weixin_44539090的博客

引用此文章

1、首先尝试了运行Reset Spyder Setting没用，还是闪一下就没然后了2、尝试了删除C:\Users\用户名\ 路径下的.spyder-py3文件夹，依然没用、3、重装了更高版本的Spyder，依然没用4、在Anaconda Powershell Prompt (Anaconda)中输入命令 spyderspyder --new-instance得到错误原因Bad file descriptor (C:\ci\zeromq_1602704446950\work\src\epol

import numpy as npimport matplotlib.pyplot as pltfrom matplotlib import rcimport matplotlib as mplimport matplotlib.font_manager as fmmyfont=fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')mpl.rcParams['axes.unicode_minus']=Falserc('mathtext', d

import numpy as npimport matplotlib.pyplot as pltfrom matplotlib import rcimport matplotlib as mplimport matplotlib.font_manager as fmmyfont=fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')mpl.rcParams['axes.unicode_minus']=Falseplt.rcParams['fo

兰德指数：需要给出真实标签信息轮廓系数calinski_harabaz分数

经典，更新这玩意更得解决措施如下：将红框框里的东西选中就Ok啦。spyder脚本无法访问variable explorer内的变量Spyder 脚本不能直接访问variable explorer 中已有的变量

如将plt.xticks(np.arange(len(S_D))+1,['决策树','神经网络','Bagging(决策树)','Bagging(神经网络)','SpeSBagging(决策树)','SpeSBagging(神经网络)','SpeSBagging(神经网络
决策树)'])改成plt.xticks(np.arange(len(S_D))+1,['决策树','神经网络','Bagging
(决策树)','Bagging
(神经网络)','SpeSBagging
(决策树)'

import numpy as npimport matplotlib.pyplot as pltfrom matplotlib import rcimport matplotlib as mplimport matplotlib.font_manager as fmmyfont=fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')mpl.rcParams['axes.unicode_minus']=Falserc('mathtext', d

from bao import *import matplotlib.pyplot as pltimport numpy as npimport pandas as pdimport matplotlib.font_manager as fmfrom collections import Counterfrom imblearn.over_sampling import BorderlineSMOTEfrom imblearn.over_sampling import SMOTEfrom s

题目：给定一个列表,请设计一个函数，实现传入一个target=3，输出3这个元素在列表a中的索引，输出格式如下：[0,7,13]a=[3,4,5,6,6,5,4,3,2,1,7,8,8,3]for index, nums in enumerate(a): if nums == target: b.append(index)print(b)...

from collections import Counterfrom sklearn.datasets import make_classificationfrom imblearn.over_sampling import ADASYNX, y = make_classification(n_classes=2, class_sep=2, weights=[0.1, 0.9], n_inf

from bao import *import matplotlib.pyplot as pltimport numpy as npimport pandas as pdimport matplotlib.font_manager as fmmyfont=fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')np.random.seed(668)#random_state = 2df = pd.read_csv('C:\\Users\\宝荣

import pandas as pdfrom sklearn.model_selection import train_test_splitfrom bao import *from sklearn import datasets # 导入库iris = datasets.load_iris() # 导入鸢尾花数据X = iris.datay = iris.targetX=np.array(X)y=np.array(y)#print(type(x_train))x_train

绘制散点图时代码如下：import numpy as npfrom bao import *from shujukuochong import *import matplotlib.font_manager as fmmyfont=fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')mpl.rcParams['axes.unicode_minus'] = Falsempl.rcParams['axes.unicode_minus']=Fals

import numpy as npfrom bao import *from shujukuochong import *plt.figure(figsize=(15,9)) colvalue=['#FF8C00','#FF1493', '#8B4513','#FF69B4', '#A9A9A9','#000000','#0000FF', '#800080','#556B2F','#008000','#FF0000','#32CD32','#48D1CC'] marke

上代码def f1(XX): A=[] #A为两个基分类器预测相同的个数 B=[] #B为量个基分类器预测不相同的个数 C=[] #用来存放多分类分歧度量值 for i in range(len(XX)): j=len(XX)-i-1 #print(j) if j>0: #print("ccc") for t in range(j):

以5行5列元素为例#把列表的数据依次填入矩阵对角线的一侧，另一侧与之对称import numpy as npfrom bao import *s=5#矩阵的行列数CC=np.array([0.3333333333333333, 0.3333333333333333, 0.2857142857142857, 0.38095238095238093, 0.19047619047619047, 0.14285714285714285, 0.23809523809523808, 0.2380952380

如车辆信息数据数据集数据量特征数类别简单分布是否有缺失值来源vehicle846184212/218/199/217否UCL下载到文件夹中将data文件选择打开方式用记事本打开将所有数据粘贴到新建的chelaingxinxi.txt文件中新建一个excel文件选择从文本导入数据选择chelaingxinxi.txt文件启用编辑选择按字符数分隔数据txt文件中数据以什么分隔此处就以什么分隔完成后点击关闭并上载得到想要的数据表

from sklearn import datasets # 导入库import numpy as npfrom collections import Counteriris = datasets.load_iris() # 导入鸢尾花数据#print(iris.data.shape,iris.target.shape) # (150, 4) (150,) 数据类型#print("
")#print(iris.feature_names) # [花萼长，花萼宽，花瓣长，花瓣宽] 属性

from sklearn.datasets import fetch_lfw_people#导入数据集，第一次可能等待时间过长，因为要在网上下载数据集import matplotlib.pyplot as pltpeople = fetch_lfw_people(min_faces_per_person=2,resize = 0.7)print(people.target_names)print("图像个数以及像素:{}".format(people.images.shape))#(9164, 87