DuckML / Duckonomics

More accessories implemented based on wealth! Currently making the demo for shipping #1

Made a panel to click the ducks and check their age, money, name etc. More shops to come…

Main Menu Created and working, going to add more shops and machine learning capabilities to choosing different shops

Made a Bussiness Tax for the government and let the simulator run for 150 days to see what happens, everyone is rich and most only last until they turn 8, will start tweaking the taxing, birth and death rate to simulate a realistic economy.

Added Population control, changing the birth and death rate to execute once every 30 second day. Added an Obituary and implemented Government Taxing on wages, (jobs added) and jobs include:

JOBS = {
“Baker”: 12,
“Fisher”: 8,
“Merchant”: 15,
“Programmer”: 25,
“Unemployed”: 0
}

Suggest some jobs in the comments, and suggest some first and last names too

FIRST_NAMES = [
“Bob”,
“Sarah”,
“Alex”,
“Emily”,
“Oscar”
]

LAST_NAMES = [
“Quackson”,
“Featherstone”,
“Breadsworth”,
“McDuck”,
“Waddles”
]

Also added some UI regarding the treasury and added a seperate birth rate for an additional child.

Added Uniquness, more traits, age, birth, death, accessories based on wealth, names and working toward a more functioning society. Also made a cleaner codebase, with constants and variable scripts in place to make everything cleaner. Fixed the duck finding a shop algorithm, based on nearest shop AND STOCK now, rather than just distance. Increase Screen Size and minor tweaks here and there.

Added a population counter and fixed a previous bug with selling bread

Added Waves, Icons, And working shop system that refills the stock everyday and uses machine learning to predict what the stock of the bakery needs to be in order to sustain the hunger of the populaation. It tracks the sales, predictions, stock and money of the stores. I also added a day counter and a time label to ensure players know the status of the shop and sales.

Began Duckonomics, created the basics and beginning to implement Machine Learning into the prices for profit of bread. Ducks have a random movement pattern, bread label in progress. Each duck will have own character traits that make it unique.

Experimented with Markov Chains and made a dynamic system that scans a dataset of sentences based off a theme, forms new sentences, that adds to the csv of QuackJudge. This creates a sustainable loop all based off one single initial dataset and a Markov Chain.

The Markov chain tracks different sentences and interprets words that come after one another to form sentences. Realistically my dataset isn’t large enough to showcase accurate data but still showcases the concept’s nature.

Made a simple word to emotion classifier using the Naive Bayes Classifier algorithm, with training of 90% and testing of 10%, it provides on average, 51% accuracy based on self-testing. By increasing the size of the dataset, the accuracy and vocabulary will increase, showcased in the vectorisation of the word below, where the one is a recognised word. Mathematically this is represented in a multi-dimensional space based on how many known words the AI understands based on training and testing. Might test image classification next or try new Machine Learning Concepts to create an All-in-one, self taught AI, image, audio, emotion etc.