Scikit-Learn Intro to Data Science Presented by: Vishnu Karnam A01962610.

Slides:



Advertisements
Similar presentations
Data analysis Lecture 10 Tijl De Bie.
Advertisements

Ordinary Least-Squares
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
1 Non-Linear and Smooth Regression Non-linear parametric models: There is a known functional form y=  x,  derived from known theory or from previous.
1 CPC group SeminarThursday, June 1, 2006 Classification techniques for Hand-Written Digit Recognition Venkat Raghavan N. S., Saneej B. C., and Karteek.
CS Statistical Machine learning Lecture 13 Yuan (Alan) Qi Purdue CS Oct
Minimum Redundancy and Maximum Relevance Feature Selection
MRA basic concepts Jyun-Ming Chen Spring Introduction MRA (multi- resolution analysis) –Construct a hierarchy of approximations to functions in.
Chapter 10 Regression. Defining Regression Simple linear regression features one independent variable and one dependent variable, as in correlation the.
Fei Xing1, Ping Guo1,2 and Michael R. Lyu2
Principal Component Analysis CMPUT 466/551 Nilanjan Ray.
Multivariate Methods Pattern Recognition and Hypothesis Testing.
Linear Methods for Regression Dept. Computer Science & Engineering, Shanghai Jiao Tong University.
Principal Component Analysis
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
The Terms that You Have to Know! Basis, Linear independent, Orthogonal Column space, Row space, Rank Linear combination Linear transformation Inner product.
Data Preprocessing in Python
Linear and generalised linear models Purpose of linear models Least-squares solution for linear models Analysis of diagnostics Exponential family and generalised.
Machine Learning Usman Roshan Dept. of Computer Science NJIT.
Overview DM for Business Intelligence.
Summarized by Soo-Jin Kim
Presented By Wanchen Lu 2/25/2013
Machine Learning CUNY Graduate Center Lecture 3: Linear Regression.
Machine Learning in Spoken Language Processing Lecture 21 Spoken Language Processing Prof. Andrew Rosenberg.
Machine Learning CSE 681 CH2 - Supervised Learning.
Data Reduction. 1.Overview 2.The Curse of Dimensionality 3.Data Sampling 4.Binning and Reduction of Cardinality.
Basics of Neural Networks Neural Network Topologies.
Using Support Vector Machines to Enhance the Performance of Bayesian Face Recognition IEEE Transaction on Information Forensics and Security Zhifeng Li,
Dimensionality Reduction Motivation I: Data Compression Machine Learning.
Linear Discrimination Reading: Chapter 2 of textbook.
Principal Component Analysis Machine Learning. Last Time Expectation Maximization in Graphical Models – Baum Welch.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
1  The Problem: Consider a two class task with ω 1, ω 2   LINEAR CLASSIFIERS.
Matrix Notation for Representing Vectors
Principle Component Analysis and its use in MA clustering Lecture 12.
Data Mining and Decision Support
Data analysis tools Subrata Mitra and Jason Rahman.
Principal Component Analysis Zelin Jia Shengbin Lin 10/20/2015.
Competition II: Springleaf Sha Li (Team leader) Xiaoyan Chong, Minglu Ma, Yue Wang CAMCOS Fall 2015 San Jose State University.
Feature Selection and Extraction Michael J. Watts
METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Part 9: Review.
Advanced Artificial Intelligence Lecture 8: Advance machine learning.
Computacion Inteligente Least-Square Methods for System Identification.
SUPERVISED AND UNSUPERVISED LEARNING Presentation by Ege Saygıner CENG 784.
Data Summit 2016 H104: Building Hadoop Applications Abhik Roy Database Technologies - Experian LinkedIn Profile:
Part 3: Estimation of Parameters. Estimation of Parameters Most of the time, we have random samples but not the densities given. If the parametric form.
Machine Learning Usman Roshan Dept. of Computer Science NJIT.
Machine Learning Supervised Learning Classification and Regression K-Nearest Neighbor Classification Fisher’s Criteria & Linear Discriminant Analysis Perceptron:
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Data Transformation: Normalization
ECE 471/571 - Lecture 19 Review 02/24/17.
Dimensionality Reduction
CH 5: Multivariate Methods
The Elements of Statistical Learning
Predict House Sales Price
Simple Linear Regression - Introduction
Probabilistic Models with Latent Variables
Principal Component Analysis
What is Regression Analysis?
ECE 471/571 – Review 1.
The Multiple Regression Model
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Intro to Machine Learning
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Data Transformations targeted at minimizing experimental variance
Analysis for Predicting the Selling Price of Apartments Pratik Nikte
Using Manifold Structure for Partially Labeled Classification
CAMCOS Report Day December 9th, 2015 San Jose State University
What is Artificial Intelligence?
ECE – Pattern Recognition Midterm Review
Presentation transcript:

Scikit-Learn Intro to Data Science Presented by: Vishnu Karnam A

Linear Regression in Mathematical form Given a Data set {y i,x 1i,x 2i …….,x ip } LR assumes that dependent variable Y i is linearly dependent on x vector. The relationship is modeled through a random error variable ε i Thus the equation can now be represented as Y i = β 1 x 1i + β 2 x 2i + …….. + β p x pi + ε i Y i = x T i β + ε i These set of equations are stacked and written in vector form as Y = X β + ε Where Y, X and ε represented as

Cont…

After mathematical representation, estimation methods are used to determine the parameters. The estimation method consists of Objective function and the parameters are set either to maximize or minimize the objective function. In machine learning we will have set of parameters that are calculated based on given data points.

Dimensionality Reduction Some of the famous Dimensionality Reduction Algorithms are 1)Principal Component Analysis 2)Incremental PCA 3)Approximate PCA 4) Kernal PCA 5) Linear Discriminant Analysis

Basic Idea The general idea behind all these algorithms Project the data on set of Orthogonal components Generally most of the algorithms use Eigen vectors Find the minimum number of components that is a representation of whole data.

PCA on IRIS data

Cross Validation and Metrics Once the models are prepared we need to test the model based on testing data. Various Cross Validation techniques present in SciKit-learn are K-fold Stratified k-fold Leave one out

Preprocessing Some of the algorithms require preprocessing of data so that the estimation methods in the algorithms perform better. Ex: PCA algorithm works on data with mean centered and normalized data. Some useful functions are Scale MinMaxScaler Normalize

Binarization, Encoding and Imputation of Missing Values Binarization is used to convert quantitative value to binary value. Encoding is used to convert categorical features as integers. Imputation allows to insert missing data with mean, median or with frequent data.