Female patients at least 21 years old 768 patients observation rows 10 columns -> 9 featues columns + 1 diabetes col (True/False)

closer the data is to what you are predicting, the better

data needs to be formatted the way we need it

1. learning type
2. result
3. complexity
4. basic vs enhanced

"Use the ML Workflow to process and transform Pima Indian Data to Create a prediction model. This Model must predict which people are likely to develop diabetes woth 70% or greater accuracy"

Prediction Model => Supervised ML (binary output)

we will stick to basic algos.

1. Nave Bayes (We use this)
2. Logistic Regession
3. Decision Tree

split the data : 70% Training + 30% Testing training the model with Algo

after training the data and makeing the predictions for the test data we can improve the predition of Ture positives

• adjust current algo
• get more data or improve data
• improve data
• switch algorithm and check which algo suits best