequence_features or []
         mlp_params = mlp_params or {}
         attention_hidden_units = attention_hidden_units or [80, 40]
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(DIEN, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
         self.use_negsampling = use_negsampling
         self.aux_loss_weight = float(aux_loss_weight)
         self.auxiliary_cache = None
@@ -361,13 +342,6 @@ class DIEN(BaseModel):
             ],
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         self.auxiliary_cache = None
         if self.candidate_feature:

nextrec/models/ranking/din.py

@@ -58,6 +58,7 @@ from nextrec.basic.layers import (
 )
 from nextrec.basic.heads import TaskHead
 from nextrec.basic.model import BaseModel
+from nextrec.utils.types import ActivationName
 
 
 class DIN(BaseModel):
@@ -78,18 +79,8 @@ class DIN(BaseModel):
         candidate_feature_name: str | None = None,
         mlp_params: dict | None = None,
         attention_hidden_units: list[int] | None = None,
-        attention_activation: str = "dice",
+        attention_activation: ActivationName = "dice",
         attention_use_softmax: bool = True,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
@@ -98,20 +89,11 @@ class DIN(BaseModel):
         sequence_features = sequence_features or []
         mlp_params = mlp_params or {}
         attention_hidden_units = attention_hidden_units or [80, 40]
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(DIN, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
@@ -182,13 +164,6 @@ class DIN(BaseModel):
             include_modules=["attention", "mlp", "candidate_attention_proj"],
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         # Get candidate item embedding
         if self.candidate_feature is None:

nextrec/models/ranking/eulernet.py

@@ -32,7 +32,7 @@ EulerNet 使用欧拉公式将特征嵌入映射到复数域，通过复数相
 """
 
 from __future__ import annotations
-
+from typing import Literal
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -61,7 +61,7 @@ class EulerInteractionLayer(nn.Module):
         num_fields: int,
         num_orders: int,
         use_implicit: bool = True,
-        norm: str | None = "ln",  # None | "bn" | "ln"
+        norm: Literal["bn", "ln"] | None = "ln",  # None | "bn" | "ln"
         eps: float = 1e-9,
     ):
         super().__init__()
@@ -203,42 +203,22 @@ class EulerNet(BaseModel):
         num_layers: int = 2,
         num_orders: int = 8,
         use_implicit: bool = True,
-        norm: str | None = "ln",
+        norm: Literal["bn", "ln"] | None = "ln",
         use_linear: bool = False,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
         dense_features = dense_features or []
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(EulerNet, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
         self.use_linear = use_linear
 
         self.linear_features = dense_features + sparse_features + sequence_features
@@ -303,13 +283,6 @@ class EulerNet(BaseModel):
             embedding_attr="embedding", include_modules=modules
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         field_emb = self.embedding(
             x=x, features=self.interaction_features, squeeze_dim=False

nextrec/models/ranking/ffm.py

@@ -63,35 +63,16 @@ class FFM(BaseModel):
         dense_features: list[DenseFeature] | None = None,
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
         dense_features = dense_features or []
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(FFM, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
@@ -154,13 +135,6 @@ class FFM(BaseModel):
             embedding_attr="field_aware_embeddings", include_modules=["linear_dense"]
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def field_aware_key(
         self, src_feature: SparseFeature | SequenceFeature, target_field
     ) -> str:

nextrec/models/ranking/fibinet.py

@@ -41,8 +41,7 @@ FiBiNET 是一个 CTR 预估模型，通过 SENET 重新分配特征字段的重
 """
 
 import torch
-import torch.nn as nn
-
+from typing import Literal
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import (
     LR,
@@ -71,19 +70,13 @@ class FiBiNET(BaseModel):
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
         mlp_params: dict | None = None,
-        interaction_combo: str = "11",  # "0": Hadamard, "1": Bilinear
-        bilinear_type: str = "field_interaction",
+        interaction_combo: Literal[
+            "01", "11", "10", "00"
+        ] = "11",  # "0": Hadamard, "1": Bilinear
+        bilinear_type: Literal[
+            "field_all", "field_each", "field_interaction"
+        ] = "field_interaction",
         senet_reduction: int = 3,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
@@ -91,24 +84,14 @@ class FiBiNET(BaseModel):
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
         mlp_params = mlp_params or {}
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(FiBiNET, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
         self.linear_features = sparse_features + sequence_features
         self.interaction_features = sparse_features + sequence_features
 
@@ -166,7 +149,7 @@ class FiBiNET(BaseModel):
         num_pairs = self.num_fields * (self.num_fields - 1) // 2
         interaction_dim = num_pairs * self.embedding_dim * 2
         self.mlp = MLP(input_dim=interaction_dim, **mlp_params)
-        self.prediction_layer = TaskHead(task_type=self.default_task)
+        self.prediction_layer = TaskHead(task_type=self.task)
 
         # Register regularization weights
         self.register_regularization_weights(
@@ -180,13 +163,6 @@ class FiBiNET(BaseModel):
             ],
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         input_linear = self.embedding(
             x=x, features=self.linear_features, squeeze_dim=True

nextrec/models/ranking/fm.py

@@ -38,8 +38,6 @@ FM 是一种通过分解二阶特征交互矩阵、以线性复杂度建模特
 - 结构简单、表现强健，常作 CTR 基线
 """
 
-import torch.nn as nn
-
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import FM as FMInteraction
 from nextrec.basic.heads import TaskHead
@@ -61,16 +59,6 @@ class FM(BaseModel):
         dense_features: list[DenseFeature] | None = None,
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
@@ -82,19 +70,9 @@ class FM(BaseModel):
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
-        if self.loss is None:
-            self.loss = "bce"
-
         self.fm_features = sparse_features + sequence_features
         if len(self.fm_features) == 0:
             raise ValueError("FM requires at least one sparse or sequence feature.")
@@ -111,13 +89,6 @@ class FM(BaseModel):
             embedding_attr="embedding", include_modules=["linear"]
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         input_fm = self.embedding(x=x, features=self.fm_features, squeeze_dim=False)
         y_linear = self.linear(input_fm.flatten(start_dim=1))

nextrec/models/ranking/lr.py

@@ -38,8 +38,6 @@ LR 是 CTR/排序任务中最经典的线性基线模型。它将稠密、稀疏
 - 权重可解释性强
 """
 
-import torch.nn as nn
-
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import EmbeddingLayer, LR as LinearLayer
 from nextrec.basic.heads import TaskHead
@@ -60,41 +58,20 @@ class LR(BaseModel):
         dense_features: list[DenseFeature] | None = None,
         sparse_features: list[SparseFeature] | None = None,
         sequence_features: list[SequenceFeature] | None = None,
-        target: list[str] | str | None = None,
-        task: str | list[str] | None = None,
-        optimizer: str = "adam",
-        optimizer_params: dict | None = None,
-        loss: str | nn.Module | None = "bce",
-        loss_params: dict | list[dict] | None = None,
-        embedding_l1_reg=0.0,
-        dense_l1_reg=0.0,
-        embedding_l2_reg=0.0,
-        dense_l2_reg=0.0,
         **kwargs,
     ):
 
         dense_features = dense_features or []
         sparse_features = sparse_features or []
         sequence_features = sequence_features or []
-        optimizer_params = optimizer_params or {}
-        if loss is None:
-            loss = "bce"
 
         super(LR, self).__init__(
             dense_features=dense_features,
             sparse_features=sparse_features,
             sequence_features=sequence_features,
-            target=target,
-            task=task or self.default_task,
-            embedding_l1_reg=embedding_l1_reg,
-            dense_l1_reg=dense_l1_reg,
-            embedding_l2_reg=embedding_l2_reg,
-            dense_l2_reg=dense_l2_reg,
             **kwargs,
         )
 
-        self.loss = loss
-
         self.embedding = EmbeddingLayer(features=self.all_features)
         linear_input_dim = self.embedding.input_dim
         self.linear = LinearLayer(linear_input_dim)
@@ -104,13 +81,6 @@ class LR(BaseModel):
             embedding_attr="embedding", include_modules=["linear"]
         )
 
-        self.compile(
-            optimizer=optimizer,
-            optimizer_params=optimizer_params,
-            loss=loss,
-            loss_params=loss_params,
-        )
-
     def forward(self, x):
         input_linear = self.embedding(x=x, features=self.all_features, squeeze_dim=True)
         y = self.linear(input_linear)