Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Machine Learning in Production with R or Python...
Search
szilard
June 08, 2017
0
190
Machine Learning in Production with R or Python - Budapest Data Forum - June 2017
szilard
June 08, 2017
Tweet
Share
More Decks by szilard
See All by szilard
Gradient Boosting Machines (GBM): From Zero to Hero (with R and Python Code) - Data Con LA - Oct 2020
szilard
0
190
Make Machine Learning Boring Again: Best Practices for Using Machine Learning in Businesses - Albuquerque Machine Learning Meetup (Online) - Aug 2020
szilard
0
130
Better than Deep Learning: Gradient Boosting Machines (GBM) - eRum conference - invited talk - June 2020
szilard
0
120
Gradient Boosting Machines (GBM): From Zero to Hero (with R and Python Code) - LA Data Science Meetup - February 2020
szilard
0
110
A Random Walk in Data Science and Machine Learning in Practice - CEU, Business Analytics Masters - Budapest, Febr 2020
szilard
0
300
Better than My Meetup/Conference Talks: Going Deeper in Various GBM Topics - GBM Advanced Workshop - Budapest, Nov 2019
szilard
0
77
Gradient Boosting Machines (GBM): From Zero to Hero (with R and Python Code) - Budapest BI Forum, Budapest, Nov 2019
szilard
0
150
Make Machine Learning Boring Again: Best Practices for Using Machine Learning in Businesses - LA Data Science Meetup - Playa Vista, August 2019
szilard
0
120
Better than Deep Learning: Gradient Boosting Machines (GBM) / 2019 edition - Budapest R and Data Science Meetups - Budapest, June 2019
szilard
0
95
Featured
See All Featured
Rails Girls Zürich Keynote
gr2m
95
14k
It's Worth the Effort
3n
187
28k
A Tale of Four Properties
chriscoyier
160
23k
How to train your dragon (web standard)
notwaldorf
96
6.3k
Learning to Love Humans: Emotional Interface Design
aarron
274
40k
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
Become a Pro
speakerdeck
PRO
29
5.5k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Building Better People: How to give real-time feedback that sticks.
wjessup
368
20k
Thoughts on Productivity
jonyablonski
70
4.9k
Making Projects Easy
brettharned
119
6.4k
Being A Developer After 40
akosma
91
590k
Transcript
Machine Learning in Production Szilárd Pafka, PhD Chief Scientist, Epoch
Budapest Data Forum June 2017
Machine Learning in Production with R Szilárd Pafka, PhD Chief
Scientist, Epoch Budapest Data Forum June 2017
Machine Learning in Production with R or Python Szilárd Pafka,
PhD Chief Scientist, Epoch Budapest Data Forum June 2017
Machine Learning in Production with R or maybe Python Szilárd
Pafka, PhD Chief Scientist, Epoch Budapest Data Forum June 2017
None
Disclaimer: I am not representing my employer (Epoch) in this
talk I cannot confirm nor deny if Epoch is using any of the methods, tools, results etc. mentioned in this talk
None
http://datascience.la/meetup-machine-learning-in-production-with-szilard-pafka/
None
None
None
None
None
None
None
None
None
None
None
None
None
Aggregation 100M rows 1M groups Join 100M rows x 1M
rows time [s] time [s]
Aggregation 100M rows 1M groups Join 100M rows x 1M
rows time [s] time [s]
None
None
None
None
binary classification, 10M records numeric & categorical features, non-sparse
http://www.cs.cornell.edu/~alexn/papers/empirical.icml06.pdf http://lowrank.net/nikos/pubs/empirical.pdf
http://www.cs.cornell.edu/~alexn/papers/empirical.icml06.pdf http://lowrank.net/nikos/pubs/empirical.pdf
None
None
None
None
None
EC2
n = 10K, 100K, 1M, 10M, 100M Training time RAM
usage AUC CPU % by core read data, pre-process, score test data
n = 10K, 100K, 1M, 10M, 100M Training time RAM
usage AUC CPU % by core read data, pre-process, score test data
None
None
None
None
None
None
None
10x
None
None
None
None
None
http://datascience.la/benchmarking-random-forest-implementations/#comment-53599
None
None
None
None
None
None
None
Best linear: 71.1
None
None
learn_rate = 0.1, max_depth = 6, n_trees = 300 learn_rate
= 0.01, max_depth = 16, n_trees = 1000
None
None
None
None
None
None
None
None
None
None
None
None
None
None
...
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None
None