def main():
col_names = [
'sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'
]
iris = pd.read_csv('./iris.data', header=None, names=col_names)
iris_class = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
iris['species_num'] = [iris_class[i] for i in iris.species]
X = iris.drop(['species', 'species_num'], axis=1).to_numpy()
y = iris.species_num.to_numpy()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
kr = Knn(3)
# knn = KNeighborsClassifier(3)
# model = knn.fit(X_train, y_train)
kr.fit(X_train, y_train)
# p = model.predict(X_test)
p2 = kr.predict(X_test)
correct = 0
total = 0
for pred in zip(p2, y_test):
if pred[0] == pred[1]:
correct += 1
total += 1
print("acc :", correct / total)
def test_minkowski_distance(self):
"""Test to check that minkowski distance is correct"""
knn = Knn(n_neighbors=3, p=5)
knn.fit(np.array(little_X), little_Y)
d = knn._minkowski_distance(np.array([3, 4]))
assert np.allclose(
d, [2.01234, 6.419382]), "Minkowski Distance is not correct"
def test_k_5(self):
"""Test to compare our knn with Sklearn knn when k=5 and distance is euclidean"""
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
prediction = knn.predict(X_test)
knn2 = Knn(n_neighbors=5)
knn2.fit(X_train, y_train)
prediction2 = knn2.predict(X_test)
assert np.alltrue(
prediction == prediction2), "Error testing knn with k=5"
def test_distance_weight_2(self):
"""Test to compare our knn with Sklearn when k=5 and weights are the inverse of distance"""
knn = KNeighborsClassifier(n_neighbors=5, weights='distance')
knn.fit(X_train, y_train)
prediction = knn.predict(X_test)
knn2 = Knn(n_neighbors=5, weights='distance')
knn2.fit(X_train, y_train)
prediction2 = knn2.predict(X_test)
assert np.alltrue(prediction == prediction2
), "Error testing knn with k=5 and weights=distance"
def test_k_5_distance_minkowski(self):
"""Test to compare our knn with Sklearn knn when k=5 and distance is minkowski with p=3"""
knn = KNeighborsClassifier(n_neighbors=5, metric="minkowski", p=3)
knn.fit(X_train, y_train)
prediction = knn.predict(X_test)
knn2 = Knn(n_neighbors=5, metric="minkowski", p=3)
knn2.fit(X_train, y_train)
prediction2 = knn2.predict(X_test)
assert np.alltrue(prediction == prediction2
), "Error testing knn (minkowski) with k=5 and p=3"
def main():
X_train, y_train, X_test, y_test = load_mnist()
# data binarization
# for i in tqdm(range(len(x_train))):
# for j in range(28):
# for k in range(28):
# x_train[i][j][k] = 1 if x_train[i][j][k] > 177 else 0
# for i in tqdm(range(len(x_test))):
# for j in range(28):
# x_test[i][j].squeeze()
# for k in range(28):
# x_test[i][j][k] = 1 if x_test[i][j][k] > 177 else 0
# plot data samples
# plot = plt.subplots(nrows=4, ncols=5, sharex='all', sharey='all')[1].flatten()
# for i in range(20):
# img = x_train[i]
# plot[i].set_title(y_train[i])
# plot[i].imshow(img, cmap='Greys', interpolation='nearest')
# plot[0].set_xticks([])
# plot[0].set_yticks([])
# plt.tight_layout()
# plt.show()
knn = Knn()
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
correct = sum((y_test - y_pred) == 0)
print('==> correct:', correct)
print('==> total:', len(X_test))
print('==> acc:', correct / len(X_test))
# plot pred samples
fig = plt.subplots(nrows=4, ncols=5, sharex='all',
sharey='all')[1].flatten()
for i in range(20):
img = X_test[i]
fig[i].set_title(y_pred[i])
fig[i].imshow(img, cmap='Greys', interpolation='nearest')
fig[0].set_xticks([])
fig[0].set_yticks([])
plt.tight_layout()
plt.show()
def main():
# getting data
# returning set of features and set of labels
# for each 4-elements set of features there is one label assigned
# label is assgined based on characteristic resulting from features
iris = datasets.load_iris()
iris_df = pd.DataFrame(iris['data'], columns=iris['feature_names'])
X = iris_df.to_numpy()
y = iris['target']
iris_df['species'] = iris['target']
# print(X) # [[5.9 3. 4.2 1.5],...,[6. 2.2 4. 1. ],...,[6.1 2.9 4.7 1.4]]
# print(y) # [0,0,0,....,1,1,1,....,2,2,2,...]
plot_chart(iris_df)
# splitting data into training and testing subsets
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=1234)
clf = Knn(k=3)
clf.fit(X_train,
y_train) # fitting model with features and corresponding labels
predictions = clf.predict(X_test)
print('Test samples shape: ' + str(X_test.shape)) # 120 features
print(X_test)
print('')
print('Predictions shape: ' + str(predictions.shape)) # 30 lables
print(predictions)
print('')
calculate_accuracy(predictions,
y_test) # comparing predicitons outcome with y_test
new_features = np.asarray([[6.2, 2.8, 5.7, 1.8]])
predicted_label = clf.predict(np.asarray(new_features))
print('')
print('New Features: ' + str(new_features))
print('Predicted label: ' + str(predicted_label))
print('Predicted speices: ' + str(species[int(predicted_label[0])]))
def main():
X_train, y_train, X_test, y_test = load_mnist()
knn = Knn()
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
correct = sum((y_test - y_pred) == 0)
print('==> correct:', correct)
print('==> total:', len(X_test))
print('==> acc:', correct / len(X_test))
# plot pred samples
fig = plt.subplots(nrows=4, ncols=5, sharex='all',
sharey='all')[1].flatten()
for i in range(20):
img = X_test[i]
fig[i].set_title(y_pred[i])
fig[i].imshow(img, cmap='Greys', interpolation='nearest')
fig[0].set_xticks([])
fig[0].set_yticks([])
plt.tight_layout()
plt.show()
def get_accuracy(k, trainx, trainy, testx, testy):
knn = Knn(k)
knn.fit(trainx, trainy)
hyp = knn.predict(testx)
return accuracy_score(hyp, testy)
def test_input_dimension(self):
"""Test to check that we raise an exception id X and y dimmension are nor consistent"""
knn = Knn(n_neighbors=3)
with self.assertRaises(ValueError):
knn.fit(X_train, y_test)
def test_manhattan_distance(self):
"""Test to check that manhattan distance is correct"""
knn = Knn(n_neighbors=3)
knn.fit(np.array(little_X), little_Y)
d = knn._manhattan_distance(np.array([5, 6]))
assert (d == [7, 7]).all(), "Manhattan Distance is not correct"
def test_euclidean_distance(self):
"""Test to check that euclidean distance is correct"""
knn = Knn(n_neighbors=3)
knn.fit(np.array(little_X), little_Y)
d = knn._euclidean_distance(np.array([5, 6]))
assert (d == [5, 5]).all(), "Euclidean Distance is not correct"
x_train_folds = []
y_train_folds = []
indices = np.array_split(np.arange(num_training),
indices_or_sections=num_folds)
for i in indices:
x_train_folds.append(x_train[i])
y_train_folds.append(y_train[i])
k_to_accuracies = {}
for k in k_choices:
acc = []
for i in range(num_folds):
x = x_train_folds[0:i] + x_train_folds[i + 1:]
x = np.concatenate(x, axis=0)
y = y_train_folds[0:i] + y_train_folds[i + 1:]
y = np.concatenate(y, axis=0)
test_x = np.array(x_train_folds[i])
test_y = np.array(y_train_folds[i])
classifier = Knn()
print(x)
classifier.fit(np.array(x), np.array(y))
y_pred = classifier.predict(k, 'M', test_x)
accuracy = np.mean(y_pred == test_y)
acc.append(accuracy)
k_to_accuracies[k] = acc
for k in sorted(k_to_accuracies):
for accuracy in k_to_accuracies[k]:
print('k=%d,accuracy=%f' % (k, accuracy))
from knn import Knn
# 导入数据
iris = datasets.load_iris()
X = iris.data[:, :2]
y = iris.target
# Kmeans
mdl_kmeans = Kmeans(k=3)
mdl_kmeans.fit(X)
# KNN
n_neighbors = 15
mdl_knn = Knn(k=n_neighbors)
mdl_knn.fit(X, y)
# 模型库
mdls = [mdl_kmeans, mdl_knn]
for mdl in mdls:
# 绘制预测图
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, .02),
np.arange(y_min, y_max, .02))
Z = mdl.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.figure()