- 博客(15)
- 资源 (3)
- 收藏
- 关注
RSS订阅原创 Python：计算类别分布CalculateClassDistribution
import numpy as npimport pandas as pdfrom sklearn import datasetsfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.metrics import cohen_kappa_scorefrom sklearn.metrics import preci...
2019-12-30 11:29:12
867
2
原创 Python：相对标准的DPC
import numpy as npimport pandas as pdimport copyimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn import metricsfrom scipy.spatial.distance import pdist,squareformfrom co...
2019-12-27 15:41:46
2226
14
原创 Python：HSAL
from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport numpy as npfrom sklearn import datasetsfrom sklearn.linear_model import Logistic...
2019-12-24 21:58:01
245
原创 Python：Hierarchical Sampling for Active Learning 2008年 ICML上的文章
from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport numpy as npfrom sklearn import datasetsfrom sklearn.linear_model import Logistic...
2019-12-24 20:37:27
398
原创 Python：numpy random choice
import numpy as npa = np.array([100,200,300,500,400,701,852,965])idx = np.random.choice(a,2,replace=False)print(idx)
2019-12-24 18:48:15
177
原创 Python：shuffle（a） 打乱array或list的顺序，原始的可迭代对象中元素顺序打乱，但原始对象的类别不变
import numpy as npa = np.array(range(20))print("a=",a)b = np.arange(20)print("b=",b)s_a = np.random.shuffle(a)s_b = np.random.shuffle(b)print(s_a)print(s_b)print("a=",a)print("b=",b)print...
2019-12-24 13:49:50
772
原创 intelligent-annotation 的使用，无tensorflow 运行通过！
from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport osimport pickleimport sysimport numpy as npfrom time import gmtimefrom time i...
2019-12-24 09:22:23
188
原创 Python：十折交叉验证sklearn KFold 的使用
from sklearn.model_selection import KFoldfrom sklearn.datasets import load_irisfrom sklearn.ensemble import RandomForestClassifierimport numpy as npX,y = load_iris(return_X_y=True)KF = KFold(n_s...
2019-12-22 23:06:11
11272
原创 Python：类别覆盖最小采样个数
import numpy as npimport scipy.io as scioimport pandas as pdimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.datasets import fetch_mldatafrom sklearn.datasets import fetc...
2019-12-21 12:24:18
283
原创 Python：处理Robot Navigation数据集的标签
import numpy as npimport pandas as pddata = np.array(pd.read_csv(r'E:\dataset\未处理数据集\Robot Navigation\sensor_readings_24.csv',header=None))X = data[:,:-1]y = data[:,-1]label = []n = len(y)fo...
2019-12-20 22:06:23
368
原创 Python：Semeion数据集标签处理
import numpy as npimport pandas as pdlabel = np.array(pd.read_csv(r'E:\dataset\未处理数据集\Semeion\label.csv',header=None))L = []n = label.shape[0]m = label.shape[1]for i in range(n): for j in ...
2019-12-20 21:20:29
698
原创 Python：下载轮子whl的地方
Unofficial Windows Binaries for Python Extension Packageshttps://www.lfd.uci.edu/~gohlke/pythonlibs/#tensorflow
2019-12-20 16:04:52
808
原创 关于什么是大数据智能决策！摘自《大数据智能决策》自动化学报
从本质上来讲，决策是决策者对决策对象或决策方案的一种分析对比和选择的过程，并最终对决策对象或决策方案进行分类、分级或排序。数据驱动的决策是决策者通过对与决策对象有关的数据进行分析，挖掘数据中隐含的有关决策对象之间的偏好关系的信息，根据得到的偏好关系信息对决策对象进行分类、分级或排序，并最终做出选择的全过程。 数据中带有用户对决策对象的偏好信息。 基于大数...
2019-12-06 21:11:15
3342
原创 Python：对array 使用 list（）不会改变array的类别
import numpy as npa = np.array([1,2,3,4,5])b = list(a)print(type(a))print(type(b))print(a)print(b)
2019-12-05 20:48:34
199
原创 python：给didi数据集添加标记
import pandas as pdimport numpy as npdata = pd.read_excel(r'E:\dataset\clusterData\didi_1.xls',header=None,index_col=None)data = np.array(data)print(data.shape)y = data[:,-1]n = len(y)labels ...
2019-12-02 15:25:42
549
Active learning via local structure reconstruction
2023-10-29
序分类数据集Nursery
2023-10-18
序分类数据集Melanoma
2023-10-18
序分类数据集Knowledge
2023-10-18
序分类数据集CTGs，数据类型：连续数值型
2023-10-18
序分类数据集eucalyptus
2023-10-18
序分类数据集Obesity
2023-10-18
主动学习方法：xPAL的python代码
2023-10-18
序分类数据集Nursery的one hot encoding版(12960个样本, 28个属性，类别数为5)
2023-05-15
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人