![](https://img-blog.csdnimg.cn/20201014180756918.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
数据挖掘
lesdiables
这个作者很懒,什么都没留下…
展开
-
预处理与降维
from sklearn.datasets import load_boston boston = load_boston() boston_data = boston['data'] boston_target = boston['target'] boston_names = boston['feature_names'] print('boston数据集数据的形状为:',boston_data.shape) print('boston数据集标签的形状为:',boston_target.shape) .原创 2021-12-10 08:44:17 · 480 阅读 · 0 评论 -
分类与聚类
from sklearn.datasets import load_iris iris = load_iris() iris_data = iris['data'] ##提取数据集中的特征 iris_target = iris['target'] ## 提取数据集中的标签 iris_names = iris['feature_names'] ### 提取特征名 print('iris数据集的特征名为:\n',iris_names) #sepal:花萼,petal:花瓣 iris特征集的特征名为 .原创 2021-12-10 08:51:38 · 760 阅读 · 0 评论 -
5.4 Logistic回归
# 使用LogisticRegression类构建Logistic回归模型 from sklearn.linear_model import LogisticRegression lr_model = LogisticRegression(solver='saga') # 训练Logistic回归模型 lr_model.fit(x_trainStd, y_train) #print('训练出来的LogisticRegression模型为:\n', lr_model) print('各特征的相关系数为:.原创 2022-05-05 17:42:52 · 729 阅读 · 0 评论 -
5 线性回归
from sklearn.datasets import load_boston from sklearn.model_selection import train_test_split # 导入load_boston数据,波士顿房价数据 boston = load_boston() x = boston['data'] y = boston['target'] names = boston['feature_names'] # 将数据划分为训练集和测试集 x_train, x_test, y_tra.原创 2022-05-05 17:41:03 · 1204 阅读 · 0 评论 -
5.1 最小二乘法拟合函数
import numpy as np from scipy import optimize import matplotlib.pyplot as plt from matplotlib import rcParams rcParams['font.sans-serif'] = 'SimHei' rcParams['axes.unicode_minus'] = False # 定义原始函数 def func(x,p): ''' x:表示函数的未知数x。 p:接收tuple,.原创 2022-05-05 17:32:57 · 823 阅读 · 0 评论 -
4 分类算法
from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split # 导入load_breast_cancer数据 cancer = load_breast_cancer() x = cancer['data'] y = cancer['target'] # 将数据划分为训练集测试集 x_train, x_test, y_train, y_test = train_te.原创 2022-04-07 10:39:33 · 979 阅读 · 0 评论 -
3.4 支持向量机异常检测
import numpy as np import matplotlib.pyplot as plt import matplotlib.font_manager from sklearn import svm # Generate train data X = 0.3 * np.random.randn(100, 2) #np.r_是按列连接两个矩阵,就是把两矩阵上下相加,要求列数相等。 #np.c_是按行连接两个矩阵,就是把两矩阵左右相加,要求行数相等。 X_train = np.r_[X + 2,.原创 2022-04-07 10:36:09 · 498 阅读 · 0 评论 -
验证曲线SVC
from sklearn.model_selection import validation_curve from sklearn.datasets import load_digits from sklearn.svm import SVC import matplotlib.pyplot as plt import numpy as np digits = load_digits() X = digits.data y = digits.target #建立参数测试集 param_range = .原创 2022-04-07 10:34:13 · 100 阅读 · 0 评论 -
学习曲线SVC
from sklearn.model_selection import learning_curve from sklearn.datasets import load_digits from sklearn.svm import SVC import matplotlib.pyplot as plt import numpy as np digits = load_digits() X = digits.data y = digits.target train_sizes, train_loss, te.原创 2022-04-07 10:32:33 · 153 阅读 · 0 评论 -
3 机器学习
from sklearn import datasets iris = datasets.load_iris() from sklearn.model_selection import train_test_split X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,test_size=0.4,random_state=0) from sklearn import svm #建立模型 svc = svm.SVC(.原创 2022-04-07 10:29:31 · 1337 阅读 · 0 评论