一、取萼片的长宽作特征分类
导入相关的包
import numpy as np
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import datasets
from sklearn import preprocessing
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
数据集
df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=0)
x = df.values[:, :-1]
y = df.values[:, -1]
print('x = \n', x)
print('y = \n', y)
le = preprocessing.LabelEncoder()
le.fit(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
print(le.classes_)
y = le.transform(y)
print('Last Version, y = \n', y)
点击运行
对数据集进行处理
x = x[:, :2]
print(x)
print(y)
x = StandardScaler().fit_transform(x)
lr = LogisticRegression() # Logistic回归模型
lr.fit(x, y.ravel()) # 根据数据[x,y]，计算回归参数
绘制图像
N, M = 500, 500 # 横纵各采样多少个值
x1_min, x1_max = x[:, 0].min(), x[:, 0].max() # 第0列的范围
x2_min, x2_max = x[:, 1].min(), x[:, 1].max() # 第1列的范围
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
x_test = np.stack((x1.flat, x2.flat), axis=1) # 测试点
cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_hat = lr.predict(x_test) # 预测值
y_hat = y_hat.reshape(x1.shape) # 使之与输入的形状相同
plt.pcolormesh(x1, x2, y_hat, cmap=cm_light) # 预测值的显示
plt.scatter(x[:, 0], x[:, 1], c=y.ravel(), edgecolors='k', s=50, cmap=cm_dark)
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid()
plt.show()
预测模型
y_hat = lr.predict(X)
Y = Y.reshape(-1)
result = y_hat == Y
print(y_hat)
print(result)
acc = np.mean(result)
print('准确度: %.2f%%' % (100 * acc))
二、取花瓣的长宽作为特征进行分类
更改数据集
X=X[:,2:]
预测模型
