return self.sigmoid(X)
def net_input(self, X):
return np.dot(X, self.w_[1:]) + self.w_[0]
def predict(self, X):
return np.where(self.net_input(X) >= 0.0, 1, 0)
X_train_01_subset = X_train[(y_train == 0) | (y_train == 1)]
y_train_01_subset = y_train[(y_train == 0) | (y_train == 1)]
lrgd = LogisticRegressionGD(eta=0.05, n_iter=1000, random_state=1)
lrgd.fit(X_train_01_subset, y_train_01_subset)
plot_decision_regions(X=X_train_01_subset,
y=y_train_01_subset,
classifier=lrgd)
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
from sklearn.linear_model import LogisticRegression
# -*- coding: utf-8 -*-
import matplotlib.pyplot as plt
from lib import plot_decision_regions, get_iris_data
from sklearn.neighbors import KNeighborsClassifier
X_train, X_train_std, X_combined, X_combined_std, X_test, y_train, y_combined, y_test = get_iris_data(
)
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=knn,
test_idx=range(105, 150))
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
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 square error)')
ax[0].set_title('Adaline - Learning rate 0.01')
ada2 = AdalineGD(eta=0.0001, n_iter=10).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 square 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(eta=0.01, n_iter=15)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [stadardized]')
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-square-error')
plt.show()
#!/usr/bin/python3
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from perceptron import Perceptron
from lib 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]
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[50:110, 0], X[50:110, 1], color='blue', marker='x',label='versicolor')
plt.xlabel('sepal length')
plt.ylabel('petal length')
plt.legend(loc='upper left')
"""
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(X, y)
"""
plt.plot(range(1, len(ppn.errors_) + 1), ppn.errors_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Number of misclassifications')
"""
plot_decision_regions(X, y, classifier=ppn)
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.xlim([-3, 3])
plt.ylim([-3, 3])
plt.legend(loc='best')
plt.show()
svm = SVC(kernel='rbf', C=10.0, gamma=0.10, random_state=1)
svm.fit(X_xor, y_xor)
plot_decision_regions(X_xor, y_xor, classifier=svm)
plt.legend(loc='upper left')
plt.show()
X_train, X_train_std, X_combined, X_combined_std, X_test, y_train, y_combined, y_test = get_iris_data(
)
svm = SVC(kernel='rbf', random_state=1, gamma=0.2, C=1.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=svm,
test_idx=range(105, 150))
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
c=c,
label=l,
marker=m)
plt.xlabel('LD1')
plt.ylabel('LD2')
plt.legend(loc='lower right')
plt.show()
# Scikit-learn
from sklearn.linear_model import LogisticRegression
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
lda = LDA(n_components=2)
X_train_lda = lda.fit_transform(X_train_std, y_train)
lr = LogisticRegression()
lr = lr.fit(X_train_lda, y_train)
plot_decision_regions(X_train_lda, y_train, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc='lower left')
plt.show()
# test set
X_test_lda = lda.transform(X_test_std)
plot_decision_regions(X_test_lda, y_test, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc='lower left')
plt.show()
color='blue',
marker='x',
label='versicolor')
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc='upper left')
plt.show()
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(X, y)
plt.plot(range(1, len(ppn.errors_) + 1), ppn.errors_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Number of updates')
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()
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
print('Class labels:', np.unique(y))
