khuangaf

dataset = dataset.shuffle()
train_dataset = dataset[:800000]
val_dataset = dataset[800000:900000]
test_dataset = dataset[900000:]
len(train_dataset), len(val_dataset), len(test_dataset)

khuangaf

import torch
from torch_geometric.data import InMemoryDataset
from tqdm import tqdm

class YooChooseBinaryDataset(InMemoryDataset):
    def __init__(self, root, transform=None, pre_transform=None):
        super(YooChooseBinaryDataset, self).__init__(root, transform, pre_transform)
        self.data, self.slices = torch.load(self.processed_paths[0])

    @property

khuangaf

import torch
from torch_geometric.data import InMemoryDataset
from tqdm import tqdm

class YooChooseBinaryDataset(InMemoryDataset):
    
    def process(self):
        
        data_list = []

khuangaf

import torch
from torch_geometric.data import InMemoryDataset
from tqdm import tqdm

class YooChooseBinaryDataset(InMemoryDataset):
    
    def process(self):
        
        data_list = []

khuangaf

data_list = []

# process by session_id
grouped = df.groupby('session_id')
for session_id, group in tqdm(grouped):
    sess_item_id = LabelEncoder().fit_transform(group.item_id)
    group = group.reset_index(drop=True)
    group['sess_item_id'] = sess_item_id
    node_features = group.loc[group.session_id==session_id,['sess_item_id','item_id']].sort_values('sess_item_id').item_id.drop_duplicates().values

khuangaf

data_list = []

      # process by session_id
      grouped = df.groupby('session_id')
      for session_id, group in tqdm(grouped):
          sess_item_id = LabelEncoder().fit_transform(group.item_id)
          group = group.reset_index(drop=True)
          group['sess_item_id'] = sess_item_id
          node_features = group.loc[group.session_id==session_id,['sess_item_id','item_id']].sort_values('sess_item_id').item_id.drop_duplicates().values

khuangaf

#randomly sample a couple of them
sampled_session_id = np.random.choice(df.session_id.unique(), 1000000, replace=False)
df = df.loc[df.session_id.isin(sampled_session_id)]
df.nunique()

khuangaf

import torch
from torch.nn import Sequential as Seq, Linear, ReLU
from torch_geometric.nn import MessagePassing

class SAGEConv(MessagePassing):
    def __init__(self, in_channels, out_channels):
        super(SAGEConv, self).__init__(aggr='max') #  "Max" aggregation.
        self.lin = torch.nn.Linear(in_channels, out_channels)
        self.act = torch.nn.ReLU()
        self.update_weight = Parameter(torch.Tensor(in_channels + out_channels, in_channels))

khuangaf

import torch
from torch_geometric.data import InMemoryDataset


class MyOwnDataset(InMemoryDataset):
    def __init__(self, root, transform=None, pre_transform=None):
        super(MyOwnDataset, self).__init__(root, transform, pre_transform)
        self.data, self.slices = torch.load(self.processed_paths[0])

    @property

khuangaf

df['label'] = df.session_id.isin(buy_df.session_id)
df.head()