A notebook demonstration of the item classifier in InvClassifier.py with an explaination of the process.
Packages Used: OS, NumPy, PIL, SkLearn, MatPlotLib, CV2
A notebook demonstration of the item quantity classifier in InvClassifier.py with an explaination of the process.
Packages Used: OS, NumPy, PIL, SkLearn, MatPlotLib, CV2
A notebook demonstration of how I set up and tested StartImageGenerator and EndImageGenerator.
Packages Used: NumPy, PIL, Json, TQDM, Pandas, Random, CV2, Math, Keras
A notebook visualization/exploration of my automatically generated gameplay dataset. This one is fun because it has a lot of pictures and data preprocessing, but this dataset did not end up chosen in the final model.
Packages Used: OS, Sys, Json, NumPy, IPython.Display, TQDM, Random
A notebook demonstrating the model outputs from MoveClassifier.py.
Packages Used: OS, NumPy, Pandas, MatPlotLib, PIL, Json, Random, IPython.display
A notebook visualization/exploration of BASALT 2022 competition gameplay dataset. This one is fun because it has a lot of pictures and data preprocessing.
Packages Used: OS, NumPy, Pandas, Json, CV2, PIL, IPython.display
A notebook exploration at an attempt to smooth the ColorMap data collected. Concluded to not be a great choice for this project, but the smoothing works and is clearly demonstrated and visualized.
Packages Used: OS, NumPy, Pandas, TQDM, PIL, CV2
A notebook exploration at an attempt to smooth the ColorMap data collected using KNN. Concluded to not be a great choice for this project again, and smoothing was fine, but not great. ColorMap Smoothing.ipynb was better.
Packages Used: OS, NumPy, PIL, CV2, TDQM
A notebook visualization of a Malmo dataset I generated for training data to feed into BlockSegmentator.py and DepthEstimator.py. Lots of visuals, tables, and pretty pictures.
Packages Used: OS, NumPy, Pandas, PIL, TQDM, IPython.display, Json, Requests, ShUtil
A notebook demonstration of how I use TF-IDF to search through the many pages of MineWiki Data distributed by MineDojo. Works really well and uses PySpark for all the data preprocessing, transformation and TF-IDF work which makes it really fast. This is the start of me introducing Natural Language Processing to get more information for my Agent.
Packages Used: OS, Pandas, PySpark SQL, PySparkML
A notebook demonstration of how I use TF-IDF to search through transcripts of 70k gameplay Youtube Videos distributed by MineDojo. After the success on the MineWiki search, I brought that to this problem. Doesn't work great because the words said are not as consistent in a transcript as a Wiki page. It still uses PySpark for all the data preprocessing, transformation and TF-IDF work which makes it really fast. After this I need to look into some other options for gathering information from transcripts.
Packages Used: Minedojo, IPython.display, Random, TDQM, OS, RE, Pandas, PySpark SQL, PySparkML
A notebook visualization of a the MineDojo Gym Environment's Observation and Action set.
Packages Used: Minedojo, NumPy, Random, PIL
A notebook visualization of a the MineDojo Gym Tasks and Instructions.
Packages Used: Minedojo