def test_adult_tree():
import os
import numpy as np
import pykitml as pk
from pykitml.datasets import adult
# Download the dataset
if (not os.path.exists('adult.data.pkl')): adult.get()
# Load adult data set
inputs_train, outputs_train, inputs_test, outputs_test = adult.load()
outputs_train = pk.onehot(outputs_train)
outputs_test = pk.onehot(outputs_test)
# Create model
ftypes = [
'continues', 'categorical', 'continues', 'categorical', 'categorical',
'categorical', 'categorical', 'categorical', 'categorical',
'continues', 'continues', 'continues', 'categorical'
]
tree_adult_classifier = pk.DecisionTree(13,
2,
max_depth=100,
min_split=100,
feature_type=ftypes)
# Train
tree_adult_classifier.train(inputs_train, outputs_train)
# Save it
pk.save(tree_adult_classifier, 'tree_adult_classifier.pkl')
# Print accuracy
accuracy = tree_adult_classifier.accuracy(inputs_train, outputs_train)
print('Train accuracy:', accuracy)
accuracy = tree_adult_classifier.accuracy(inputs_test, outputs_test)
print('Test accuracy:', accuracy)
# Plot confusion matrix
tree_adult_classifier.confusion_matrix(inputs_test,
outputs_test,
gnames=['False', 'True'])
# Assert accuracy
assert (tree_adult_classifier.accuracy(inputs_test, outputs_test)) >= 84
def test_banknote_forest():
import os
import numpy as np
import pykitml as pk
from pykitml.datasets import banknote
# Download the dataset
if (not os.path.exists('banknote.pkl')): banknote.get()
# Load heart data set
inputs_train, outputs_train, inputs_test, outputs_test = banknote.load()
# Change 0/False to [1, 0]
# Change 1/True to [0, 1]
outputs_train = pk.onehot(outputs_train)
outputs_test = pk.onehot(outputs_test)
# Create model
ftypes = ['continues'] * 4
forest_banknote_classifier = pk.RandomForest(4,
2,
max_depth=9,
feature_type=ftypes)
# Train
forest_banknote_classifier.train(inputs_train, outputs_train)
# Save it
pk.save(forest_banknote_classifier, 'forest_banknote_classifier.pkl')
# Print accuracy
accuracy = forest_banknote_classifier.accuracy(inputs_train, outputs_train)
print('Train accuracy:', accuracy)
accuracy = forest_banknote_classifier.accuracy(inputs_test, outputs_test)
print('Test accuracy:', accuracy)
# Plot confusion matrix
forest_banknote_classifier.confusion_matrix(inputs_test,
outputs_test,
gnames=['False', 'True'])
# Assert accuracy
assert (forest_banknote_classifier.accuracy(inputs_test,
outputs_test)) >= 98
def test_sonar_forest():
import os
import numpy as np
import pykitml as pk
from pykitml.datasets import sonar
# Download the dataset
if (not os.path.exists('sonar.pkl')): sonar.get()
# Load the sonar dataset
inputs_train, outputs_train, inputs_test, outputs_test = sonar.load()
outputs_train = pk.onehot(outputs_train)
outputs_test = pk.onehot(outputs_test)
# Create model
forest_sonar_classifier = pk.RandomForest(60,
2,
max_depth=9,
feature_type=['continues'] * 60)
# Train the model
forest_sonar_classifier.train(inputs_train,
outputs_train,
num_feature_bag=60)
# Save it
pk.save(forest_sonar_classifier, 'forest_sonar_classifier.pkl')
# Print accuracy
accuracy = forest_sonar_classifier.accuracy(inputs_train, outputs_train)
print('Train accuracy:', accuracy)
accuracy = forest_sonar_classifier.accuracy(inputs_test, outputs_test)
print('Test accuracy:', accuracy)
# Plot confusion matrix
forest_sonar_classifier.confusion_matrix(inputs_test,
outputs_test,
gnames=['False', 'True'])
def test_heart_tree():
import os.path
import numpy as np
import pykitml as pk
from pykitml.datasets import heartdisease
# Download the dataset
if (not os.path.exists('heartdisease.pkl')): heartdisease.get()
# Load heart data set
inputs, outputs = heartdisease.load()
outputs = pk.onehot(outputs)
# Create model
ftypes = [
'continues', 'categorical', 'categorical', 'continues', 'continues',
'categorical', 'categorical', 'continues', 'categorical', 'continues',
'categorical', 'categorical', 'categorical'
]
tree_heart_classifier = pk.DecisionTree(13,
2,
max_depth=7,
feature_type=ftypes)
# Train
tree_heart_classifier.train(inputs, outputs)
# Save it
pk.save(tree_heart_classifier, 'tree_heart_classifier.pkl')
# Print accuracy
accuracy = tree_heart_classifier.accuracy(inputs, outputs)
print('Accuracy:', accuracy)
# Plot confusion matrix
tree_heart_classifier.confusion_matrix(inputs,
outputs,
gnames=['False', 'True'])
# Plot descision tree
tree_heart_classifier.show_tree()
# Assert accuracy
assert (tree_heart_classifier.accuracy(inputs, outputs)) >= 94
def test_heart_bayes():
import os.path
import numpy as np
import pykitml as pk
from pykitml.datasets import heartdisease
# Download the dataset
if (not os.path.exists('heartdisease.pkl')): heartdisease.get()
# Load heart data set
inputs, outputs = heartdisease.load()
# Change 0/False to [1, 0]
# Change 1/True to [0, 1]
outputs = pk.onehot(outputs)
distrbutions = [
'gaussian', 'binomial', 'multinomial', 'gaussian', 'gaussian',
'binomial', 'multinomial', 'gaussian', 'binomial', 'gaussian',
'multinomial', 'multinomial', 'multinomial'
]
# Create model
bayes_heart_classifier = pk.NaiveBayes(13, 2, distrbutions)
# Train
bayes_heart_classifier.train(inputs, outputs)
# Save it
pk.save(bayes_heart_classifier, 'bayes_heart_classifier.pkl')
# Print accuracy
accuracy = bayes_heart_classifier.accuracy(inputs, outputs)
print('Accuracy:', accuracy)
# Plot confusion matrix
bayes_heart_classifier.confusion_matrix(inputs,
outputs,
gnames=['False', 'True'])
# Assert accuracy
assert (bayes_heart_classifier.accuracy(inputs, outputs)) > 84