應(yīng)用機(jī)器學(xué)習(xí)分類算法的五個步驟

• 選擇特征
• 選擇一個性能指標(biāo)
• 選擇一個分類器和一個優(yōu)化算法
• 評價模型的性能
• 優(yōu)化算法

選擇 scikit-learn

構(gòu)建一個基于scikit-learn 的 perceptron

讀取數(shù)據(jù) - iris

分配訓(xùn)練集和測試集

標(biāo)準(zhǔn)化特征值

訓(xùn)練感知器模型

用訓(xùn)練好的模型進(jìn)行預(yù)測

計算性能指標(biāo)

描繪分類界面

# encoding:utf-8
__author__ = 'Matter'

# 讀取數(shù)據(jù)
from sklearn import datasets
import numpy as np
iris = datasets.load_iris()
X = iris.data[:,[2,3]]
y = iris.target

# 訓(xùn)練數(shù)據(jù)和測試數(shù)據(jù)分為7:3
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)

# 標(biāo)準(zhǔn)化數(shù)據(jù)
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)

# 引入sklearn的Perceptron并進(jìn)行訓(xùn)練
from sklearn.linear_model import Perceptron
ppn = Perceptron(n_iter=40,eta0=0.01,random_state=0)
ppn.fit(x_train_std,y_train)


y_pred = ppn.predict(x_test_std)
print('錯誤分類數(shù): %d' % (y_test != y_pred).sum())
# 錯誤分類數(shù):4

from sklearn.metrics import accuracy_score
print('準(zhǔn)確率: %.2f' % accuracy_score(y_test, y_pred))
# 準(zhǔn)確率: 0.91

# 繪制決策邊界
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
import warnings

def versiontuple(v):
    return tuple(map(int, (v.split("."))))

def plot_decision_regions(X,y,classifier,test_idx=None,resolution=0.02):
    # 設(shè)置標(biāo)記點(diǎn)和顏色
    markers = ('s','x','o','^','v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # 繪制決策面
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    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())

    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)

    # 高粱所有的數(shù)據(jù)點(diǎn)
    if test_idx:
        # 繪制所有數(shù)據(jù)點(diǎn)
        if not versiontuple(np.__version__) >= versiontuple('1.9.0'):
            X_test, y_test = X[list(test_idx), :], y[list(test_idx)]
            warnings.warn('Please update to NumPy 1.9.0 or newer')
        else:
            X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='',
                alpha=1.0, linewidth=1, marker='o',
                s=55, label='test set')

def plot_result():
    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('petal width [standardized]')
    plt.legend(loc='upper left')

    plt.tight_layout()
    plt.show()

plot_result()

繪制決策邊界