SGBAU · Third Year B.E. Artificial Intelligence and Data Science · NEP 2020
Data Analytics
6AD231PC · Semester VI · 3 credits · IE 40 + ESE 60
Unit 1: Foundations of Data Analytics and the Analytics Lifecycle
8 hoursThe scope of data analytics — descriptive, diagnostic, predictive and prescriptive — BI versus data science versus big data, the five Vs, the analytics lifecycle from discovery to operationalising, CRISP-DM, roles in the analytics ecosystem, and data ethics and privacy.
Examined in the 60-mark end-semester paper
- Classification of analytics
- Characteristics of big data
- Data analytics life cycle
- Data science lifecycle: CRISP-DM
- Informed consent and the five Cs of data ethics
Unit 2: Data Preparation and Data Management
7 hoursData types and scales, collecting from multiple sources, integration, data-quality issues, missing values and outliers, transformation and aggregation; relational databases and SQL for analytics — GROUP BY, joins, subqueries and window functions; data warehousing with star and snowflake schemas, and ETL versus ELT.
Examined in the 60-mark end-semester paper
- Data integration and transformation
- Handling missing data
- Outlier detection: z-score and IQR
- Aggregate functions and set operations
- Data warehouse schemas
- ETL pipelines
Unit 3: Descriptive and Diagnostic Analytics
7 hoursDescriptive statistics and summary measures, KPIs, exploratory data analysis, correlation and covariance, trends and patterns, segmentation, root-cause analysis, hypothesis testing and regression, with business-analytics case studies.
Examined in the 60-mark end-semester paper
- Exploratory data analysis
- Measures of central tendency and spread
- Correlation and covariance
- KPIs, metrics and briefing books
- Linear and logistic regression
Unit 4: Data Visualisation and Analytics Communication
7 hoursVisualisation in BI, data and task abstraction and the four levels of validation, pre-attentive attributes and perception, ethical and misleading charts; scalar, multidimensional, heat-map, cluster, treemap, sunburst and network visualisations; Matplotlib and Seaborn, dashboard design, Tableau and Power BI, and storytelling with data.
Examined in the 60-mark end-semester paper
- Big data visualisation techniques
- Human perception and information processing
- Matplotlib and Seaborn
- Visualisation with Tableau
- Power BI reports and dashboards
Unit 5: Python and Excel for Data Analytics
8 hoursNumPy arrays and vectorised computation, pandas data structures, loading data and file formats, cleaning and transforming data, strings and missing data, descriptive statistics and plotting; Excel — cleaning, sorting, filtering, lookups, pivot tables and conditional formatting, and the Analysis ToolPak for statistics, correlation, regression, ANOVA, moving averages and exponential smoothing.
Examined in the 60-mark end-semester paper
- NumPy arrays and broadcasting
- Pandas data frames
- Excel functions, lookups and data cleaning
- PivotTables and PivotCharts
Unit 6: Big Data Tools
7 hoursBig-data storage, the Hadoop ecosystem, HDFS and MapReduce, the limits of MapReduce, Apache Spark and how it compares with Hadoop, and NoSQL.
Examined in the 60-mark end-semester paper
- Big data technologies
- Hadoop and MapReduce in the cloud
- NoSQL and its business drivers
Unit contents are summarised from the official SGBAU syllabus . AiCanCode.org is not affiliated with Sant Gadge Baba Amravati University (SGBAU).