Course:FRE521D
| FRE 521D: Data Analytics in Climate, food and Environment | |
|---|---|
 | |
| FRE 521D | |
| Section: | |
| Instructor: | TBD |
| Email: | TBD |
| Office: | TBA |
| Office Hours: | TBA |
| Class Schedule: | Feb 24 to April 11
Tue/Thu from 10:00- 11:30 AM |
| Classroom: | MCML 154 |
| Important Course Pages | |
| Syllabus | |
| Lecture Notes | |
| Assignments | |
| Course Discussion | |
COURSE DESCRIPTION
In this course we will explore data and try to find patterns. We will look at the field of data science, using R, SQL, and Python to move through a data pipeline, from database, through some data wrangling, data visualization and inference.
LEARNING OUTCOMES
1. Machine Learning Fundamental
- Terminology and Building Models
- Machine learning approaches: regression, classification, clustering, decision trees and random forest.
- Best and worst practices of managing machine learning projects.
- Machine Learning pipeline development and value
- Application: Climate Example: Assessment of ESG compliance by firms
2. SQL
- Intro ( significance of SQL in data analysis and the modern job market, Understanding databases: Why are they essential?)
- Databases
- Different types of databases: Relational vs. Non-relational
- Introduction to RDBMS (Relational Database Management System) structure
- Intro to SQL
- Basic SQL Queries ( ‘Select’, ‘Distinct’, ‘Where’, ‘Order by’, ‘Limit’
- Functions and aggregation
- Basic functions: ‘count()’, ‘sum()’, ‘AVG()’, ‘MIN()’ ,‘Max()’
- Grouping data using ‘GROUP BY’
- Filtering on aggregated data using ‘HAVING’
- Joins and relationship.
- Best and worst practices of managing machine learning projects.
- Application: Climate Example: https://wbwaterdata.org/dataset/waterbase-water-quality.
3. Data Access and Querying on Cloud Based Platforms: API methods.
- Data formats of CSV, JSON, or XML and how to accesss
- Data wrangling, data cleaning, and preliminary visualization with Python
- Advantages and disadvantages of the major data formats
- Determining the best match between data formats and select analysis.
REAL-WORLD APPLICATIONS IN CLIMATE, FOOD & ENVIRONMENT
Machine Learning is the tool for analyzing big data and increasingly food and environment application have a big data component. This course will apply the data tools to areas such as ESG assessment, climate impact, and business ratings.
Career Relevance: Highlight how the course aligns with prospective career paths, emphasizing real-world applicability.
Businesses such as banks (lending assessment), agribusinesses (precision ag) are increasingly reliant on SQL and machine learning for assessments and predictive analytics.
Major project provides the opportunity to practice and data skills to a real-world data set.
- How can we transition to making data-driven decisions?
- How to use data and numbers to tell a story which will influence decision makers?
ASSESSMENT METHODS
| Activity | % of Grade |
|---|---|
| Assignments / Labs | 20% |
| Project | 30% |
| Quizz | 10% |
| Participation | 10% |
| Midterm | 30% |
| Total | 100% |