python中sklearn库

import seaborn as sns
#加载数据集
iris = sns.load_dataset("iris")


#数据清洗，筛去部分特征
iris_simple = iris.drop(["sepal_length", "sepal_width"], axis=1)
iris_simple.head()


#标签编码，将字符串映射为整数
from sklearn.preprocessing import LabelEncoder
encoder = LabelEncoder()
iris_simple["species"] = encoder.fit_transform(iris_simple["species"])


#构建训练集和测试集合
from sklearn.model_selection import train_test_split
train_set, test_set = train_test_split(iris_simple, test_size=0.2)
test_set.head()


#分离训练集的特征和标签
iris_x_train = train_set[["petal_length", "petal_width"]]
iris_y_train = train_set["species"].copy()


#分离测试集的特征和标签
iris_x_test = test_set[["petal_length", "petal_width"]]
iris_y_test = test_set["species"].copy()

from sklearn.neighbors import KNeighborsClassifier


#构建分类器对象，目的就是训练出这个对象
clf = KNeighborsClassifier()


#训练分类器对象
clf.fit(iris_x_train, iris_y_train)


#将训练好的分类器来预测测试集结果
res = clf.predict(iris_x_test)
print(res)
print(iris_y_test.values)


#评估结果
accuracy = clf.score(iris_x_test, iris_y_test)
print("预测正确率:{:.0%}".format(accuracy))


#存储数据
out = iris_x_test.copy()
out["y"] = iris_y_test
out["pre"] = res
out.to_csv("iris_predict.csv")

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt


def draw(clf):


    # 将数据特征网格化
    M, N = 500, 500
    x1_min, x2_min = iris_simple[["petal_length", "petal_width"]].min(axis=0)
    x1_max, x2_max = iris_simple[["petal_length", "petal_width"]].max(axis=0)
    t1 = np.linspace(x1_min, x1_max, M)
    t2 = np.linspace(x2_min, x2_max, N)
    x1, x2 = np.meshgrid(t1, t2)
    
    # 用分类器预测每一个网格
    x_show = np.stack((x1.flat, x2.flat), axis=1)
    y_predict = clf.predict(x_show)
    
    # 配色
    cm_light = mpl.colors.ListedColormap(["#A0FFA0", "#FFA0A0", "#A0A0FF"])
    cm_dark = mpl.colors.ListedColormap(["g", "r", "b"])
    
    # 绘制预测区域图
    plt.figure(figsize=(10, 6))
    plt.pcolormesh(t1, t2, y_predict.reshape(x1.shape), cmap=cm_light)
    
    # 绘制原始数据点
    plt.scatter(iris_simple["petal_length"], iris_simple["petal_width"], label=None,
                c=iris_simple["species"], cmap=cm_dark, marker='o', edgecolors='k')
    plt.xlabel("petal_length")
    plt.ylabel("petal_width")
    
    # 绘制图例
    color = ["g", "r", "b"]
    species = ["setosa", "virginica", "versicolor"]
    for i in range(3):
        plt.scatter([], [], c=color[i], s=40, label=species[i])    # 利用空点绘制图例
    plt.legend(loc="best")
    plt.title('iris_classfier')
    
#调用函数
draw(clf)

from sklearn.naive_bayes import GaussianNB
#构建分类器对象，目的就是训练这个对象
clf = GaussianNB()
#训练
clf.fit(iris_x_train, iris_y_train)
#预测
res = clf.predict(iris_x_test)
print(res)
print(iris_y_test.values)
#评估结果
accuracy = clf.score(iris_x_test, iris_y_test)
print("预测正确率:{:.0%}".format(accuracy))
可视化
draw(clf)