Machine Learning and Trend Analysis in PHP - DevDays Vilnius

TREND ANALYSIS AND MACHINE LEARNING IN PHP DEVDAYS VILNIUS 2018
@MICHAELCULLUMUK

@MICHAELCULLUMUK SLIDO: #K100 ME?

MICHAEL CULLUM @MICHAELCULLUMUK

@MICHAELCULLUMUK SLIDO: #K100 STATISTICS

@MICHAELCULLUMUK SLIDO: #K100 ARTIFICIAL INTELLIGENCE

@MICHAELCULLUMUK SLIDO: #K100 MACHINE LEARNING

@MICHAELCULLUMUK LEARNING Cause  &  Effect Context Process Knowledge

@MICHAELCULLUMUK USING Cause Knowledge Process Prediction  of an  effect

@MICHAELCULLUMUK Cause Knowledge Process Process Cause Predicted  effect Effect

@MICHAELCULLUMUK EXAMPLE 1+1= 2 1+2= 3 1+3= 4 2+1= 3
3+1= 4 Cause Effect

3+1= 4 Knowledge

3+1= 4 Cause 3+1= Predicted Effect 4 Knowledge

@MICHAELCULLUMUK INFERENCE 1x + 3 = 4 1x + 4
= 4 1x + 3 = 5 2x + 3 = 7 1x + 4 = ? x = 10

@MICHAELCULLUMUK INFERENCE “eggs”

@MICHAELCULLUMUK SLIDO: #K100 MACHINE LEARNING AS A 4-STEP PROCESS

@MICHAELCULLUMUK SLIDO: #K100 1. ACQUIRE DATA

@MICHAELCULLUMUK SLIDO: #K100 2. TRAIN MODEL

@MICHAELCULLUMUK SLIDO: #K100 3. ASK YOUR QUESTION

@MICHAELCULLUMUK SLIDO: #K100 4. GET PREDICTED ANSWER

@MICHAELCULLUMUK SLIDO: #K100 1. ACQUIRE DATA

@MICHAELCULLUMUK SLIDO: #K100 GOOD LUCK

@MICHAELCULLUMUK SLIDO: #K100 2. TRAIN MODEL

@MICHAELCULLUMUK SLIDO: #K100 SUPERVISED LEARNING UNSUPERVISED LEARNING

@MICHAELCULLUMUK SLIDO: #K100 SUPERVISED LEARNING

@MICHAELCULLUMUK SLIDO: #K100 KNOWN OUTCOMES

@MICHAELCULLUMUK SLIDO: #K100 QUALITATIVE - REGRESSION QUANTATIVE - CLASSIFICATION

@MICHAELCULLUMUK SLIDO: #K100 CLASSIFICATION Rating Conclusion 100 Good 25 Bad
50 Good 40 Bad

@MICHAELCULLUMUK SLIDO: #K100 LINEAR CLASSIFIER Item Value Black PHP  Devs
White Sales Sales Test PHP Test

@MICHAELCULLUMUK SLIDO: #K100 QUALITATIVE - REGRESSION QUANTATIVE - CLASSIFICATION

@MICHAELCULLUMUK SLIDO: #K100 REGRESSION Price % alcohol 5.00 8.25 6.00
10 4.00 6.75 3.00 5 0 2.5 5 7.5 10 0 1.5 3 4.5 6

@MICHAELCULLUMUK SLIDO: #K100 UNSUPERVISED LEARNING

@MICHAELCULLUMUK SLIDO: #K100 DISCOVERY

@MICHAELCULLUMUK SLIDO: #K100 ASSOCIATION  CLUSTERING

@MICHAELCULLUMUK SLIDO: #K100 ASSOCIATION Item 1 Item 2 T-shirt Shorts
Shorts T-shirt Suit Black Shoes Socks Underwear Item 1 Item 2 Black shoes Suit Socks Underwear Underwear Socks T-shirt Socks

Shorts T-shirt Suit Black Shoes Socks Underwear Item 1 Item 2 Black shoes Suit Socks Underwear Underwear Socks T-shirt Socks People who buy socks,  also often buy underwear People who who buy  underwear always buy  socks

Shorts T-shirt Suit Black Shoes Socks Underwear Item 1 Item 2 Black shoes Suit Socks Underwear Underwear Socks T-shirt Socks People who buy socks,  also often buy underwear People who buy suits  always buy black shoes People who who buy  underwear always buy  socks People who buy black  shoes, always buy suits

Shorts T-shirt Suit Black Shoes Socks Underwear Item 1 Item 2 Black shoes Suit Socks Underwear Underwear Socks T-shirt Socks People who buy socks,  also often buy underwear People who buy suits  always buy black shoes People who who buy  underwear always buy  socks People who buy black  shoes, always buy suits People who buy shorts  always buy t-shirts People who buy t-shirts,  also often buy shorts

@MICHAELCULLUMUK SLIDO: #K100 ASSOCIATION  CLUSTERING

@MICHAELCULLUMUK SLIDO: #K100 CLUSTER ANALYSIS IS THE TASK OF GROUPING
A SET OF OBJECTS IN SUCH A WAY THAT OBJECTS IN THE SAME GROUP ARE MORE SIMILAR TO EACH OTHER THAN TO THOSE IN OTHER GROUPS.

@MICHAELCULLUMUK SLIDO: #K100 CLUSTER ANALYSIS

@MICHAELCULLUMUK SLIDO: #K100 3. QUESTION  4. PREDICTED ANSWER

@MICHAELCULLUMUK SLIDO: #K100 ALGORITHMS

@MICHAELCULLUMUK SLIDO: #K100 LEAST SQUARES

@MICHAELCULLUMUK SLIDO: #K100 LEAST SQUARES REGRESSION LINE

@MICHAELCULLUMUK SLIDO: #K100 MATHS

@MICHAELCULLUMUK SLIDO: #K100 A+BX=Y

@MICHAELCULLUMUK SLIDO: #K100 ▸ Each point has an x and
y value ▸ We need an equation of a line ▸ We move the line an inﬁnite number of times ▸ Each time, we draw a box between every point, and the line, with one corner on the line, and another on the point ▸ The correct line is the one where the sum of the area of all the squares is smallest PROCESS

@MICHAELCULLUMUK SLIDO: #K100 DEMO

@MICHAELCULLUMUK SLIDO: #K100 PHP

@MICHAELCULLUMUK SLIDO: #K100 DEMOS php-ai/php-ml

@MICHAELCULLUMUK SLIDO: #K100 CODE $samples = [[60], [61], [62], [63],
[65]]; $targets = [3.1, 3.6, 3.8, 4, 4.1]; $regression = new LeastSquares(); $regression->train($samples, $targets); echo $regression->predict([64]);

@MICHAELCULLUMUK SLIDO: #K100 NEAREST NEIGHBOUR

@MICHAELCULLUMUK SLIDO: #K100 3-NEAREST NEIGHBOUR

@MICHAELCULLUMUK SLIDO: #K100 5-NEAREST NEIGHBOUR

@MICHAELCULLUMUK SLIDO: #K100 MATHS

@MICHAELCULLUMUK SLIDO: #K100 PHP

@MICHAELCULLUMUK SLIDO: #K100 DEMO 0 1 2 3 4 0
1 2 3 4

@MICHAELCULLUMUK SLIDO: #K100 DEMO 0 1.25 2.5 3.75 5 0
1 2 3 4

@MICHAELCULLUMUK SLIDO: #K100 DEMO $samples = [[1, 3], [1, 4],
[2, 4], [3, 1], [4, 1], [4, 2]]; $labels = ['a', 'a', 'a', 'b', 'b', 'b']; $classifier = new KNearestNeighbors(); $classifier->train($samples, $labels); echo $classifier->predict([3, 2]);

@MICHAELCULLUMUK SLIDO: #K100 USES OF MACHINE LEARNING

@MICHAELCULLUMUK SLIDO: #K100 NUMERICAL ANALYSIS

@MICHAELCULLUMUK SLIDO: #K100 EXCEPTIONS

@MICHAELCULLUMUK SLIDO: #K100 E-COMMERCE

@MICHAELCULLUMUK SLIDO: #K100 FAULT DETECTION

@MICHAELCULLUMUK SLIDO: #K100 ROOT CAUSE ANALYSIS

@MICHAELCULLUMUK SLIDO: #K100 CLASSIFICATION

@MICHAELCULLUMUK SLIDO: #K100 NATURAL LANGUAGE PROCESSING

@MICHAELCULLUMUK SLIDO: #K100 ANALYSIS OF SUPPORT QUERIES

@MICHAELCULLUMUK SLIDO: #K100 ANALYSIS OF LARGE NUMBERS OF DOCUMENTS

@MICHAELCULLUMUK SLIDO: #K100 FUN

@MICHAELCULLUMUK SLIDO: #K100 ANY QUESTIONS?

THANKS - AČIŪ @MICHAELCULLUMUK

TREND ANALYSIS AND MACHINE LEARNING IN PHP DEVDAYS VILNIUS 2018
@MICHAELCULLUMUK

Machine Learning and Trend Analysis in PHP - De...

Machine Learning and Trend Analysis in PHP - DevDays Vilnius

More Decks by Michael C.

Other Decks in Programming

Featured

Transcript