Yvesx的博客

sklearn中聚类算法和评价指标

模型随机森林是集成学习算法的一种。sklearn更多的集成学习算法RandomForestClassifier 参数详解重要的参数有基分类器的个数（n_estimators）、特征选择算法(critirion)、单个决策树的最大深度(max_depth)等。预处理import pandas as pdpath = "../Data/classify.csv"rawdata = pd.read_csv(path) X = rawdata.iloc[:,:13]Y = rawdata.iloc

模型sklearn.neighbors类库里有4个主要的模型，k最邻近：KNeighborsClassifier、KNeighborsRegressor；半径最邻近：RadiusNeighborsClassifier，RadiusNeighborsRegressor。classifier分类，regression回归这里使用KNeighborsClassifier参数详解最重要两个参数：metric knn的距离计算方式和n_neighbors k的大小。预处理import pandas as

模型sklearn.naive_bayes类库的主要分类器：GaussianNB, MultinomialNB, BernoulliNB参数详解预处理import pandas as pdpath = "../Data/classify.csv"rawdata = pd.read_csv(path) X = rawdata.iloc[:,:13]Y = rawdata.iloc[:,14] # {”A":0,"B":1,"C":2}Y = pd.Categorical(Y).codes

模型sklearn.svm中的支持向量机：Classify：SVC、nuSVC、LinearSVCRegression：SVR、nuSVR、LinearSVROneClassSVM本文采用Classify系列，classify三个模型的区别；参数详解预处理import pandas as pdpath = "../Data/classify.csv"rawdata = pd.read_csv(path) X = rawdata.iloc[:,:13]Y = rawdata.iloc[:

文章目录步骤建立模型特征选择预剪枝预处理训练测试+评价模型可视化不同的criterion和max_depth训练决策树结果步骤建立模型class sklearn.tree.DecisionTreeClassifier(criterion=’gini’, splitter=’best’, max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features=None, ran

文章目录多分类问题步骤建立模型预处理训练测试+评价模型多次划分训练集、测试集训练结果多分类问题步骤建立模型class sklearn.linear_model.LogisticRegression(penalty='l2', *, dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None, solver='lbfgs', max_iter=1