from sklearn.preprocessing import StandardScaler
from sklearn.tree import DecisionTreeClassifier
from utils.graph import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
tree = DecisionTreeClassifier(criterion='entropy', max_depth=3, random_state=0)
tree.fit(X_train_std, y_train)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined_std,
y=y_combined,
classifier=tree,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
import numpy as np
from models.Perceptron import Perceptron
from utils.graph import plot_decision_regions
df = pd.read_csv(
'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data',
header=None)
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[0:100, [0, 2]].values
# plt.scatter(X[:50, 0], X[:50, 1], color='red', marker='o', label='setosa')
# plt.scatter(X[50:100, 0], X[50:100, 1], color='blue', marker='x', label='versicolor')
# plt.xlabel('sepal length')
# plt.ylabel('petal length')
# plt.legend(loc='upper left')
# plt.show()
ppn = Perceptron()
ppn.fit(X, y)
plt.plot(range(1, len(ppn._errors) + 1), ppn._errors, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Number of misclassifications')
plt.show()
plot_decision_regions(X, y, classifier=ppn)
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc='upper left')
plt.show()
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[0:100, [0, 2]].values
# fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(8,4))
# ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y)
# ax[0].plot(range(1, len(ada1._cost) + 1), np.log10(ada1._cost), marker='o')
# ax[0].set_xlabel('Epochs')
# ax[0].set_ylabel('log(Sum-squared-error)')
# ax[0].set_title('Adaline - learning_rate 0.01')
# ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y)
# ax[1].plot(range(1, len(ada2._cost) + 1), ada2._cost, marker='o')
# ax[1].set_xlabel('Epochs')
# ax[1].set_ylabel('Sum-squared-error')
# ax[1].set_title('Adaline - Learning_rate 0.0001')
# plt.show()
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
ada = AdalineGD(n_iter=15, eta=0.01).fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
plt.plot(range(1, len(ada._cost) + 1), ada._cost, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.show()
n = dataset.X_std_train[dataset.y_train == i+1, :].shape[0]
mean_vec = mean_vec.reshape(DIMENSION, 1)
S_B += n * (mean_vec - mean_overall).dot((mean_vec - mean_overall).T)
print(S_B.shape)
eigen_vals, eigen_vecs = np.linalg.eig(np.linalg.inv(S_W).dot(S_B))
eigen_pairs = [(np.abs(eigen_vals[i]), eigen_vecs[:, i]) for i in range(len(eigen_vals))]
eigen_pairs = sorted(eigen_pairs, key=lambda k: k[0], reverse=True)
# the first two linear discriminats (eigenvectors) capture the most class-discrimitatory information
tot = sum(eigen_vals.real)
discr = [(i / tot) for i in sorted(eigen_vals.real, reverse=True)]
cum_discr = np.cumsum(discr)
plt.bar(range(1, 14), discr, alpha=0.5, align='center', label='individual "discriminability"')
plt.step(range(1, 14), cum_discr, where='mid', label='cumulative "discriminability')
plt.ylabel('"discriminability" ratio')
plt.xlabel('Linear Discriminants')
plt.ylim([-0.1, 1.1])
plt.legend(loc='best')
plt.show()
w = np.hstack((eigen_pairs[0][1][:, np.newaxis].real, eigen_pairs[1][1][:, np.newaxis].real))
X_lda_train = dataset.X_std_train.dot(w)
lr = LogisticRegression()
lr.fit(X_lda_train, dataset.y_train)
plot_decision_regions(X=X_lda_train, y=dataset.y_train, classifier=lr)
plt.xlabel('ld1')
plt.ylabel('ld2')
plt.legend(loc='lower left')
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import SVC
from utils.graph import plot_decision_regions
np.random.seed(0)
X_xor = np.random.randn(200, 2)
y_xor = np.logical_xor(X_xor[:, 0] > 0, X_xor[:, 1] > 0)
y_xor = np.where(y_xor, 1, -1)
plt.scatter(X_xor[y_xor == 1, 0],
X_xor[y_xor == 1, 1],
c='b',
marker='x',
label='1')
plt.scatter(X_xor[y_xor == -1, 0],
X_xor[y_xor == -1, 1],
c='r',
marker='s',
label='-1')
plt.ylim(-3, 3)
plt.legend()
plt.show()
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_xor, y_xor)
plot_decision_regions(X_xor, y_xor, classifier=svm)
plt.legend(loc='upper left')
plt.show()