Created
January 5, 2021 06:14
-
-
Save mikesparr/f4acfac770e5a3491dee5a3076115326 to your computer and use it in GitHub Desktop.
AI Demo (model training)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# creating a function automatically (model training) | |
# 1. assemble some data with known answers (aka 'class' or 'label') | |
data = [[pizza,good],[spinach,bad],[cake,good]] | |
# 2. choose a portion of records for testing accuracy later | |
train = [[pizza,good],[spinach,bad]] | |
test = [[cake,good]] # if input cake, expect 'good' | |
# 3. extract the features for training set you think matter | |
# [type, smell, spice, temp, sweetness, color, class] | |
cleandata = [ | |
[4, 20, 1, 135, 55, 2, 1], // pizza | |
[2, 12, 1, 89, 30, 4, 0], // spinach | |
] | |
# 4. separate out the known answers from the inputs (aka features) | |
train_x = [[4,20,1,135,55,2],[2,12,1,89,30,4]] # features | |
train_y = [[1],[0]] # class or labels | |
# 5. choose which type of function to create (trial/error) | |
myclassifier = SomeAlgorithmFromSomeFramework(line_type) # ignore | |
# 6. train your 'model' (function) | |
myclassifier.fit(train_x, train_y) # see goal seek example below | |
# 7. test accuracy | |
# a. extract features from test data you set aside | |
# b. pass in test data features and get prediction | |
# c. compare prediction to known value to see if it's right |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment