from sklearn.decomposition import PCA
from sklearn.datasets import load_breast_cancer
from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter
cancer = load_breast_cancer()
(X_cancer, y_cancer) = load_breast_cancer(return_X_y=True)
# Before applying PCA, each feature should be centered (zero mean) and with unit variance
X_normalized = StandardScaler().fit(X_cancer).transform(X_cancer)
pca = PCA(n_components=2).fit(X_normalized)
X_pca = pca.transform(X_normalized)
print(X_cancer.shape, X_pca.shape)
plot_labelled_scatter(X_pca, y_cancer, ['malignant', 'benign'])
plt.xlabel('First principal component')
plt.ylabel('Second principal component')
plt.title('Breast Cancer Dataset PCA (n_components = 2)')
# Plotting the magnitude of each feature value for the first two principal components
fig = plt.figure(figsize=(8, 4))
plt.imshow(pca.components_, interpolation='none', cmap='plasma')
feature_names = list(cancer.feature_names)
plt.gca().set_xticks(np.arange(-.5, len(feature_names)))
plt.gca().set_yticks(np.arange(0.5, 2))
plt.gca().set_xticklabels(feature_names, rotation=90, ha='left', fontsize=12)
plt.gca().set_yticklabels(['First PC', 'Second PC'], va='bottom', fontsize=12)
plt.colorbar(orientation='horizontal',
ticks=[pca.components_.min(), 0,
from sklearn.datasets import make_blobs from sklearn.cluster import KMeans from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter X, y = make_blobs(random_state=10) kmeans = KMeans(n_clusters=3) kmeans.fit(X) plot_labelled_scatter(X, kmeans.labels_, ['Cluster 1', 'Cluster 2', 'Cluster 3'])
from sklearn.datasets import make_blobs
from sklearn.cluster import DBSCAN
from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter
X, y = make_blobs(n_samples=25, random_state=9)
dbscan = DBSCAN(eps=2, min_samples=2)
cls = dbscan.fit_predict(X)
print("Cluster membership values:\n{}".format(cls))
plot_labelled_scatter(X, cls + 1,
['Noise', 'Cluster 0', 'Cluster 1', 'Cluster 2'])
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
import pandas as pd
import matplotlib.pyplot as plt
from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter
tsne = TSNE(random_state=0)
fruits = pd.read_table('../resources/fruit_data_with_colors.txt')
feature_names_fruits = ['height', 'width', 'mass', 'color_score']
target_fruit_names = ['apple', 'mandarin', 'orange', 'lemon']
X_fruits = fruits[feature_names_fruits]
y_fruits = fruits['fruit_label']
# each feature should be centered (zero mean) and with unit variance
X_fruits_normalized = StandardScaler().fit(X_fruits).transform(X_fruits)
X_tsne = tsne.fit_transform(X_fruits_normalized)
plot_labelled_scatter(X_tsne, y_fruits,
['apple', 'mandarin', 'orange', 'lemon'])
plt.xlabel('First t-SNE feature')
plt.ylabel('Second t-SNE feature')
plt.title('Fruits dataset t-SNE')
from sklearn.datasets import make_blobs
from sklearn.cluster import AgglomerativeClustering
from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter
X, y = make_blobs(random_state=10)
cls = AgglomerativeClustering(n_clusters=3)
cls_assignment = cls.fit_predict(X)
plot_labelled_scatter(X, cls_assignment,
['Cluster 1', 'Cluster 2', 'Cluster 3'])
from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler
import pandas as pd
import matplotlib.pyplot as plt
from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter
fruits = pd.read_table('../resources/fruit_data_with_colors.txt')
feature_names_fruits = ['height', 'width', 'mass', 'color_score']
target_fruit_names = ['apple', 'mandarin', 'orange', 'lemon']
X_fruits = fruits[feature_names_fruits].values
y_fruits = fruits[['fruit_label']] - 1
X_fruits_normalized = MinMaxScaler().fit(X_fruits).transform(X_fruits)
kmeans = KMeans(n_clusters=4, random_state=0)
kmeans.fit(X_fruits_normalized)
plot_labelled_scatter(X_fruits_normalized, kmeans.labels_,
['Cluster 1', 'Cluster 2', 'Cluster 3', 'Cluster 4'])
import matplotlib.pyplot as plt from scipy.cluster.hierarchy import ward, dendrogram from sklearn.datasets import make_blobs from applied_machine_learning.fundamentals_of_machine_learning.adspy_shared_utilities import plot_labelled_scatter X, y = make_blobs(random_state=10, n_samples=10) plot_labelled_scatter(X, y, ['Cluster 1', 'Cluster 2', 'Cluster 3']) print(X) plt.figure() dendrogram(ward(X)) plt.show()
