2. PRINCIPAL COMPONENT ANALYSIS
(PCA)
INTRODUCTION
PCA is Standard Tool in modern data analysis
It is very useful method for extracting relavant information from confusing
data sets.
DEFINITION
PCA is a statistical procedure that uses an orthogonal transformation to
convert a set of observations of Possibly correlated variables into set of of
values of linearly uncorrealeted variables called Principle Components.
The number of Principle Components is less than or equal to the number of
Orignal Values
4. GOAL'S
The main Goals of a PCA analysis is to Identify the patterns in Data.
PCA aims to detect the Correlation between variables.
It attempt to reduce the dimentionality.
DIMENSIONALITY REDUCTION
It reduces the dimensions of a D-dimensional dataset by projecting it
onto a (k)-dimension subspaces (where k<d) in order to increase the
Computational efficiency while retaining most of the information.
5. TRANSFORMATION
The Transformation is defined in such a way that the first principal component has
the largest possible variance and each succeeding component in turn has the next
highest possible variance.
PCA APPROACH
Standardize the data.
Perform singular Vector Decomposition to get the Eigenvector & Eigenvalues .
Sort Eigenvalues in desending order and choose the k-eigenvectors.
Construct the Projection matrix from the selected k-eigenvectors.
Transform the original dataset via projection matrix to obtain a k-dimentional feature subspace.
Limitation Results of PCA depends upon is the scaling of the variables.
6.
7.
8.
9. CONFUSION MATRIX
It is used to find the relation between Predicted value and Actual value.
If value is True then we can say that it is Actual value.
If the value is gain after some Observation then we can say that it is
Predicted value.
In Other words it is the difference between what we are Visualising and
Reality.
PREDICTED ACTUAL
TRUE POSITIVE Rain Rain
TRUE NEGATIVE Not Rain Not Rain
FALSE POSITIVE Rain Not Rain
FALSE NEGATIVE Not Rain Rain