Introduction to Data Analytics: Data and knowledge, criteria to assess the knowledge, descriptive statistics of the data, inferential statistics, exploratory data analysis, knowledge discovery in data bases, data analysis processes, SEMMA, CRISP-DM, methods, tasks and tools.

Understanding the Data: Attribute understanding, kinds of attributes (nominal, interval, ratio types). Characteristics of one dimensional data, location measures, dispersion measures, and shape measures. Characteristic measures of multidimensional data, data quality, visual analytics of one dimensional data, density plots, box plots, scatter plots. Correlation and covariance. Methods for multidimensional data ( just briefing). Analysis of data pertaining to civil engineering.

Principles of Data Modelling: The four steps of modeling, model classes, black-box models, fitting criteria and score functions, error functions for classification problems, measure of interestingness, closed form algorithm for model fitting. Types of errors. Model validation (briefing on methods). Modelling on the data specific to civil engineering.

Data Preparation: Selection of data, feature selection, selecting top ranked subset of data, cross product, wrapper approach, and correlation based filter. Cleaning data, improving data quality, dealing with missing values, construct data, providing operability, assuring impartiality and maximize efficiency. Complex data types. Implementation of methods on data specific to civil engineering.

Finding patterns in data: Clustering – methods. Hierarchical clustering. Dissimilarity measures, Minkowisci, Euclidian, Manhattan, Chebyshev, and cosine. Deviation measures. Association rules. Brief introduction to self organizing maps. Implementation of methods on data specific to civil engineering.