Skip to content

Instantly share code, notes, and snippets.

import json
from gensim.models import Word2Vec
import nltk
from nltk.tokenize import sent_tokenize, word_tokenize
def get_train(end):
train = []
@bowbowbow
bowbowbow / waveform.py
Created August 9, 2018 10:02 — forked from moeseth/waveform.py
Create Soundcloud style waveform from Audio in Python
from pydub import AudioSegment
from matplotlib import pyplot as plot
from PIL import Image, ImageDraw
import numpy as np
import os
src = "./test.mp3"
audio = AudioSegment.from_file(src)
data = np.fromstring(audio._data, np.int16)
sudo apt-get update
sudo apt-get install build-essential chrpath libssl-dev libxft-dev -y
sudo apt-get install libfreetype6 libfreetype6-dev -y
sudo apt-get install libfontconfig1 libfontconfig1-dev -y
cd ~
export PHANTOM_JS="phantomjs-2.1.1-linux-x86_64"
wget https://github.com/Medium/phantomjs/releases/download/v2.1.1/$PHANTOM_JS.tar.bz2
sudo tar xvjf $PHANTOM_JS.tar.bz2
sudo mv $PHANTOM_JS /usr/local/share
sudo ln -sf /usr/local/share/$PHANTOM_JS/bin/phantomjs /usr/local/bin
@bowbowbow
bowbowbow / hashtag_baseline.py
Last active June 16, 2018 17:16
TOP K=10, Mean Average Precision : 0.87821
import json
import random
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn import preprocessing
json_data = open('./dataset.json').read()
tweets = json.loads(json_data)
tweets_train, tweets_test = [], []
images.txt
@bowbowbow
bowbowbow / fr_parser_with_injection.py
Last active November 13, 2017 12:32
trust있으면 만점, distrust있으면 최하점 넣는 방식으로 fr_train.txt 생성
from collections import defaultdict
users = {}
trust = {}
# 신뢰 관계 특정 개수 이상인 유저
group = {}
group_list = []
def build_users():
#include <cstdio>
#include <iostream>
#include <vector>
#include <map>
#include <set>
#include <string>
#include <algorithm>
#include <ctime>
#include <fstream>
#include <cmath>
@bowbowbow
bowbowbow / CF.java
Created November 1, 2017 13:11
데이터 전처리 코드와 ALS CF
package org.deeplearning4j.examples.feedforward.classification;
import org.apache.spark.api.java.function.VoidFunction;
import org.bytedeco.javacv.FrameFilter;
import scala.Tuple2;
import org.apache.spark.api.java.*;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.recommendation.ALS;
import org.apache.spark.mllib.recommendation.MatrixFactorizationModel;
from collections import defaultdict
from decimal import *
import random
import time
getcontext().prec = 128
# convert to big decimal
def lf(num):
return Decimal(num)
from collections import defaultdict
from decimal import *
import random
import time
#getcontext().prec = 1000
# convert to big decimal
def lf(num):
return Decimal(num)