xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0],
y=X[y == cl, 1],
alpha=0.8,
c=cmap(idx),
marker=markers[idx],
label=cl)
ada = AdalineSGD(n_iter=15, eta=0.01, random_state=1)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Stochastic 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('Average Cost')
plt.show()
import numpy as np
from adalineSGD import AdalineSGD
from mainPerceptron import plot_decision_regions
# Print the tail of the data
df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=None)
# Visualisation the Data
y = df.iloc[0:100, 4].values
print(y)
y = np.where(y == 'Iris-setosa', -1, 1)
print(y)
X = df.iloc[0:100, [0, 2]].values
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 = AdalineSGD(n_iter=15, eta=0.01, random_state=1)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Stochastic 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('Average Cost')
plt.show()
from init_obj import create_universe, prepare_data, show_universe, test_model from adaline import Adaline from adalineSGD import AdalineSGD import numpy as np groups = create_universe() X, Y = prepare_data(groups) # show_universe(groups) y = np.where(Y == 'A', 1, -1) model = Adaline(0.0001, 50) model.fit(X, y) # stochastic model2 = AdalineSGD(0.0001, 50) model2.fit(X, y) test_model(X, model, model2)
We can see that the data is linearly separable. Now, let us run the
perceptron algorithm and look at the number of errors make during each
epoch.
"""
from adalineGD import AdalineGD
from adalineSGD import AdalineSGD
# Standardize data
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()
adln = AdalineGD(eta=0.01, n_iter=25)
adln.fit(X_std, y)
adln1 = AdalineSGD(eta=0.01, n_iter=25)
adln1.fit(X_std, y)
plt.plot(range(1,
len(adln1.errors_) + 1),
adln1.errors_,
marker='x',
color='red',
label='AdalineSGD')
plt.plot(range(1,
len(adln.errors_) + 1),
adln.errors_,
marker='o',
color='blue',
label='AdalineGD')
plt.xlabel('Epoch #')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.tight_layout()
plt.show()
# fit adaline with standardized features
# convergence is now successful with a learning rate of 0.01
# this adaline implementation uses stochastic gradient descient
ada = AdalineSGD(n_iter=15, eta=0.01, random_state=1)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Stochastic Gradient Descent')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Average Cost')