机器学习—基础算法（二）

机器学习——基础算法（二）

一、回归实践

（一）局部加权回归

（二）一般使用Logistic回归和Softmax回归进行分类。

#!/usr/bin/python
# -*- coding:utf-8 -*-

import numpy as np
import pandas as pd
from sklearn import preprocessing
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler, PolynomialFeatures
from sklearn.pipeline import Pipeline
import matplotlib.pyplot as plt
import matplotlib as mpl
import matplotlib.patches as mpatches




if __name__ == "__main__":
    path = 'iris.data'  # 数据文件路径

    # # # 手写读取数据
    # f = file(path)
    # x = []
    # y = []
    # for d in f:
    #     d = d.strip()
    #     if d:
    #         d = d.split(',')
    #         y.append(d[-1])
    #         x.append(map(float, d[:-1]))
    # print '原始数据X：\n', x
    # print '原始数据Y：\n', y
    # x = np.array(x)
    # print 'Numpy格式X：\n', x
    # y = np.array(y)
    # print 'Numpy格式Y - 1:\n', y
    # y[y == 'Iris-setosa'] = 0
    # y[y == 'Iris-versicolor'] = 1
    # y[y == 'Iris-virginica'] = 2
    # print 'Numpy格式Y - 2:\n', y
    # y = y.astype(dtype=np.int)
    # print 'Numpy格式Y - 3:\n', y
    # print '\n\n============================================\n\n'

    # # 使用sklearn的数据预处理
    # df = pd.read_csv(path, header=None)
    # x = df.values[:, :-1]
    # y = df.values[:, -1]
    # print x.shape
    # print y.shape
    # print 'x = \n', x
    # print 'y = \n', y
    # le = preprocessing.LabelEncoder()
    # le.fit(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
    # print le.classes_
    # y = le.transform(y)
    # print 'Last Version, y = \n', y

    # def iris_type(s):
    #     it = {'Iris-setosa': 0,
    #           'Iris-versicolor': 1,
    #           'Iris-virginica': 2}
    #     return it[s]
    #
    # # 路径，浮点型数据，逗号分隔，第4列使用函数iris_type单独处理
    # data = np.loadtxt(path, dtype=float, delimiter=',',
    #                   converters={4: iris_type})

    data = pd.read_csv(path, header=None)
    data[4] = pd.Categorical(data[4]).codes
    # iris_types = data[4].unique()
    # print iris_types
    # for i, type in enumerate(iris_types):
    #     data.set_value(data[4] == type, 4, i)
    x, y = np.split(data.values, (4,), axis=1)
    # print 'x = \n', x
    # print 'y = \n', y
    # 仅使用前两列特征
    x = x[:, :2]
    lr = Pipeline([('sc', StandardScaler()),
                   ('poly', PolynomialFeatures(degree=2)),
                   ('clf', LogisticRegression()) ])
    lr.fit(x, y.ravel())
    y_hat = lr.predict(x)
    y_hat_prob = lr.predict_proba(x)
    np.set_printoptions(suppress=True)
    print ('y_hat = \n', y_hat)
    print ('y_hat_prob = \n', y_hat_prob)
    print (u'准确度：%.2f%%' % (100*np.mean(y_hat == y.ravel())))
    # 画图
    N, M = 500, 500     # 横纵各采样多少个值
    x1_min, x1_max = x[:, 0].min(), x[:, 0].max()   # 第0列的范围
    x2_min, x2_max = x[:, 1].min(), x[:, 1].max()   # 第1列的范围
    t1 = np.linspace(x1_min, x1_max, N)
    t2 = np.linspace(x2_min, x2_max, M)
    x1, x2 = np.meshgrid(t1, t2)                    # 生成网格采样点
    x_test = np.stack((x1.flat, x2.flat), axis=1)   # 测试点

    # # 无意义，只是为了凑另外两个维度
    # x3 = np.ones(x1.size) * np.average(x[:, 2])
    # x4 = np.ones(x1.size) * np.average(x[:, 3])
    # x_test = np.stack((x1.flat, x2.flat, x3, x4), axis=1)  # 测试点

    mpl.rcParams['font.sans-serif'] = [u'simHei']
    mpl.rcParams['axes.unicode_minus'] = False
    cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
    cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
    y_hat = lr.predict(x_test)                  # 预测值
    y_hat = y_hat.reshape(x1.shape)                 # 使之与输入的形状相同
    plt.figure(facecolor='w')
    plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)     # 预测值的显示
    plt.scatter(x[:, 0], x[:, 1], c=np.squeeze(y), edgecolors='k', s=50, cmap=cm_dark)    # 样本的显示
    plt.xlabel(u'花萼长度', fontsize=14)
    plt.ylabel(u'花萼宽度', fontsize=14)
    plt.xlim(x1_min, x1_max)
    plt.ylim(x2_min, x2_max)
    plt.grid()
    patchs = [mpatches.Patch(color='#77E0A0', label='Iris-setosa'),
              mpatches.Patch(color='#FF8080', label='Iris-versicolor'),
              mpatches.Patch(color='#A0A0FF', label='Iris-virginica')]
    plt.legend(handles=patchs, fancybox=True, framealpha=0.8)
    plt.title(u'鸢尾花Logistic回归分类效果 - 标准化', fontsize=17)
    plt.show()

（二）

（三）AUC(分类器指标)

# -*-coding:utf-8-*-

import numbers
import numpy as np
import scipy as sp
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.svm import SVC
from sklearn.preprocessing import label_binarize
from numpy import interp
from sklearn import metrics
from itertools import cycle


if __name__ == '__main__':
    np.random.seed(0)
    pd.set_option('display.width', 300)
    np.set_printoptions(suppress=True)
    n = 300
    x = np.random.randn(n, 50)
    y = np.array([0]*100+[1]*100+[2]*100)
    n_class = 3

    alpha = np.logspace(-3, 3, 7)
    clf = LogisticRegression(penalty='l2', C=1)
    clf.fit(x, y)
    y_score = clf.decision_function(x)
    y = label_binarize(y, classes=np.arange(n_class))
    colors = cycle('gbc')
    fpr = dict()
    tpr = dict()
    auc = np.empty(n_class+2)
    mpl.rcParams['font.sans-serif'] = u'SimHei'
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(7, 6), facecolor='w')
    for i, color in zip(np.arange(n_class), colors):
        fpr[i], tpr[i], thresholds = metrics.roc_curve(y[:, i], y_score[:, i])
        auc[i] = metrics.auc(fpr[i], tpr[i])
        plt.plot(fpr[i], tpr[i], c=color, lw=1.5, alpha=0.7, label=u'AUC=%.3f' % auc[i])
    # micro
    fpr['micro'], tpr['micro'], thresholds = metrics.roc_curve(y.ravel(), y_score.ravel())
    auc[n_class] = metrics.auc(fpr['micro'], tpr['micro'])
    plt.plot(fpr['micro'], tpr['micro'], c='r', lw=2, ls='-', alpha=0.8, label=u'micro，AUC=%.3f' % auc[n_class])
    # macro
    fpr['macro'] = np.unique(np.concatenate([fpr[i] for i in np.arange(n_class)]))
    tpr_ = np.zeros_like(fpr['macro'])
    for i in np.arange(n_class):
        tpr_ += interp(fpr['macro'], fpr[i], tpr[i])
    tpr_ /= n_class
    tpr['macro'] = tpr_
    auc[n_class+1] = metrics.auc(fpr['macro'], tpr['macro'])
    print  (auc)
    print  ('Macro AUC:', metrics.roc_auc_score(y, y_score, average='macro'))
    plt.plot(fpr['macro'], tpr['macro'], c='m', lw=2, alpha=0.8, label=u'macro，AUC=%.3f' % auc[n_class+1])
    plt.plot((0, 1), (0, 1), c='#808080', lw=1.5, ls='--', alpha=0.7)
    plt.xlim((-0.01, 1.02))
    plt.ylim((-0.01, 1.02))
    plt.xticks(np.arange(0, 1.1, 0.1))
    plt.yticks(np.arange(0, 1.1, 0.1))
    plt.xlabel('False Positive Rate', fontsize=13)
    plt.ylabel('True Positive Rate', fontsize=13)
    plt.grid(b=True)
    plt.legend(loc='lower right', fancybox=True, framealpha=0.8, fontsize=12)
    # plt.legend(loc='lower right', fancybox=True, framealpha=0.8, edgecolor='#303030', fontsize=12)
    plt.title(u'ROC和AUC', fontsize=17)
    plt.show()

（三）用线性模型做预测

做差分y(i)-y(i-1)没有明显趋势增长，但是方差变大，即震荡加大。解决办法：取对数。

模型一：自回归

模型二：滑动平均;抹去周期性的震荡线


AR是自回归，MA是滑动平均 ，RMSE是差距值

二 、决策树和随机森林

（一）决策树的层数：Level

（二）条件熵

（三）相对熵

（四）互信息

（五）决策树（Decision Tree）

（六）Gini系数