'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data',
header=None)
df.tail()
import matplotlib.pyplot as plt
import numpy as np
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[0:100, [0, 2]].values
from AdalineSDG import AdalineSDG
from DecisionRegion import plot_decision_regions
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 = AdalineSDG(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('Sum_squared-error')
plt.show()
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
#One-vs-Rest(OvR)
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
y_pred = knn.predict(X_test_std)
print('Misclassified samples: %d' % (y_test != y_pred).sum())
from sklearn.metrics import accuracy_score
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as pyplot
from DecisionRegion import plot_decision_regions
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=knn)
plt.xlabel('petal length [standardized]')
plt.ylabel('sepal length [standarsized]')
plt.legend(loc='upper left')
plt.show()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
#One-vs-Rest(OvR)
from sklearn.linear_model import Perceptron
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
ppn.fit(X_train_std, y_train)
y_pred = ppn.predict(X_test_std)
print('Misclassified samples: %d' % (y_test != y_pred).sum())
from sklearn.metrics import accuracy_score
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as pyplot
from DecisionRegion import plot_decision_regions
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=ppn,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('sepal length [standarsized]')
plt.legend(loc='upper left')
plt.show()
import matplotlib.pyplot as plt
import numpy as np
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='setaosa')
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()
from Perceptron import Perceptron
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 missclassifiactions')
plt.show()
from DecisionRegion import plot_decision_regions
plot_decision_regions(X, y, classifier=ppn)
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc='upper left')
plt.show()