mindis

mindis

// Based on tinrtgu's Python script here:
// https://www.kaggle.com/c/avazu-ctr-prediction/forums/t/10927/beat-the-benchmark-with-less-than-1mb-of-memory 
package main

import (
    "encoding/csv"
    "os"
    "strconv"
    "hash/fnv"
    "math"

mindis

{
  "type" : "record",
  "name" : "TrainingExample",
  "namespace" : "com.linkedin.metronome.avro.generated",
  "fields" : [ {
    "name" : "uid",
    "type" : [ "null", "string", "long", "int" ],
    "doc" : "a unique id for the training event",
    "default" : null
  }, {

mindis

#!/usr/bin/env python
'''Crop an image to just the portions containing text.

Usage:

    ./crop_morphology.py path/to/image.jpg

This will place the cropped image in path/to/image.crop.png.

For details on the methodology, see

mindis

#install pylucene from http://lucene.apache.org/pylucene/

import sys
import lucene
import os
from java.io import File
from java.nio.file import Paths
from itertools import izip
from lucene import JavaError

mindis

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

mindis

- word2vec https://arxiv.org/abs/1310.4546
- sentence2vec, paragraph2vec, doc2vec http://arxiv.org/abs/1405.4053
- tweet2vec http://arxiv.org/abs/1605.03481
- tweet2vec https://arxiv.org/abs/1607.07514
- author2vec http://dl.acm.org/citation.cfm?id=2889382
- item2vec http://arxiv.org/abs/1603.04259
- lda2vec https://arxiv.org/abs/1605.02019
- illustration2vec http://dl.acm.org/citation.cfm?id=2820907
- tag2vec http://ktsaurabh.weebly.com/uploads/3/1/7/8/31783965/distributed_representations_for_content-based_and_personalized_tag_recommendation.pdf
- category2vec http://www.anlp.jp/proceedings/annual_meeting/2015/pdf_dir/C4-3.pdf

mindis

#include "storage_engine/compression.h"
#include "perftest_tools.h"

#define ZSTD_STATIC_LINKING_ONLY
#include <zstd.h>

#include <iostream>
#include <cstdlib>
#include <algorithm>
#include <zlib.h>

mindis

package blog;

import com.google.caliper.SimpleBenchmark;
import java.util.BitSet;

public class BitSetBenchmark extends SimpleBenchmark{
  private BitSet bitSet;

  @Override
  protected void setUp() {

mindis

#List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

#Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

#Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(value_list)]