This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# Define variables | |
TRITON_URL="localhost:8000" | |
MODEL_NAME="executor_model" | |
MODEL_VERSION="1" | |
# Create JSON payload | |
PAYLOAD=$(cat <<EOF | |
{ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from merlin.systems.dag.ops.workflow import TransformWorkflow | |
from merlin.systems.dag.ensemble import Ensemble | |
import nvtabular as nvt | |
import os | |
BASE_DIR = "." | |
if not os.path.isdir(os.path.join(BASE_DIR, 'ensemble')): | |
os.makedirs(os.path.join(BASE_DIR, 'ensemble')) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import argparse | |
import os | |
import nvtabular as nvt | |
from nvtabular import ops | |
from merlin.io import Dataset | |
from merlin.dag.ops.subgraph import Subgraph | |
def parse_args(): | |
parser = argparse.ArgumentParser(description='Process the generated dataset using NVTabular') | |
parser.add_argument('--input_path', type=str, default='./data/simulated/source_dataset/*.parquet', help='Input dataset path') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
import pyarrow.parquet as pq | |
from tqdm import tqdm | |
import os | |
import argparse | |
def parse_args(): | |
parser = argparse.ArgumentParser(description='Generate a large categorical dataset') | |
parser.add_argument('--col1_cardinality', type=int, default=50_000_000, help='Cardinality of column 1') |