myui

context = HiveContext(sc)

context.sql("
  SELECT 
    feature, avg(weight) as weight
  FROM (
      SELECT train_logregr(features, label)
         as (feature, weight)
      FROM trainTable
  ) model

myui

val trainDf = 
  spark.read.format("libsvm”).load(“a9a.train")

trainDf.train_logregr($"feature", $"label")
  .groupby("feature")
  .agg("weight"->"avg")

myui

a = load 'a9a.train' 
      as (rowid:int, label:float, features:{(featurepair:chararray)});
b = foreach c generate flatten(
      logress(features, label, '-total_steps ${total_steps}')
    ) as (feature, weight);
c = group b by feature;
d = foreach c generate group, AVG(c.weight);
store d into 'a9a_model1';

myui

set ytics nomirror
set y2tics
set yr[-20:20]

plot \
  "cf2d.dat" using 1:2 with lines title "x", \
  "cf2d.dat" using 1:3 with lines title "outlier" axes x1y2, \
  "cf2d.dat" using 1:4 with lines title "change" axes x1y2

myui

set ytics nomirror
unset y2tics
set y2r[-200:300]
set yr[0:60]
set datafile separator " "
 
plot \
  "hivemall_twitter2d.dat" using 1:2 with lines title "x" axes x1y2, \
  "hivemall_twitter2d.dat" using 1:3 with lines title "outlier" axes x1y1

myui

/*
 * Hivemall: Hive scalable Machine Learning Library
 *
 * Copyright (C) 2015 Makoto YUI
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *         http://www.apache.org/licenses/LICENSE-2.0

myui

Item-base collabolative filtering

1. Prepare transaction table

Prepare following transaction table. We are generating feature_vector for each item_id based on cooccurrence of purchased items, a sort of bucket analysis.

userid	item_id	purchase_at timestamp
1	31231	2015-04-9 00:29:02
1	13212	2016-05-24 16:29:02

myui

run: +main

_export:
  td:
    apikey: ${TD_API_KEY}
    database: criteo
    engine: hive

+main:
  +prepare:

myui

/*
 * Hivemall: Hive scalable Machine Learning Library
 *
 * Copyright (C) 2015 Makoto YUI
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *         http://www.apache.org/licenses/LICENSE-2.0

myui

/*
 * Hivemall: Hive scalable Machine Learning Library
 *
 * Copyright (C) 2015 Makoto YUI
 * Copyright (C) 2013-2015 National Institute of Advanced Industrial Science and Technology (AIST)
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *