BalazsHoranyi

from distributed import Client, LocalCluster
import dask.dataframe as dd
import numpy as np

cluster = LocalCluster(ip='0.0.0.0', n_workers=32, threads_per_worker=1, diagnostics_port=8787, **{'memory_limit': 2e9})
client = Client(cluster)
print(client)

df = dd.read_parquet('parquet/')
print(f'found {len(df)} interactions')

BalazsHoranyi

def bpr_loss(positive_predictions, negative_predictions):
    """
    Bayesian Personalised Ranking pairwise loss function. Original Implementation: https://github.com/maciejkula/spotlight

    """

    loss = (1.0 - F.sigmoid(positive_predictions -
                            negative_predictions))

    return loss.mean()

BalazsHoranyi

import pandas as pd
import numpy as np
import pyarrow as pa
import pyarrow.parquet as pq
import requests
import datetime
import os
import gzip
from joblib import Parallel, delayed