kaopanboonyuen/GISTDA2022

Geospatial Big Data Analytics 2022

Geospatial Big Data Analytics (GISTDA Training 2022)

Lecturer: Teerapong Panboonyuen (Kao), Ph.D.

Contact: panboonyuen.kao@gmail.com

Short links for lecture slide and exercises:

Morning Survey: https://forms.gle/NHzWFi2W7QWi9JnM7

Lecture Slides: https://github.com/kaopanboonyuen/GISTDA2022/tree/main/lecture_slides

Module 0: Visualization

Google Data Studio: https://datastudio.google.com/

1. Disaster Tweets (Data Set): https://github.com/kaopanboonyuen/GISTDA2022/raw/main/dataset/visualize/disaster_text.csv
2. Med Resource (Data Set): https://github.com/kaopanboonyuen/GISTDA2022/raw/main/dataset/visualize/med_resources_text.csv

Module 1: PySpark

0. PySpark Transform and Action:
1. Basic PySpark:
2. Basic RDD:
3. Spark SQL:
4. Basic DataFrame:
5. Classification:
6. Clustering:

Module 2: PySpark (Assignment)

1. Titatic DataSet:
2. Iris DataSet (Classification):

Module 3: Deep Learning (Convolution Neural Networks)

Basic Convolution Neural Networks:

** Lecture Slide (from https://cs231n.stanford.edu/): http://cs231n.stanford.edu/slides/2021/lecture_5.pdf

Reference:

1. https://www.kaggle.com/code
2. https://www.tensorflow.org/tutorials
3. https://github.com/topics/machine-learning
4. https://archive.ics.uci.edu/ml/datasets.php
5. https://www.analyticsvidhya.com/blog/2021/12/disaster-tweet-classification-using-bert-neural-network/
6. http://cs231n.stanford.edu/slides/2021/lecture_5.pdf