鸢尾花数据集的使用举例子

Question

机器学习常用数据集鸢尾花数据集的使用举例子，同时对数据集进行相应的介绍。

Answer 1

鸢尾花数据集（部分），共计150条记录，包含 setosa,versicolor,virginica 三种花型。
示例代码如下：

# coding: utf-8

from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.datasets import load_iris
import argparse

# 根据参数选择模型
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", type=str, default="knn", help="请输入模型简称")
args = vars(ap.parse_args())

models = {
    "knn": KNeighborsClassifier(n_neighbors=1),
    "naive_bayes": GaussianNB(),
    "logit": LogisticRegression(solver="lbfgs", multi_class="auto"),
    "svm": SVC(kernel="rbf", gamma="auto"),
    "decision_tree": DecisionTreeClassifier(),
    "random_forest": RandomForestClassifier(n_estimators=100),
    "mlp": MLPClassifier()
}

# 载入鸢尾花数据集，然后进行训练集和测试集的划分，75%数据作为训练集，其余25%作为测试集
# random_state是随机状态，类似随机种子
print("载入鸢尾花数据集...")
dataset = load_iris()
(trainX, testX, trainY, testY) = train_test_split(dataset.data, dataset.target, random_state=3, test_size=0.25)

# 训练模型
print("正在使用模型：'{}'".format(args["model"]))
model = models[args["model"]]
model.fit(trainX, trainY)

# 预测并输出一份分类结果报告
print("生成结果报告")
predictions = model.predict(testX)
print(classification_report(testY, predictions, target_names=dataset.target_names))