def main(k, data_set_name=None):
split_percentage = 0.7
# Load dataset
if data_set_name is not None:
data_set = read_file_into_dataset(
"C:\\Users\\Grant\\Documents\\School\\Winter 2016\\CS 450\\Prove01\\"
+ data_set_name)
data_set = randomize_dataset(data_set)
else:
data_set_name = "iris"
iris = datasets.load_iris()
data_set = randomize_dataset(iris)
data_set.data = normalize(data_set.data)
data_sets = split_dataset(data_set, split_percentage)
training_set = data_sets['train']
testing_set = data_sets['test']
# My Classifier
knnClassifier = KnnClassifier()
knnClassifier.k = k
knnClassifier.train(training_set.data, training_set.target,
training_set.target_names)
predictions = knnClassifier.predict(testing_set.data)
my_accuracy = get_accuracy(predictions, testing_set.target)
# Better Classifier
better_classifier = KNeighborsClassifier(n_neighbors=k)
better_classifier.fit(training_set.data, training_set.target)
predictions = better_classifier.predict(testing_set.data)
better_accuary = get_accuracy(predictions, testing_set.target)
print("My results: " + str(my_accuracy) + "%")
print("Better results: " + str(better_accuary) + "%")
results = "k = " + str(k) + "\nMy results: " + str(
my_accuracy) + "%\n" + "Better results: " + str(better_accuary) + "%\n"
write_to_results_file(
os.getcwd() + os.sep + ".." + os.sep + str(k) + "-" + data_set_name +
"_results.txt", results, k)
def main(k, data_set_name=None):
split_percentage = 0.7
# Load dataset
if data_set_name is not None:
data_set = read_file_into_dataset("C:\\Users\\Grant\\Documents\\School\\Winter 2016\\CS 450\\Prove01\\" + data_set_name)
data_set = randomize_dataset(data_set)
else:
data_set_name = "iris"
iris = datasets.load_iris()
data_set = randomize_dataset(iris)
data_set.data = normalize(data_set.data)
data_sets = split_dataset(data_set, split_percentage)
training_set = data_sets['train']
testing_set = data_sets['test']
# My Classifier
knnClassifier = KnnClassifier()
knnClassifier.k = k
knnClassifier.train(training_set.data, training_set.target, training_set.target_names)
predictions = knnClassifier.predict(testing_set.data)
my_accuracy = get_accuracy(predictions, testing_set.target)
# Better Classifier
better_classifier = KNeighborsClassifier(n_neighbors=k)
better_classifier.fit(training_set.data, training_set.target)
predictions = better_classifier.predict(testing_set.data)
better_accuary = get_accuracy(predictions, testing_set.target)
print("My results: " + str(my_accuracy) + "%")
print("Better results: " + str(better_accuary) + "%")
results = "k = " + str(k) + "\nMy results: " + str(my_accuracy) + "%\n" + "Better results: " + str(better_accuary) + "%\n"
write_to_results_file(os.getcwd() + os.sep + ".." + os.sep + str(k) + "-" + data_set_name + "_results.txt", results, k)
df.columns[i]].quantile(0.25) != 1:
index.append(i)
features = df[df.columns[index]]
labels = df[df.columns[len(df.columns) - 1]]
# Replacing alphabets to numbers for ease of use
labels = labels.replace('A', 1).replace('B', 2).replace('C', 3).replace(
'D', 4).replace('E', 5)
X = features.values
y = labels.values
X_train, X_test, Y_train, Y_test = train_test_split(features.values,
labels.values,
test_size=0.2)
# Running knn classifier on the dataset
start = timeit.default_timer()
knnClf = KnnClassifier(X_train, Y_train)
predictions = knnClf.predict(X_test=X_test, k=41)
stop = timeit.default_timer()
print("Run Time: ", stop - start)
# transform the list into an array
predictions = np.asarray(predictions)
# evaluating accuracy
accuracy = accuracy_score(Y_test[0:100], predictions)
print('\nThe accuracy of our classifier is %d%%' % accuracy)