资源列表
聚类
- 相似性划分,Q型聚类,是理想的多变量统计技术,主要有分层聚类法和迭代聚类法。 聚类分析也称群分析、点群分析,是研究分类的一种多元统计方法。(Similarity classification and Q clustering are ideal multivariate statistical techniques, including hierarchical clustering and iterative clustering. Cluster analysis, also known a
master
- 集体智慧编程源码,修改了部分小bug,更新了一些库的版本(Collective intelligence programming source code, modify part of the small bug, updated some of the library version.)
numpy基础
- Python 数据分析numpy库基础,方便大家学习。(Numpy Basic knowledge)
globle_kmeans
- 全局k-means算法,可有效解决传统k-means算法受初始点影响的缺陷,该方法可获得数据稳定的聚类结果。
naivebayes
- 朴素贝叶斯分类算法的代码,可实现多案例使用(The code of the simple Bias classification algorithm can be used for multiple cases)
TianChi_ijcai
- 根据过去一段时间的销售量,消费记录,预测商店的未来销售量(According to the sales volume and consumption record in the past period,Forecast the future sales volume of the store)
360563
- 本软件一共收录了355个TC2 0库函数,每一个函数都提供了相应的头文件,函数用途,函数全称,输入输出参数,函数的返回值,以()
SMOTE
- 针对非平衡数据集中少数类数据过少的问题进行过采样,SMOTE算法采用人工合成稀有类的方法将非平衡数据变为平衡数据之后在用于数据挖掘(Over sampling techniques for minority data)
dataanalyse
- 利用pandas、numpy、scipy组建的数据分析工具。可以实现均值、频数、最大值、最小值、分位数等得统计。(Data analysis tools built by pandas, numpy and SciPy. The statistics of mean, frequency, maximum, minimum and quantile can be achieved.)
load_ANN
- python 语言 Ann算法电力负荷预测,网上发现的,共享一下(Python language, Ann algorithm, power load forecasting, online discovery, sharing.)
rqpd_0.6
- 对数进行分位数回归分析,求得分位数回归方程参数。(The quantile regression analysis is performed on the logarithm to obtain the number of regression equations for the score.)
svm
- 该代码实现了经典的SVM支持向量机算法,Python语言编写,产生结果图。(This code implements the classic SVM support vector machine algorithm, Python language, and produces the result graph.)