sklearn iris(鸢尾花)数据集应用

数据背景

由Fisher在1936年整理，包含4个特征（Sepal.Length（花萼长度）、Sepal.Width（花萼宽度）、Petal.Length（花瓣长度）、Petal.Width（花瓣宽度）），特征值都为正浮点数，单位为厘米。目标值为鸢尾花的分类（Iris Setosa（山鸢尾）、Iris Versicolour（杂色鸢尾），Iris Virginica（维吉尼亚鸢尾））。

测试代码

新建lr_riis.py文件，编写代码

# -*- coding:utf-8 -*-
import numpy as np

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

def load_data():
    iris = datasets.load_iris()
    print(iris.keys())
    n_samples, n_features = iris.data.shape
    print((n_samples, n_features))
    print(iris.data[0])
    print(iris.target.shape)
    print(iris.target)
    print(iris.target_names)
    print("feature_names:", iris.feature_names)


def main():
   load_data()

if __name__ == '__main__':
    main()

运行结果为：

由结果可知：
iris中有5个key值

iris.data 包含了四个特征值，例如[5.1, 3.5, 1.4, 0.2]
iris.target为目标值
iris.feature_names为特征名称

模型预测实践

重新更新下代码

# -*- coding:utf-8 -*-
import numpy as np

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

def load_data():
    # 共150条数据，训练120条，测试30条，进行2,8分进行模型训练
    # 每条数据类型为 x{nbarray} [6.4, 3.1, 5.5, 1.8]
    inputdata = datasets.load_iris()
    # 切分，测试训练2,8分
    x_train, x_test, y_train, y_test = \
        train_test_split(inputdata.data, inputdata.target, test_size = 0.2, random_state=0)
    return x_train, x_test, y_train, y_test

def main():
    # 训练集x ,测试集x,训练集label,测试集label
    x_train, x_test, y_train, y_test = load_data()
    # l2为正则项
    model = LogisticRegression(penalty='l2')
    model.fit(x_train, y_train)

    print "w: ", model.coef_
    print "b: ", model.intercept_
    # 准确率
    print "precision: ", model.score(x_test, y_test)
    print "MSE: ", np.mean((model.predict(x_test) - y_test) ** 2)

if __name__ == '__main__':
    main()

运行结果为：