通过一个案例来理解机器学习的分类任务
关于数据集的相关介绍大家可以观看下面的连接:
iris数据集的介绍
根据数据集的特征值来预测目标值
即通过x来预测y
相应的代码如下:
# Training Machine Learning Algorithms for Classification
# 加载数据
s = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
print('From URL:', s)
df = pd.read_csv(s, header=None, encoding='utf-8')
s = 'iris.data'
print('From local Iris path:', s)
df = pd.read_csv(s, header=None, encoding='utf-8')
df.tail()
class Perceptron:"""感知器分类.参数------------eta : float学习率 (between 0.0 and 1.0)n_iter : int训练数据集的迭代次数random_state : int随机数量生成器做随机权重属性-----------w_ : 1d-array权重b_ : Scalar偏置项errors_ : list每个epoch的预测错误数量"""def __init__(self, eta=0.01, n_iter=50, random_state=1):self.eta = etaself.n_iter = n_iterself.random_state = random_statedef fit(self, X, y):"""拟合训练数据.参数----------X :shape = [n_examples, n_features]训练向量,其中n_examples是示例的数量,n_features是特征的数量。y :shape = [n_examples]目标值Returns-------self : object"""rgen = np.random.RandomState(self.random_state)self.w_ = rgen.normal(loc=0.0, scale=0.01, size=X.shape[1])self.b_ = np.float_(0.)self.errors_ = []for _ in range(self.n_iter):errors = 0for xi, target in zip(X, y):update = self.eta * (target - self.predict(xi))self.w_ += update * xiself.b_ += updateerrors += int(update != 0.0)self.errors_.append(errors)return selfdef net_input(self, X):"""Calculate net input"""return np.dot(X, self.w_) + self.b_def predict(self, X):"""Return class label after unit step"""return np.where(self.net_input(X) >= 0.0, 1, 0)
# ### Plotting the Iris data
# select setosa and versicolor
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', 0, 1)
# extract sepal length and petal length
X = df.iloc[0:100, [0, 2]].values
# plot data
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='s', label='Versicolor')
plt.xlabel('Sepal length [cm]')
plt.ylabel('Petal length [cm]')
plt.legend(loc='upper left')
# plt.savefig('images/02_06.png', dpi=300)
plt.show()
# ### Training the perceptron model
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.savefig('images/02_07.png', dpi=300)
plt.show()
# ### A function for plotting decision regions
def plot_decision_regions(X, y, classifier, resolution=0.02):# setup marker generator and color mapmarkers = ('o', 's', '^', 'v', '<')colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')cmap = ListedColormap(colors[:len(np.unique(y))])# plot the decision surfacex1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))lab = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)lab = lab.reshape(xx1.shape)plt.contourf(xx1, xx2, lab, alpha=0.3, cmap=cmap)plt.xlim(xx1.min(), xx1.max())plt.ylim(xx2.min(), xx2.max())# plot class examplesfor idx, cl in enumerate(np.unique(y)):plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], label=f'Class {cl}', edgecolor='black')
plot_decision_regions(X, y, classifier=ppn)
plt.xlabel('Sepal length [cm]')
plt.ylabel('Petal length [cm]')
plt.legend(loc='upper left')
plt.savefig('images/02_08.png', dpi=300)
plt.show()