rnyak

import os
import tensorflow as tf
import merlin.models.tf as mm

from nvtabular.workflow import Workflow

from merlin.systems.dag.ops.tensorflow import PredictTensorflow
from merlin.systems.dag.ensemble import Ensemble
from merlin.systems.dag.ops.workflow import TransformWorkflow

rnyak

import os
os.environ["TF_GPU_ALLOCATOR"]="cuda_malloc_async"
import glob
import numpy as np
import pandas as pd
import gc
import calendar
import datetime

import cudf

rnyak

import os
os.environ["TF_GPU_ALLOCATOR"]="cuda_malloc_async"
import glob
import numpy as np
import pandas as pd
import gc
import calendar
import datetime

import cudf

rnyak

import os
os.environ["TF_GPU_ALLOCATOR"]="cuda_malloc_async"
import glob
import numpy as np
import pandas as pd
import gc
import calendar
import datetime

import cudf

rnyak

import os
import nvtabular as nvt
from nvtabular.ops import *
from merlin.schema.tags import Tags
import merlin.models.tf as mm
from merlin.io.dataset import Dataset
import tensorflow as tf

DATA_FOLDER = os.environ.get("DATA_FOLDER", "./data/")
# define output path for the processed parquet files

rnyak

import os
import glob

import numpy as np
import pandas as pd

import cudf
import cupy as cp
import nvtabular as nvt
from nvtabular.ops import *

rnyak

name: "0_transformworkflow"
input {
  name: "item_id"
  data_type: TYPE_INT32
  dims: -1
  dims: 1
}
input {
  name: "category"
  data_type: TYPE_INT32

rnyak

import os
import glob

import numpy as np
import pandas as pd

import cudf
import cupy as cp
import nvtabular as nvt
from nvtabular.ops import *

rnyak

from merlin.datasets.synthetic import generate_data
train, valid = generate_data("dressipi2022-preprocessed", num_rows=10000, set_sizes=(0.8, 0.2))
item_features_names = ['f_' + str(col) for col in [47, 68]]
cat_features = [['item_id', 'purchase_id']] + item_features_names >> nvt.ops.Categorify()

features = ['session_id', 'timestamp', 'date'] + cat_features
to_aggregate = {}
to_aggregate['date'] = ["first"]
to_aggregate['item_id'] = ["last", "list"]
to_aggregate['purchase_id'] = ["first"]   

rnyak

import os
import numpy as np
import pandas as pd
import nvtabular as nvt

NUM_ROWS = 1000
long_tailed_item_distribution = np.clip(np.random.lognormal(3., 1., NUM_ROWS).astype(np.int32), 1, 50000)

# generate random item interaction features 
df = pd.DataFrame(np.random.randint(70000, 80000, NUM_ROWS), columns=['session_id'])