DataMining(1)_Know Your Data

Data Objects and Attribute Types

Record
- Relational records
- Data matrix, e.g., numerical matrix, crosstabs
- Document data: text documents: term-frequency vector
- Transaction data
Graph and network
- World Wide Web
- Social or information networks
- Molecular Structures
Ordered
- Video data: sequence of images
- Temporal data: time-series
- Sequential Data: transaction sequences
- Genetic sequence data
Spatial, image and multimedia:
- Spatial data: maps
- Image data:
- Video data

Data Objects:Data sets are made up of data objects.
A data objectrepresents an entity.

Attributes
Attribute (ordimensions, features, variables): a data field, representing a characteristic or feature of a data object.
Nominal
Binary
Ordinal
Quantity(integer or real-valued)
Interval
Ratio

Basic Statistical Descriptions of Data

1. Motivation

   Measuring the Central Tendency
   Mean (algebraic measure) (sample vs. population)
   Median
   Mode
   

   Measuring the Dispersion of Data
   Quartiles, outliers and boxplots
   Variance and standard deviation (sample:s, population: σ)
   Five-number summary
   Boxplot

Graphic Displays of Basic Statistical Descriptions
Boxplot
Histogram
Quantile plot

Quantile-quantile (q-q) plot

Scatter plot

Data dispersion characteristics
Numerical dimensions
Dispersion analysis on computed measures

Data Visualization

Categorization of visualization methods:
Pixel-oriented visualization techniques

Geometric projection visualization techniques

Icon-based visualization techniques
1.Chernoff Faces

2.Stick Figures
Hierarchical visualization techniques
1.Dimensional Stacking
2.Worlds-within-Worlds
3.Tree-Map
4.InfoCube
5.Three-D Cone Trees
Visualizing complex data and relations

Measuring Data Similarity and Dissimilarity

Similarity
Data matrix

Dissimilarity
Dissimilarity matrix

Proximity
Simple matching

A contingency table for binary data

Distance measure for symmetric binary variables

Distance measure for asymmetric binary variables

Jaccard coefficient

Jaccard coefficient is the same as “coherence”:

Standardizing Numeric Data

Minkowski distance: A popular distance measure
L-h norm:

h= 1: Manhattan distance
h = 2: (L2 norm)Euclidean distance
h →∞. “supremum”(Lmax norm, L∞norm) distance.

Ordinal Variables

Attributes of Mixed Type

Cosine Similarity
cos(d1,d2)=(d1•d2)/||d1||||d2||,