KNN

.

data = pd.read_csv("car.data")
# print(data.head())

le = preprocessing.LabelEncoder()
buying = le.fit_transform(list(data["buying"]))
maint = le.fit_transform(list(data["maint"]))
door = le.fit_transform(list(data["door"]))
persons = le.fit_transform(list(data["persons"]))
safety = le.fit_transform(list(data["safety"]))
lug_boot = le.fit_transform(list(data["lug_boot"]))
cls = le.fit_transform(list(data["class"]))
# print(buying)

predict = "class"

x = list(zip(buying, maint, door, persons, lug_boot, safety))
y = list(cls)

x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(x, y, test_size=0.1)
# print(x_train, y_train)

model = KNeighborsClassifier(n_neighbors=5)
model.fit(x_train, y_train)
acc = model.score(x_test, y_test)
print(acc)

predicted = model.predict(x_test)
names = ['unacc', 'acc', 'good', 'vgood']

for x in range(len(predicted)):
    print("Predicted: ", names[predicted[x]], "Data: ", x_test[x], "Actual: ", names[y_test[x]])
    n = model.kneighbors([x_test[x]], 5, True)
    print("N: ", n)

SVM

.

cancer = datasets.load_breast_cancer()
# print(cancer.feature_names)
# print(cancer.target_names)

x = cancer.data
y = cancer.target

x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(x, y, test_size=0.2)
# print(x_train, y_train)

classes = ['malignant' 'benign']

cls = svm.SVC(kernel="linear", C=2)
# kernel="poly", degree=2
cls.fit(x_train, y_train)

y_pred = cls.predict(x_test)

acc = metrics.accuracy_score(y_test, y_pred)
print(acc)


clf = KNeighborsClassifier(n_neighbors=9)
clf.fit(x_train, y_train)
y_pred_2 = clf.predict(x_test)
acc_2 = metrics.accuracy_score(y_test, y_pred_2)
print(acc_2)

K Means

.

digits = load_digits()
data = scale(digits.data)
y = digits.target

k = 10
samples, features = data.shape


def bench_k_means(estimator, name, data):
    estimator.fit(data)
    print('%-9s\t%i\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f'
          % (name, estimator.inertia_,
             metrics.homogeneity_score(y, estimator.labels_),
             metrics.completeness_score(y, estimator.labels_),
             metrics.v_measure_score(y, estimator.labels_),
             metrics.adjusted_rand_score(y, estimator.labels_),
             metrics.adjusted_mutual_info_score(y,  estimator.labels_),
             metrics.silhouette_score(data, estimator.labels_,
                                      metric='euclidean')))

clf = KMeans(n_clusters=k, init="random", n_init=10)
bench_k_means(clf, "1", data)

K Means p2

.

np.random.seed(42)

digits = load_digits()
data = scale(digits.data)

n_samples, n_features = data.shape
n_digits = len(np.unique(digits.target))
labels = digits.target

sample_size = 300

print("n_digits: %d, \t n_samples %d, \t n_features %d"
      % (n_digits, n_samples, n_features))


print(82 * '_')
print('init\t\ttime\tinertia\thomo\tcompl\tv-meas\tARI\tAMI\tsilhouette')


def bench_k_means(estimator, name, data):
    t0 = time()
    estimator.fit(data)
    print('%-9s\t%.2fs\t%i\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f'
          % (name, (time() - t0), estimator.inertia_,
             metrics.homogeneity_score(labels, estimator.labels_),
             metrics.completeness_score(labels, estimator.labels_),
             metrics.v_measure_score(labels, estimator.labels_),
             metrics.adjusted_rand_score(labels, estimator.labels_),
             metrics.adjusted_mutual_info_score(labels,  estimator.labels_),
             metrics.silhouette_score(data, estimator.labels_,
                                      metric='euclidean',
                                      sample_size=sample_size)))

bench_k_means(KMeans(init='k-means++', n_clusters=n_digits, n_init=10),
              name="k-means++", data=data)

bench_k_means(KMeans(init='random', n_clusters=n_digits, n_init=10),
              name="random", data=data)


print(82 * '_')

# #############################################################################
# Visualize the results on PCA-reduced data

reduced_data = PCA(n_components=2).fit_transform(data)
kmeans = KMeans(init='k-means++', n_clusters=n_digits, n_init=10)
kmeans.fit(reduced_data)

# Step size of the mesh. Decrease to increase the quality of the VQ.
h = .02     # point in the mesh [x_min, x_max]x[y_min, y_max].

# Plot the decision boundary. For that, we will assign a color to each
x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))

# Obtain labels for each point in mesh. Use last trained model.
Z = kmeans.predict(np.c_[xx.ravel(), yy.ravel()])

# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1)
plt.clf()
plt.imshow(Z, interpolation='nearest',
           extent=(xx.min(), xx.max(), yy.min(), yy.max()),
           cmap=plt.cm.Paired,
           aspect='auto', origin='lower')

plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
# Plot the centroids as a white X
centroids = kmeans.cluster_centers_
plt.scatter(centroids[:, 0], centroids[:, 1],
            marker='x', s=169, linewidths=3,
            color='w', zorder=10)
plt.title('K-means clustering on the digits dataset (PCA-reduced data)\n'
          'Centroids are marked with white cross')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
plt.show()