import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import SVC
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(-3.0)
plt.legend()
plt.show()
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_xor, y_xor)
from pdr import plot_decision_regions
plot_decision_regions(X=X_xor, y=y_xor, classifier=svm)
plt.legend(loc='upper left')
plt.show()
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)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
svm = SVC(kernel='linear', C=1.0, random_state=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('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
from sklearn.linear_model import SGDClassifier
SGDsvm = SGDClassifier(loss='hinge')
SGDsvm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=SGDsvm,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='entropy',
n_estimators=10,
random_state=0)
from sklearn import datasets
import numpy as np
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
forest.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
from pdr import plot_decision_regions
import matplotlib.pyplot as plt
plot_decision_regions(X=X_combined,
y=y_combined,
classifier=forest,
test_idx=range(105,150))
plt.title('Random Forest')
plt.xlabel('sepal length')
plt.ylabel('petal length')
plt.legend(loc='upper left')
plt.show()
#Splitting data sets
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
#Combining data
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
#Standardization
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
#KNN model
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
#Plotting Decision regions
plot_decision_regions(X_combined,
y_combined,
classifier=knn,
test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.title('KNN')
plt.show()
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='entropy',
max_depth=3, random_state=0)
from sklearn import datasets
import numpy as np
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
from pdr import plot_decision_regions
import matplotlib.pyplot as plt
plot_decision_regions(X=X_combined,
y=y_combined,
classifier=tree,
test_idx=range(105,150))
plt.title('Decision Tree')
plt.xlabel('sepal length')
plt.ylabel('petal length')
plt.legend(loc='upper left')
plt.show()
plt.figure(0)
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(-3.0)
plt.legend()
plt.show()
plt.figure(1)
svm = SVC(kernel = 'rbf', random_state = 0, gamma = 1.0, C = 10.0)
svm.fit(X_xor, y_xor)
plot_decision_regions(X_xor, y_xor, classifier = svm)
plt.title('Kernel SVM')
plt.legend(loc = 'upper left')
plt.show()
iris = 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)
X_combined_std = np.vstack((X_train_std, X_test_std))
#Standardize
ss = StandardScaler()
X_train_std = ss.fit_transform(X_train)
X_test_std = ss.transform(X_test)
#Initializing LDA and fit the training data
lda = LDA(n_components=2)
X_train_lda = lda.fit_transform(X_train_std, y_train)
#LR training
lr = LogisticRegression()
lr.fit(X_train_lda, y_train)
#Plot the decision regions of training set
plot_decision_regions(X_train_lda, y_train, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.title('LDA on training set')
plt.legend(loc='best')
plt.show()
#Plot the decision regions of test set
X_test_lda = lda.fit_transform(X_test_std, y_test)
plot_decision_regions(X_test_lda, y_test, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.title('LDA on test set')
plt.legend(loc='best')
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
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('petal length')
plt.ylabel('sepal length')
plt.legend(loc = 'upper left')
plt.show()
# get the perceptron model
model = Perceptron(eta = 0.1, n_iter = 10)
# train the model
model.fit(X, y)
# plot the training error
plt.plot(range(1, len(model.errors_) + 1), model.errors_, marker = 'o')
plt.xlabel('Epochs')
plt.ylabel('Number of misclassifications')
plt.show()
# create decision regions
pdr.plot_decision_regions(X, y, classifier = model)
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc = 'upper left')
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import SVC
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(-3.0)
plt.legend()
plt.show()
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_xor, y_xor)
from pdr import plot_decision_regions
plot_decision_regions(X=X_xor, y=y_xor, classifier=svm)
plt.legend(loc='upper left')
plt.show()
# Train the model
model1.fit(X_std, y)
# Plot the training error
plt.plot(range(1,
len(model1.cost_) + 1),
model1.cost_,
marker='o',
color='red')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.show()
# Plot the decision boundary
pdr.plot_decision_regions(X_std, y, classifier=model1)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [standardized')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
# Create the AdalineSGD model
model2 = AdalineSGD(n_iter=15, eta=0.01, random_state=1)
# Train the model
model2.fit(X_std, y)
# Plot the training errors of both of the models
plt.plot(range(1,
len(model2.cost_) + 1),