![GeostatsGuy Lectures](/img/default-banner.jpg)
- Видео 173
- Просмотров 894 081
GeostatsGuy Lectures
США
Добавлен 29 авг 2018
I'm Michael Pyrcz, a Professor in the Cockrell School of Engineering and Jackson School of Geosciences, at The University of Texas at Austin.
I teach and research data analytics, geostatistics and machine learning and I share all of my university educational content with the world!
- 100s of recorded data science lectures
- 100s of well-documented data science workflows in Python
- 50 interactive Python dashboards
I do this to support my students with evergreen content that outlasts the semester and assist working professionals to learn and apply data science.
My goal is accessible and actionable educational content for all, because education changed my life (learn more at michaelpyrcz.com/my-story).
The channel playlists include my university classes:
1. Data Analytics and Geostatistics
2. Spatial Data Analytics and Modeling Modeling
3. Machine Learning
and:
4. Data Science Basics in Python
5. Data Science Interactive Demonstrations
6. Random Talks
I teach and research data analytics, geostatistics and machine learning and I share all of my university educational content with the world!
- 100s of recorded data science lectures
- 100s of well-documented data science workflows in Python
- 50 interactive Python dashboards
I do this to support my students with evergreen content that outlasts the semester and assist working professionals to learn and apply data science.
My goal is accessible and actionable educational content for all, because education changed my life (learn more at michaelpyrcz.com/my-story).
The channel playlists include my university classes:
1. Data Analytics and Geostatistics
2. Spatial Data Analytics and Modeling Modeling
3. Machine Learning
and:
4. Data Science Basics in Python
5. Data Science Interactive Demonstrations
6. Random Talks
09 Data Science Interactive: Monte Carlo Simulation
Data Science Interactive Python Demonstrations: Chapter 09: Monte Carlo Simulation
In this walk-through, I explain the basics of Monte Carlo Simulation (MCS). Essential for:
* doing math with distributions to build uncertainty models
* bootstrap for machine learning model bagging and random forest
* Markov chain Monte Carlo for Bayesian regression, etc.
Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories github.com/GeostatsGuy/Python... . For more complete lectures check out my other RUclips lectures with linked Python workflows and demonstrations:
* Monte Carlo Simulation:
ruclips.net/video/Qb8TsSINpnU/видео.html
* Bootstrap:
ruclips.net/video...
In this walk-through, I explain the basics of Monte Carlo Simulation (MCS). Essential for:
* doing math with distributions to build uncertainty models
* bootstrap for machine learning model bagging and random forest
* Markov chain Monte Carlo for Bayesian regression, etc.
Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories github.com/GeostatsGuy/Python... . For more complete lectures check out my other RUclips lectures with linked Python workflows and demonstrations:
* Monte Carlo Simulation:
ruclips.net/video/Qb8TsSINpnU/видео.html
* Bootstrap:
ruclips.net/video...
Просмотров: 1 232
Видео
08 Data Science Interactive: Central Limit Theorem
Просмотров 6967 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 08: Central Limit Theorem In this walk-through, I explain the central limit theorem. If you work with averaging or summations of random variables then you will encounter the central limit theorem in you data science workflows! Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories github.com...
07 Data Science Interactive: Correlation Coefficients with Outliers
Просмотров 6517 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 07: Correlation Coefficients with Outliers In this walk-through, I explain the concept of correlation for machine learning feature engineering and focus on the limitation of sensitivity to outliers. This then motivates the introduction to the rank correlation coefficient and a comparison between both regular correlation coefficient and ran...
06 Data Science Interactive: Correlation Coefficients
Просмотров 7237 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 06: Correlation Coefficients In this walk-through, I explain the concept of correlation for machine learning feature engineering. Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories @ github.com/GeostatsGuy/PythonNumericalDemos/blob/master/Interactive_Correlation_Coefficient.ipynb . For m...
05 Data Science Interactive: Distribution Transformation for Machine Learning Feature Engineering
Просмотров 7168 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 05: Distribution Transformation for Machine Learning Feature Engineering In this walk-through, I explain the concept of distribution transformation for machine learning feature engineering. Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories @ github.com/GeostatsGuy/PythonNumericalDemos/b...
04 Data Science Interactive: Norms for Machine Learning
Просмотров 6698 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 04: Norms for Machine Learning In this walk-through, I explain the concept of norms for predictive machine learning and then demonstrate the impact of choice of norm on a simple predictive machine learning model, linear regression. Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories @ git...
03 Data Science Interactive: Bayesian Coin Example
Просмотров 6938 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 03: Bayesian Coin Example In this walk-through I demonstrate the Bayesian coin example from Sivia's Bayesian Tutorial (1996, 2006). I use this example in my courses, because I found it very useful to help my students to understand Bayesian updating. I hope that it helps you also! Follow along with the interactive Python code in a Jupyter N...
02 Data Science Interactive: Bayesian Updating
Просмотров 1,3 тыс.8 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 02: Bayesian Updating In this walk-through I demonstrate the basic concepts of Bayesian updating for the case of what is the probability of a thing happening given a positive test with an interactive dashboard and custom plots. Then I show the example of Bayesian updating under the assumption of Gaussian distributed Follow along with the i...
01 Data Science Interactive: Marginal, Joint, Conditional
Просмотров 2,6 тыс.8 месяцев назад
Data Science Interactive Python Demonstrations: Chapter 01: Marginal, Joint and Conditional Probabilities and Distributions In this walk-through I demonstrate the basic concepts of marginal, joint and conditional probabilities and distributions with a simple synthetic mineral mining dataset. Follow along with the interactive Python code in a Jupyter Notebook available in my GitHub repositories ...
16c Data Analytics: Decision Making
Просмотров 2,2 тыс.Год назад
Lecture on decision making in the presence of uncertainty. Follow along with the demonstration workflow in Python: o. Decision making, optimum estimation in the presence of uncertainty: github.com/GeostatsGuy/PythonNumericalDemos/blob/master/Interactive_DecisionMaking.ipynb Follow along with the demonstration workflow in Excel: o. Decision making, optimum estimation in the presence of uncertain...
Data Science Basics: Bootstrap
Просмотров 2,6 тыс.2 года назад
Live Jupyter walk-through of bootstrap for uncertainty modeling in Python. I demonstrate that we can bootstrap to calculate uncertainty, due to data paucity, for any statistic! This should be enough to get anyone started building data analytics workflows in Python. The demonstrated workflow is available at: github.com/GeostatsGuy/PythonNumericalDemos/blob/master/PythonDataBasics_Bootstrap.ipynb...
Data Science Basics: Bivariate Data Visualization
Просмотров 1,6 тыс.2 года назад
Live Jupyter walk-through of basic bivariate data visualization in Python with the matplotlib and Seaborn package. I start from a simple scatter plot and incrementally add complexity with attention to design and composition of plotting elements for improved communication. This should be enough to get anyone started building data analytics workflows in Python. The demonstrated workflow is availa...
Data Science Basics: Univariate Statistics
Просмотров 1,7 тыс.3 года назад
Live Jupyter walk-through of basic univariate statistics in Python.This should be enough to get anyone started building predictive machine learning workflows in Python. The demonstrated workflow is available at: github.com/GeostatsGuy/PythonNumericalDemos/blob/master/PythonDataBasics_Univariate_Statistics.ipynb #DataAnalytics #DataVisualization #DataScience #Statistics
Data Science Basics: Predictive Machine Learning
Просмотров 1,8 тыс.3 года назад
Live Jupyter walk-through of basic predictive machine learning model building in Python with the scikit-learn package.This should be enough to get anyone started building predictive machine learning workflows in Python. The demonstrated workflow is available at: github.com/GeostatsGuy/PythonNumericalDemos/blob/master/PythonDataBasics_PedictiveMachineLearning.ipynb #DataAnalytics #DataVisualizat...
DIRECT 2021 14 Tuning Deep Learning Models Maldonado-Cruz
Просмотров 4633 года назад
DIRECT Consortium at The University of Texas at Austin, working on novel methods and workflows in spatial, subsurface data analytics, geostatistics and machine learning. This is Tuning Ensemble Machine Learning Uncertainty Models by Eduardo Maldonado-Cruz. Join the consortium for access to all graduate student research, papers, codes and demonstration workflows.
DIRECT 2021 10 Deep Learning Multi-scale Modeling
Просмотров 4243 года назад
DIRECT 2021 10 Deep Learning Multi-scale Modeling
DIRECT 2021 11 Machine Learning History Matching
Просмотров 4453 года назад
DIRECT 2021 11 Machine Learning History Matching
DIRECT 2021 12 Scientific Machine Learning
Просмотров 2923 года назад
DIRECT 2021 12 Scientific Machine Learning
DIRECT 2021 13 Multi-scale Neural Networks Santos
Просмотров 5713 года назад
DIRECT 2021 13 Multi-scale Neural Networks Santos
DIRECT 2021 09 Spatial Variogram via CNN
Просмотров 5733 года назад
DIRECT 2021 09 Spatial Variogram via CNN
DIRECT 2021 08 Spatial Statistics for Modeling
Просмотров 3653 года назад
DIRECT 2021 08 Spatial Statistics for Modeling
DIRECT 2021 06 Machine Learning Spatial Bias Mitigation
Просмотров 2213 года назад
DIRECT 2021 06 Machine Learning Spatial Bias Mitigation
DIRECT 2021 07 CRM for scikit-learn Estimator
Просмотров 1783 года назад
DIRECT 2021 07 CRM for scikit-learn Estimator
DIRECT 2021 04 Spatial Data Analytics
Просмотров 3723 года назад
DIRECT 2021 04 Spatial Data Analytics
Texas Groundwater Uncertainty Keynote July, 2021
Просмотров 7813 года назад
Texas Groundwater Uncertainty Keynote July, 2021
5f Machine Learning: Non-cooperative Game Theory
Просмотров 1,5 тыс.3 года назад
5f Machine Learning: Non-cooperative Game Theory
Awesome video, Thanks! If we have a problem with ML, could we discuss the issue with you?
I love it
One of the best introductory classes I’ve seen, thanks so much. I have a basic (sorry) technical question: you seem to be showing slides from a ppt but inside you have working python notebook. How do you do this?
do you have a video of spatial correlation/auto correlation?
Cool video
Hi sir , could you please interpret the result ? , i am getting some confusion related to the categorical value interpretation from the output
Your classes are amazing!
Thanks! Played with your code for the Gaussian stuff and had an ah-ha moment.
Great explanation!!
Let's say that I'm tracking the profile of some person. I choose features F1, F2, F3, ..., Fn. I designed idiocy function fi. This is a function which maps features in the range between 0 and 100. You say that we need to model the distributions F_x. How I could do it? Do I need to steal this knowledge from somewhere?
Thank you so much!
Excellent explanation and presentation
Best content from best teacher...please continue to share the very interesting contents...following from Algeria :)
great lecture. is it possible to adjust the density values based on cluster density?. is there any algorithm to achieve this?. thanks
Super!
Hi, do you have any Excel file that shows the two-dimensional variogram? Like parallel and perpendicular transects?
Excellent video Professor. May I get access to your PPT slides. Thank you so much for making such amazing lectures open source and accessible.
Thanks a lot ! Very clear explanation
You're awesome! Thanks so much for this.
Thanks great explanation! GeostatsGuy can I ask you what if I have to sample categorical classes. For example, prediction model of land use changes. I would add non-changes but where if i have clustered changes (i.e. changes that occur in one specific region). Thanks!
Thank you Very much!!!
Hi professor, thank you for all your lectures - they are a great resource for fundementals. I wanted to ask, @ 35:24 you speak about creating a 2D ndarrays using the meshgrid function. I wanted to ask why the "-1*" is needed in the arguments for the "yy" array?
Greetings from #China professor. I am honoured to be your virtual student and always feel pleasure in learning from your videos. Keep inspiring!
Thank you Michael for this awesome video!
Is "stationarity" in this lecture similar to "homogeneity"?
The way you explain is fantastic. Thank you for making it available for the public!
Thanks Proffesor for helping us and sharing your knowledge, that was really helpful.
Thanks Pr. Pyrcz
"PromoSM"
Happy New Yr, waiting for DS & ML project end-end. kindly make it
This is absolutely amazing. I took Bayesian stats for my MS in Data Science (Analytics) from Georgia Institute of Technology, a top three engineering school, and yet, even as a top tier engineering school, neither the professor nor the TAs bothered to explain these this well. I will be rewatching this several more times. Thank you for the work you put in to create all of this and talk us through it.
Thank you very much for sharing this outstanding content.
Man knows his shit
😍 thx for new topic
thank you very much. I enjoyed your interesting presentation.
Nice explanation
Thanks for the very nice demonstration 👍
Thanks as always Mike. I love this short demo series. They are great teasers for deciding what I would like to dig deeper into with your other lectures
When learning about a complex topic, there is a teaching moment when the diverse components make sense together. This video brought disparate parts of my knowledge and experience together brilliantly. I am a software developer who is making the transition from managing financial transactions to analyzing features that explain migration. This video helps me so much. Thank you!!!!
Wooow, thx for video
Amazing.
Awesome! I am loving this series! Thank you!!!
Great stuff, keep it up boss
Thank you! I've got about 44 more to go! :) I hope these are helpful.
It's a pleasure to see you again
Thank you! It has been a while! Super busy and excited to keep building more content on RUclips.
It's a clear explanation and very helpful. Much appreciated.
Thank you for this, Professor Michael.
is there any section in the courses where you show certain concepts by coding?
What can be the physical interpretation of negative correlation? How is it possible that places dislike each other?, Michał Michalak
Great explanation! Thank you!
So far, very detailed information and abundant of clear examples to meak easier the processing of Geostats learning
Why is the case where no one does nothing including player1’s value?