raven4752’s gists

raven4752 / ubuntu_enable_bbr.sh

Created March 24, 2018 14:56 — forked from Jamesits/ubuntu_enable_bbr.sh

Ubuntu enable BBR

	#!/bin/bash
	set -eu

	SYSCTL_FILE=/etc/sysctl.d/90-tcp-bbr.conf

	# check root
	if [[ $EUID -ne 0 ]]; then
	echo "This script must be run as root"
	exit 1
	fi

raven4752 / keras_limit.py

Last active February 2, 2023 13:42

limit gpu memory usage of keras

	#put the these lines before importing any module from keras.
	import tensorflow as tf

	from keras.backend.tensorflow_backend import set_session
	config = tf.ConfigProto()
	config.gpu_options.allow_growth = True
	config.gpu_options.visible_device_list = "0" #only the gpu 0 is allowed
	set_session(tf.Session(config=config))

raven4752 / train_test_valid_split.py

Created April 4, 2018 08:20

a function to split train validation and test set

	#from https://stackoverflow.com/questions/38250710/how-to-split-data-into-3-sets-train-validation-and-test
	def train_validate_test_split(df, train_percent=.6, validate_percent=.2, seed=None):
	np.random.seed(seed)
	perm = np.random.permutation(df.index)
	m = len(df.index)
	train_end = int(train_percent * m)
	validate_end = int(validate_percent * m) + train_end
	train = df.ix[perm[:train_end]]
	validate = df.ix[perm[train_end:validate_end]]
	test = df.ix[perm[validate_end:]]

raven4752 / expr.py

Last active June 11, 2018 11:50

cross validating model with multiple input/output

	def multi_array_shuffle(*arrays, random_state=1):
	array_length = arrays[0].shape[0]
	permutated = []
	np.random.seed(random_state)
	permutation = np.random.permutation(array_length)
	for array in arrays:
	permutated.append(array[permutation, ...])
	return permutated

	def cv_model_func(model_func, inputs, targets, scores_func, label=None, seed=1, fold=5, **kwargs):

raven4752 / gist:3669ac1cf4aa7f9faf63d3328cd507f7

Created July 11, 2018 09:56

callback to save best model and early stopping with multi-input/multi-output using custom score functions

	import numpy as np
	import pandas as pd
	from keras.callbacks import Callback

	class ScoreMetric(Callback):
	def __init__(self, score_func, num_input=1, num_target=1):
	super(ScoreMetric, self).__init__()
	self.num_input = num_input
	self.num_target = num_target
	self.score_func = score_func

raven4752 / bibex_to_apa.py

Last active September 12, 2018 06:33

turn bibtex string into apa formatted citation string. the authors' names are concatenated by commas. First name and mid name are shortened.

	import bibtexparser
	from bibtexparser.bparser import BibTexParser
	from bibtexparser.customization import convert_to_unicode


	def parse_author(auth_str):
	auth_str_authors = auth_str.split(" and ")
	authors = []
	for author in auth_str_authors:
	if "," in author:

raven4752 / install_docker.sh

Last active May 6, 2019 17:57

script to install docker and nvidia-docker

	#!/bin/bash
	sudo apt-get update
	sudo apt-get install -y \
	apt-transport-https \
	ca-certificates \
	curl \
	software-properties-common
	curl -fsSL https://download.docker.com/linux/ubuntu/gpg \| sudo apt-key add -
	sudo add-apt-repository \
	"deb [arch=amd64] https://download.docker.com/linux/ubuntu \

raven4752 / valid_model.py

Created November 7, 2018 04:36

machine learning routine code

	from sklearn.ensemble import RandomForestClassifier
	from sklearn.ensemble import AdaBoostClassifier
	from sklearn.model_selection import KFold
	from sklearn.metrics import roc_auc_score
	import pandas as pd
	import numpy as np
	import os
	from matplotlib import pyplot as plt

raven4752 / hash_file.py

Created November 7, 2018 05:38

hash a file in python

	import hashlib
	def md5(fname):
	hash_md5 = hashlib.md5()
	with open(fname, "rb") as f:
	for chunk in iter(lambda: f.read(4096), b""):
	hash_md5.update(chunk)
	return hash_md5.hexdigest()

raven4752 / Dockerfile

Last active November 14, 2018 15:10

dockerfile and requirements.txt for abstractive summarization task with pytorch using chinese mirrors

	FROM nvidia/cuda:9.0-cudnn7-devel-ubuntu16.04
	ARG PYTHON_VERSION=3.6
	# workaround of the gpg error. see https://github.com/NVIDIA/nvidia-docker/issues/619
	RUN rm /etc/apt/sources.list.d/cuda.list

	# use the source of tuna
	RUN sed -i 's/archive.ubuntu.com/mirrors.tuna.tsinghua.edu.cn/g;s/security.ubuntu.com/mirrors.tuna.tsinghua.edu.cn/g' /etc/apt/sources.list
	RUN sed -i 's/http/https/g' /etc/apt/sources.list

	#for mongodb

raven4752 raven4752