def randomforest(table, n, m, f):
output.printHeader('Random Forest')
print("N = " + str(n) + " M = " + str(m) + " F = " + str(f))
indexes = [INDICES['degree'], INDICES['ethnicity'], INDICES['gender']]
domains = table_utils.get_domains(table, indexes)
forest_labels, train, test = \
run_a_table(table, indexes,
INDICES['salary'], n, m, f)
forest_accurcay = accuracy(forest_labels)
print('\tAccuracy = ' + str(forest_accurcay))
_printConfusionMatrix(forest_labels, 'Salary')
def knn_and_naive(table):
""" Analyzes the table based on Knn and Naive Bayes
:param table: the table of the titanic dataset
:return: nothing
"""
map_columns_table(table)
table = knn.normalize_table(table, [5, 7])
# KNN
output.printHeader('K-Nearest Neighbors')
labels = partition_util.random_subsample_knn(table, 5, 10,
constants.INDICES['salary'])
accuracy = classifier_util.accuracy(labels)
print('\tRandom Subsample')
print('\t\tAccuracy = ' + str(accuracy) + ', error rate = ' +
str(1 - accuracy))
labels = partition_util.stratified_cross_fold_knn(
table, 5, 10, constants.INDICES['salary'])
accuracy = classifier_util.accuracy(labels)
accuracy_values.append(accuracy)
print('\tStratified Cross Folds (5)')
print('\t\tAccuracy = ' + str(accuracy) + ', error rate = ' +
str(1 - accuracy))
_printConfusionMatrix(labels, 'Salary')
# Naive Bayes
output.printHeader('Naive Bayes')
test_by_names = ['degree', 'ethnicity', 'gender']
accuracy = classifier_util.accuracy(
partition_util.random_subsample_naive_bayes(
table, 10, constants.INDICES['salary'], test_by_names))
print('\tRandom Subsample')
print('\t\tAccuracy = ' + str(accuracy) + ', error rate = ' +
str(1 - accuracy))
labels = partition_util.stratified_cross_fold_naive_bayes(
table, 10, constants.INDICES['salary'], test_by_names)
accuracy = classifier_util.accuracy(labels)
accuracy_values.append(accuracy)
print('\tStratified CrossFolding')
print('\t\tAccuracy = ' + str(accuracy) + ', error rate = ' +
str(1 - accuracy))
_printConfusionMatrix(labels, 'Salary')
def main():
# Data preprocessing
newTable = file_system.loadTable("../datasets/income.csv")
removedRowsTable = clean.removeNA(newTable)
incomeDataFullNoNA = file_system.write(removedRowsTable,
"../datasets/incomeNoNA.csv")
output.printHeader('Rows with NAs have been removed.')
# Data visualization
data_vis()
output.printHeader('Data visualization complete.')
# KNN and Naive Bayes classifiers
table = file_system.loadTable('../datasets/incomeNoNA.csv')
knn_and_naive(table)
# Decision Tree classifier
table = file_system.loadTable('../datasets/incomeNoNA.csv')
decisiontree(table)
# Random Forest classifier
table = file_system.loadTable('../datasets/incomeNoNA.csv')
randomforest(table, 3000, 215, 2) #N, M, and F vals
def decisiontree(table):
map_columns_table(table)
output.printHeader('Decision Tree')
attributes = these(INDICES, 'ethnicity', 'degree', 'gender')
domains = table_utils.get_domains(table, attributes)
tree = decision_tree.tdidt(table, attributes, domains, INDICES['salary'])
decision_tree.print_rules(tree, [
'age', 'job-type', 'degree', 'marital-status', 'ethnicity', 'gender',
'country', 'salary'
], 'salary')
attributes = these(INDICES, 'degree', 'ethnicity', 'gender')
# Creates a myClassifier function that's paritally filled out
# From decision_tree.classify
# Essentially a new function:
# myClassifier(training, test, class_index)
myClassifier = partial(decision_tree.classify,
att_indexes=attributes,
att_domains=domains)
labels = homework.stratified_cross_fold(table, 10, INDICES['salary'],
myClassifier)
acc = accuracy(labels)
accuracy_values.append(acc)
print('\n')
print('Stratified CrossFolding')
print('\tAccuracy = ' + str(acc) + ', error rate = ' + str(1 - acc))
print('\n')
# Confusion Matrix
_printConfusionMatrix(labels, 'Salary')
def _printConfusionMatrix(labels, name):
""" Prints a confusion matrix for given labels """
output.printHeader('Confusion Matrix')
partition_util.print_confusion_matrix(labels, name)