binshengliu

# https://stackoverflow.com/a/45438143/955952
def random_choice_noreplace(m, n, axis=-1):
    # m, n are the number of rows, cols of output
    return np.random.rand(m, n).argsort(axis=axis)

binshengliu

conda config --append channels bioconda
conda install perl perl-db-file perl-xml-parser perl-libwww-perl # This will install tons of packages
sed -i '1 s/perl.*/env perl/' ~/.files2rouge/ROUGE-1.5.5.pl

binshengliu

arr = np.array(np.meshgrid(arr0, arr1)).T.reshape(-1, 2)

binshengliu

sort -u -k 1,2 run.monobert.dev.small.tsv | trec_eval -m recip_rank_cut.10 qrels.dev.small.tsv -
sort -u -k 1,2 run.duobert.dev.small.tsv | trec_eval -m recip_rank_cut.10 qrels.dev.small.tsv -

binshengliu

perf record -F 99 -g -a <command>
perf script | ~/src/FlameGraph/stackcollapse-perf.pl | ~/src/FlameGraph/flamegraph.pl > perf.svg
google-chrome perf.svg

binshengliu

# https://stackoverflow.com/a/10154763/955952
fig.savefig('samplefigure', bbox_extra_artists=(lgd,text), bbox_inches='tight')

binshengliu

% https://tex.stackexchange.com/q/32886/124998
\includegraphics[width=\textwidth,height=\textheight,keepaspectratio]{myfig}

binshengliu

from more_itertools import always_iterable
from typing import Callable, Union
import multiprocessing
import pandas as pd


def groupby_mp(groupby_df: pd.core.groupby.DataFrameGroupBy,
               func: Callable[[pd.DataFrame], Union[pd.DataFrame, pd.Series]],
               num_cpus: int = multiprocessing.cpu_count() // 2,
               chunksize: int = 1) -> pd.DataFrame:

binshengliu

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

binshengliu

def tqdmf(path, *args, **kwargs):
    with tqdm(
            total=os.stat(path).st_size,
            unit='B',
            unit_scale=True,
            unit_divisor=1024,
            *args,
            **kwargs) as bar:
        with open(path, 'r') as f:
            for line in f: