分类算法实例四：用Logistic算法和KNN算法进行鸢尾花数据分类

墨蓝 2023-07-13 13:37 154阅读 0赞

import numpy as np
    import matplotlib as mpl
    import matplotlib.pyplot as plt
    import pandas as pd
    import warnings
    import sklearn
    from sklearn.linear_model import LogisticRegressionCV
    from sklearn.linear_model.coordinate_descent import ConvergenceWarning
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.preprocessing import label_binarize
    from sklearn import metrics
    
    # 设置字符集，防止中文乱码
    mpl.rcParams['font.sans-serif']=[u'simHei']
    mpl.rcParams['axes.unicode_minus']=False
    # 拦截异常
    warnings.filterwarnings(action = 'ignore', category=ConvergenceWarning)
    
    # 数据加载
    path = "datas/iris.data"
    names = ['sepal length', 'sepal width', 'petal length', 'petal width', 'cla']
    df = pd.read_csv(path, header=None, names=names)
    df['cla'].value_counts()
    df.head()

![20200312132438124.png][]

def parseRecord(record):
        result=[]
        r = zip(names,record)
        for name,v in r:
            if name == 'cla':
                if v == 'Iris-setosa':
                    result.append(1)
                elif v == 'Iris-versicolor':
                    result.append(2)
                elif v == 'Iris-virginica':
                    result.append(3)
                else:
                    result.append(np.nan)
            else:
                result.append(float(v))
        return result

# 1. 数据转换为数字以及分割
    # 数据转换
    datas = df.apply(lambda r: parseRecord(r), axis=1)
    # 异常数据删除
    datas = datas.dropna(how='any')
    # 数据分割
    X = datas[names[0:-1]]
    Y = datas[names[-1]]
    # 数据抽样（训练数据和测试数据分割）
    X_train,X_test,Y_train,Y_test = train_test_split(X, Y, test_size=0.4, random_state=0)
    
    print ("原始数据条数:%d；训练数据条数:%d；特征个数:%d；测试样本条数:%d" % (len(X), len(X_train), X_train.shape[1], X_test.shape[0]))

![20200312133056855.png][]

# 2. 数据标准化
    ss = StandardScaler()
    X_train = ss.fit_transform(X_train)
    X_test = ss.transform(X_test)
    
    # 3. 特征选择
    
    # 4. 降维处理
    
    # 5. 模型构建
    lr = LogisticRegressionCV(Cs=np.logspace(-4,1,50), cv=3, fit_intercept=True, penalty='l2', solver='lbfgs', tol=0.01, multi_class='multinomial')
    # solver可选：‘newton-cg’, 'lbfgs', 'liblinear', 'sag'（mini-batch），默认为liblinear
    lr.fit(X_train, Y_train)

![20200312134313510.png][]

# 6. 模型效果输出
    # 将正确的数据转换为矩阵形式
    y_test_hot = label_binarize(Y_test,classes=(1,2,3))
    # 得到预测的损失值
    lr_y_score = lr.decision_function(X_test)
    # 计算ROC的值
    lr_fpr, lr_tpr, lr_threasholds = metrics.roc_curve(y_test_hot.ravel(),lr_y_score.ravel())
    # threasholds阈值
    # 计算AUC的值
    lr_auc = metrics.auc(lr_fpr, lr_tpr)
    print ("Logistic算法R值：", lr.score(X_train, Y_train))
    print ("Logistic算法AUC值：", lr_auc)
    
    # 7. 模型预测
    lr_y_predict = lr.predict(X_test)

![20200312134703137.png][]

# KNN算法实现
    # a. 模型构建
    knn = KNeighborsClassifier(n_neighbors=3)
    knn.fit(X_train, Y_train)
    
    # b. 模型效果输出
    # 将正确的数据转换为矩阵形式
    y_test_hot = label_binarize(Y_test,classes=(1,2,3))
    # 得到预测的损失值
    knn_y_score = knn.predict_proba(X_test)
    # 计算ROC的值
    knn_fpr, knn_tpr, knn_threasholds = metrics.roc_curve(y_test_hot.ravel(),knn_y_score.ravel())
    # 计算AUC的值
    knn_auc = metrics.auc(knn_fpr, knn_tpr)
    print ("KNN算法R值：", knn.score(X_train, Y_train))
    print ("KNN算法AUC值：", knn_auc)
    
    # c. 模型预测
    knn_y_predict = knn.predict(X_test)
    knn_y_score

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70][]

# 画图1：ROC曲线画图
    plt.figure(figsize=(8, 6), facecolor='w')
    plt.plot(lr_fpr,lr_tpr,c='r',lw=2,label=u'Logistic算法,AUC=%.3f' % lr_auc)
    plt.plot(knn_fpr,knn_tpr,c='g',lw=2,label=u'KNN算法,AUC=%.3f' % knn_auc)
    plt.plot((0,1),(0,1),c='#a0a0a0',lw=2,ls='--')
    # 设置X轴的最大和最小值
    plt.xlim(-0.01, 1.02)
    # 设置y轴的最大和最小值
    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(FPR)', fontsize=16)
    plt.ylabel('True Positive Rate(TPR)', fontsize=16)
    plt.grid(b=True, ls=':')
    plt.legend(loc='lower right', fancybox=True, framealpha=0.8, fontsize=12)
    plt.title(u'鸢尾花数据Logistic和KNN算法的ROC/AUC', fontsize=18)
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70 1][]

# 画图2：预测结果画图
    x_test_len = range(len(X_test))
    plt.figure(figsize=(12, 9), facecolor='w')
    plt.ylim(0.5,3.5)
    plt.plot(x_test_len, Y_test, 'ro',markersize = 6, zorder=3, label=u'真实值')
    plt.plot(x_test_len, lr_y_predict, 'go', markersize = 10, zorder=2, label=u'Logis算法预测值,$R^2$=%.3f' % lr.score(X_test, Y_test))
    plt.plot(x_test_len, knn_y_predict, 'yo', markersize = 16, zorder=1, label=u'KNN算法预测值,$R^2$=%.3f' % knn.score(X_test, Y_test))
    plt.legend(loc = 'lower right')
    plt.xlabel(u'数据编号', fontsize=18)
    plt.ylabel(u'种类', fontsize=18)
    plt.title(u'鸢尾花数据分类', fontsize=20)
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70 2][]

[20200312132438124.png]: https://img-blog.csdnimg.cn/20200312132438124.png
[20200312133056855.png]: https://img-blog.csdnimg.cn/20200312133056855.png
[20200312134313510.png]: https://img-blog.csdnimg.cn/20200312134313510.png
[20200312134703137.png]: https://img-blog.csdnimg.cn/20200312134703137.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200312135233995.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU=,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200312140043430.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU=,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20200312140410852.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU=,size_16,color_FFFFFF,t_70