def remove_features(removal_order, train_file, test_file, attr_file,
max_features):
train_accs = []
test_accs = []
remove_columns = []
for col in removal_order:
print(col)
remove_columns.append(col)
if len(remove_columns) == max_features: break
print(remove_columns)
train_data, train_attr = read_data(train,
attr,
remove_columns=remove_columns)
test_data, test_attr = read_data(test,
attr,
remove_columns=remove_columns)
tree = decision_tree.DecisionTreeLearning(train_data, train_attr,
"normal", "class")
decision_tree.print_tree(tree)
y_pred, y_true = decision_tree.predict(train_data, tree)
train_acc = decision_tree.accuracy_score(y_pred, y_true)
print('Accuracy on Training Data: {0}'.format(train_acc * 100))
y_pred, y_true = decision_tree.predict(test_data, tree)
test_acc = decision_tree.accuracy_score(y_pred, y_true)
print('Accuracy on Training Data: {0}'.format(test_acc * 100))
train_accs.append(train_acc)
test_accs.append(test_acc)
return train_accs, test_accs
def menu_1():
print("\nType the filename you would like to run the classifier on")
filename = raw_input(" >> ")
print("\nPlease type the filename with the types of classifiers listed")
label_file = raw_input(" >> ")
prepped_data = prep_data(filename, label_file)
tree = decision_tree.build_decision_tree(prepped_data)
decision_tree.print_tree(tree, 100)
def main():
train_file = 'train.txt'
test_file = 'test.txt'
bayes_accuracy = naive_bayes(train_file, test_file)
knn_accuracy = knn(train_file, test_file, k=5)
dt_accuracy, tree = decision_tree(train_file, test_file)
with open('output.txt', 'w') as f:
print_tree(tree, f)
f.write('\n{}\t{}\t{}\n'.format(round(dt_accuracy, 2),
round(knn_accuracy, 2),
round(bayes_accuracy, 2)))
def run_tests(df, df_training, labels):
for m in dt.Measure:
for i in range(1, 5):
tree_depth = i
min_split = 1
test_set = df.values
measure = m
tree = dt.build_tree(df_training.values,
max_depth=tree_depth,
min_size=min_split,
measure=measure)
print("=" * 40)
dt.print_tree(tree, labels)
print('Min split: {}'.format(min_split))
print('Tree depth: {}'.format(tree_depth))
print('Train Size: {}'.format(len(df_training)))
print('Test Size: {}'.format(len(test_set)))
print('Accuracy: {:.4f}'.format(dt.accuracy(test_set, tree)))
print('Measure: {}'.format(measure))
print("=" * 40)
def main():
#Set display option for data frames
pd.set_option('display.max_columns', 11)
pd.set_option('display.width', 200)
#Read data and remove garbage
df = pd.read_csv('winequalityN.csv')
df = dt.remove_garbage(
pd.DataFrame(data=df, columns=list(df.columns.values)))
cols = df.columns.tolist()
cols = cols[1:] + cols[0:1] #Move wine color column to last column
#df = df[cols]
df = df[cols].drop(['total sulfur dioxide'], axis='columns')
labels = df.columns.values
#Extract training data, sample size n
df_white = df[(df['type'] == 0.0)]
df_red = df[(df['type'] == 1.0)]
df_training = df.sample(n=100, random_state=1) #Mixed sample
# run_tests(df, df_training, labels)
tree_depth = 3
min_split = 1
test_set = df.values
measure = dt.Measure.GINI
tree = dt.build_tree(df_training.values,
max_depth=tree_depth,
min_size=min_split,
measure=measure)
print("=" * 40)
dt.print_tree(tree, labels)
print('Min split: {}'.format(min_split))
print('Tree depth: {}'.format(tree_depth))
print('Train Size: {}'.format(len(df_training)))
print('Test Size: {}'.format(len(test_set)))
print('Accuracy: {:.4f}'.format(dt.accuracy(test_set, tree)))
print('Measure: {}'.format(measure))
print("=" * 40)
dt.prune_tree(tree)
dt.print_tree(tree, labels)
test_fraction = 0.25
max_depth = 2
min_sample_per_node = 2
criterion = 'gini'
prediction_type = 'classification'
# load dataset
X, Y, X_feature_names = common_fns.get_data(filename=filename, target=target)
# random split into test and train
X_train, Y_train, X_test, Y_test = common_fns.split_train_test(
X, Y, test_fraction=test_fraction)
# fit tree on train set
tree = dtree.fit_decision_tree(X=X_train,
Y=Y_train,
max_depth=max_depth,
min_sample_per_node=min_sample_per_node,
criterion=criterion)
# print tree for debugging/reference
dtree.print_tree(tree=tree, X_feature_names=X_feature_names)
# make predictions on test set
Y_predict = dtree.predict_all(tree=tree,
X=X_test,
prediction_type=prediction_type)
# calculate various classification scores
dtree.calculate_scores(Y_predict=Y_predict, Y_ref=Y_test)
def __repr__(self):
#the reason this is formatted like this is because Python doesn't like
#printing with no returns. This basically calls the function that prints everything
#then prints None. The way this is formatted helps the None from being printed.
return '' if str(watdt.print_tree(self.tree)) == None else ''
from decision_tree import get_header
from decision_tree import set_header
from decision_tree import get_unique_values
import csv
training_data = []
with open('data.csv', encoding="utf8") as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
for row in readCSV:
new_row = []
for item in row[0].split(','):
new_row.append(item)
training_data.append(new_row)
my_tree = build_tree(training_data)
print_tree(my_tree)
print()
testing_data = []
for i in range(len(get_header()) - 1):
ask = 'Введіть ' + str(get_header()[i]) + str(
get_unique_values(training_data, i)) + ': '
user_input = input(ask)
testing_data.append(user_input)
print("Передбачено: %s" % (print_leaf(classify(testing_data, my_tree))))
input()