�ݺ�ߣ

MaM Machine Learning
Study group
Speaker Session - 17/04/2019
https://www.meetup.com/MaM-Machine-Learning-Study-Group/

Thanks to our host and sponsor
Imperial College Data Science Institute
Recworks Meet a Mentor community
https://recworks.co.uk/ https://meetamentor.co.uk

Agenda
Introduction to data analysis and data cleaning
By Mark Bell
Study group: the story so far
By Dave Snowdon and Jeremie Charlet

Study group
The story so far
Jeremie Charlet & Dave Snowdon

Agenda
How we work
What we��ve learnt
House prices project
IMDB Reviews project
Next steps

The power of the mob
Slack for group coordination
During a study session
�� One person ��drives��
�� Everyone else contributes suggestions
�� New ��driver�� each session
�� Everyone literally on the same page
�� Allows people to get up to speed without being put on the spot

Id,MSSubClass,MSZoning,LotFrontage,LotArea,Street,Alley,LotShape,LandContour,Utilities,LotConfig,La
ndSlope,Neighborhood,Condition1,Condition2,BldgType,HouseStyle,OverallQual,OverallCond,YearBuilt,Y
earRemodAdd,RoofStyle,RoofMatl,Exterior1st,Exterior2nd,MasVnrType,MasVnrArea,ExterQual,ExterCon
d,Foundation,BsmtQual,BsmtCond,BsmtExposure,BsmtFinType1,BsmtFinSF1,BsmtFinType2,BsmtFinSF
2,BsmtUnfSF,TotalBsmtSF,Heating,HeatingQC,CentralAir,Electrical,1stFlrSF,2ndFlrSF,LowQualFinSF,Gr
LivArea,BsmtFullBath,BsmtHalfBath,FullBath,HalfBath,BedroomAbvGr,KitchenAbvGr,KitchenQual,TotRm
sAbvGrd,Functional,Fireplaces,FireplaceQu,GarageType,GarageYrBlt,GarageFinish,GarageCars,Garage
Area,GarageQual,GarageCond,PavedDrive,WoodDeckSF,OpenPorchSF,EnclosedPorch,3SsnPorch,Scre
enPorch,PoolArea,PoolQC,Fence,MiscFeature,MiscVal,MoSold,YrSold,SaleType,SaleCondition,SalePric
e
1,60,RL,65,8450,Pave,NA,Reg,Lvl,AllPub,Inside,Gtl,CollgCr,Norm,Norm,1Fam,2Story,7,5,2003,2003,Gab
le,CompShg,VinylSd,VinylSd,BrkFace,196,Gd,TA,PConc,Gd,TA,No,GLQ,706,Unf,0,150,856,GasA,Ex,Y,S
Brkr,856,854,0,1710,1,0,2,1,3,1,Gd,8,Typ,0,NA,Attchd,2003,RFn,2,548,TA,TA,Y,0,61,0,0,0,0,NA,NA,NA,0
,2,2008,WD,Normal,208500
2,20,RL,80,9600,Pave,NA,Reg,Lvl,AllPub,FR2,Gtl,Veenker,Feedr,Norm,1Fam,1Story,6,8,1976,1976,Gabl
e,CompShg,MetalSd,MetalSd,None,0,TA,TA,CBlock,Gd,TA,Gd,ALQ,978,Unf,0,284,1262,GasA,Ex,Y,SBrk
r,1262,0,0,1262,0,1,2,0,3,1,TA,6,Typ,1,TA,Attchd,1976,RFn,2,460,TA,TA,Y,298,0,0,0,0,0,NA,NA,NA,0,5,2
007,WD,Normal,181500

Kaggle house prices
�� Given a data set with information about house & area predict house price
�� Lots of fumbling around in the dark
�� Gradually got to grips with scikit learn and pandas
�� From machinelearningmastery.com learnt to use a methodology
�� Tried with and without outliers
�� Tried various models: linear regression, random forest, simple NN
�� Experimented with mapping categorical values
�� Tried using RFE and random forest to find most important fields

Methodology
5-Step Systematic Process
1. Define the Problem
2. Prepare Data
3. Spot Check Algorithms
4. Improve Results
5. Present Results
https://machinelearningmastery.com/process-for-working-through-machine-learning-problems/

It��s harder than it looks!
�� Keep your data & labels separate!
�� How to Prevent Catastrophic Failure in Production ML Systems, Martin Goodson��, QCon
London 2019
�� Need a methodology - or can get overwhelmed by all the possibilities
�� If it looks too good to be true...
callingbullshit.org

IMDB Movie Review
sentiment analysis

Learnings - IMDB Reviews project
Problem: Given (long) movie review as plain text
Decide: is review positive or negative?
'This is one of the silliest movies I have ever had the misfortune to watch! I should have expected it, after seeing the first two, but I keep
getting suckered into these types of movies with the idea of "Maybe they did it right this time". Nope - not even close. Where do I
begin? How about with the special effects... To give you an idea of what passes for SFX in this movie, at one point a soldier is shooting
at a "Raptor" as it runs down a hallway. Even with less than a second of screen time, the viewer can easily see that it is just a man with
a tail apparently taped to him running around. Bad bad bad bad. How about the acting? If that's what you can call it. There is one
character who, I suppose, is supposed to be from the south. However, after living in the south for six years now, I have never heard this
way of talking. Perhaps he has some sort of weird disability - the inability to talk normally. I find it fascinating that the character does
nothing that requires him to have that accent - therefore there was no reason for the actor to try to do one. How about the plot? It��s
pretty basic - Raptors escape, people with guns must hunt them down. I��m starting to wonder why the dinosaurs in these movies
always seem to run into the nearest system of tunnels... wouldn��t they stay outside to hunt prey? ...

processing text data
vectorization techniques

The dog is on the table
processing text data
vectorization techniques
[ 0, 1, 1, 0, 0, 0, 2, �� ]
[Cat dog table monkey movie man the �� ]
[12, 908, 35, 45, 12, 13]
12 The
...
908 Dog

Read research papers to create models
Learn/practice with both scikit learn for ML and Keras for DL
Discovered different neural network architectures: CNN, LSTM

compared multiple ML and DL architectures

Next steps
Start new project
Mob v2
�� Pomodoros
�� Mob + pair work
�� With homework (reading articles or research papers)
Follow our methodology from start to finish
Join us: https://www.meetup.com/MaM-Machine-Learning-Study-Group/

�ݺ�ߣ

Machine learning study group 17 4 2019

Recommended

More Related Content

Similar to Machine learning study group 17 4 2019 (20)

More from Jeremie Charlet (10)

Recently uploaded (20)

Machine learning study group 17 4 2019

Editor's Notes