lfoppiano

import argparse
import os
from pathlib import Path

import requests

# Constants
GLUTTON_URL = "ADD BIBLIO GLUTTON LOOKUP SERVICE"

lfoppiano

# Credits to https://marmelab.com/blog/2018/03/21/using-nvidia-gpu-within-docker-container.html 

# Run with 
# [CPU] docker run     --runtime=nvidia     --rm     -ti     -v "${PWD}:/app"     tensorflow/tensorflow:1.15.5-gpu     python /app/nvidia-benchmark.py cpu 10000
# [GPU] docker run     --runtime=nvidia     --rm     -ti     -v "${PWD}:/app"     tensorflow/tensorflow:1.15.5-gpu     python /app/nvidia-benchmark.py gpu 10000


import sys
import numpy as np
import tensorflow as tf

lfoppiano

JProfiler with Docker

Docker

DockerFile

DockerFile should have JProfiler installation.

RUN wget <JProfiler file location> -P /tmp/ && \
  tar -xzf /tmp/<JProfiler file> -C /usr/local && \
  rm /tmp/<JProfiler file>

lfoppiano

from difflib import SequenceMatcher

def group_by_with_soft_matching(input_list, threshold):
    matching = {}
    last_matching = -1

    input_list_sorted = sorted(list(set(input_list)), reverse=True)

    for index_x, x in enumerate(input_list_sorted):
        unpacked = [y for x in matching for y in matching[x]]

lfoppiano

import json
import os
import pathlib
import sys

from delft.sequenceLabelling.preprocess import WordPreprocessor

if __name__ == '__main__':
    if len(sys.argv) != 2:
        print("Invalid parameters. Usage: python json_migration.py model directory. "

lfoppiano

# Just return the sha of the duplicated files 
sha1sum * | gsort | gawk '{a[$1]++}END{for(i in a){if(a[i]-1)print i, a[i]}}'

# Return the last file name for each duplicated files 
sha1sum * | gsort | gawk '{a[$1]++; b[$1]=$2}END{for(i in a){if(a[i]-1)print i, b[i]}}' 

lfoppiano

import prodigy
from prodigy.components.loaders import JSONL
from prodigy.util import split_string


@prodigy.recipe('superconductor-material-recipe',
                dataset=prodigy.recipe_args['dataset'],
                source=("The source data as a JSONL file", "positional", None, str),
                label=("One or more comma-separated labels", "option", "l", split_string))
def superconductors_detection(dataset, source=None, label=None):