第一个机器学习项目代码：Iris Flower

第一个机器学习项目代码：Iris Flower

# -*- coding: utf-8 -*-
"""
第一个python学习项目
"""
# 导入类库
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

# 导入数据
filename = 'iris.data.csv'
names = ['separ-length', 'separ-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv(filename, names=names)

if __name__ == '__main__':
    # # 显示数据维度
    # print('数据维度： 行 %s， 列 %s' % dataset.shape)
    # print(dataset.head(10))
    # print(dataset.describe())
    # # 分类分布情况
    # print(dataset.groupby('class').size())
    # # 箱线图
    # # dataset.plot(kind='box', subplots=True, layout=(2, 2), sharex=False, sharey=False)
    # # 直方图
    # # dataset.hist()
    # # 散点矩阵图
    # scatter_matrix(dataset)
    # pyplot.show()

    # 分离数据集
    array = dataset.values
    X = array[:, 0:4]
    Y = array[:, 4]
    validation_size = 0.2
    seed = 7
    X_train, X_validation, Y_train, Y_validation = \
        train_test_split(X, Y, test_size=validation_size, random_state=seed)

    # 算法审查
    models = {'LR': LogisticRegression(), 'LDA': LinearDiscriminantAnalysis(), 'KNN': KNeighborsClassifier(),
              'CART': DecisionTreeClassifier(), 'NB': GaussianNB(), 'SVM': SVC()}
    # 评估算法
    results = []
    for key in models:
        # 10折交叉验证
        kFold = KFold(n_splits=10, shuffle=True, random_state=seed)
        cv_results = cross_val_score(models[key], X_train, Y_train, cv=kFold, scoring='accuracy')
        results.append(cv_results)
        print('%s: %f(%f)' % (key, cv_results.mean(), cv_results.std()))

    # 箱线图比较算法
    fig = pyplot.figure()
    fig.suptitle('Algorithm Comparison')
    ax = fig.add_subplot(111)
    pyplot.boxplot(results)
    ax.set_xticklabels(models.keys())
    pyplot.show()

    # 使用评估数据集评估SVM算法
    svm = SVC()
    svm.fit(X_train, Y_train)
    predictions = svm.predict(X_validation)
    print(accuracy_score(Y_validation, predictions))
    print(confusion_matrix(Y_validation, predictions))
    print(classification_report(Y_validation, predictions))

​ 代码学习书籍：机器学习Python实践