学习笔记——仅仅为了留下Pima印第安人糖尿病发病数据集的网址

最新推荐文章于 2023-12-30 16:51:09 发布

潘达酱豆是沃

最新推荐文章于 2023-12-30 16:51:09 发布

阅读量625

点赞数

分类专栏：转载学习

原文链接：https://blog.csdn.net/qq_42370150/article/details/96189615

版权

转载学习专栏收录该内容

15 篇文章 0 订阅

订阅专栏

本文链接： https://blog.csdn.net/qq_42370150/article/details/96189615

            </div>
                                                <!--一个博主专栏付费入口-->
         
         <!--一个博主专栏付费入口结束-->
        <link rel="stylesheet" href="https://csdnimg.cn/release/phoenix/template/css/ck_htmledit_views-4a3473df85.css">
                                    <link rel="stylesheet" href="https://csdnimg.cn/release/phoenix/template/css/ck_htmledit_views-4a3473df85.css">
            <div class="htmledit_views" id="content_views">
                                        <h3><a name="t0"></a>查看对应的版本</h3>


 
 
   
   
    
    
   
   
   
   
    
    
     
     # 下载和安装Python和SciPy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # Python version
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import sys
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('Python: {}'.format(sys.version))
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # scipy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import scipy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('scipy: {}'.format(scipy.__version__))
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # numpy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import numpy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('numpy: {}'.format(numpy.__version__))
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # matplotlib
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import matplotlib
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('matplotlib: {}'.format(matplotlib.__version__))
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # pandas
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import pandas
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('pandas: {}'.format(pandas.__version__))
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # scikit-learn
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import sklearn
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print('sklearn: {}'.format(sklearn.__version__))

新建一个简单的Dataframe(数据帧)


 
 
   
   
    
    
   
   
   
   
    
    
     
     import numpy
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import pandas
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     import matplotlib.pyplot as plt
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 散点矩形
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     from pandas.plotting import scatter_matrix
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 特征缩放
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     from sklearn.preprocessing import StandardScaler
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 交叉验证法
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     from sklearn.model_selection import KFold
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 逻辑回归
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     from sklearn.linear_model import LogisticRegression
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     myarray = numpy.array([[1, 2, 3], [4, 5, 6]])
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     rownames = ['a', 'b']
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     colnames = ['one', 'two', 'three']
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     mydataframe = pandas.DataFrame(myarray, index=rownames, columns=colnames)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print(mydataframe)


 
 
   
   
    
    
   
   
   
   
    
    
     
        one  two  three
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     a    1    2      3
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     b    4    5      6

从csv加载数据输出的为行列


 
 
   
   
    
    
   
   
   
   
    
    
     
     import pandas
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     data = pandas.read_csv(url, names=names)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 行列
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print(data.shape)

csv数据转换用描述性统计理解数据


 
 
   
   
    
    
   
   
   
   
    
    
     
     data = pandas.read_csv(url, names=names)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     description = data.describe()
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print(description)

绘图用可视化理解数据


 
 
   
   
    
    
   
   
   
   
    
    
     
     data = pandas.read_csv(url, names=names)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     scatter_matrix(data)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     plt.show()

为预处理数据建模做准备


 
 
   
   
    
    
   
   
   
   
    
    
     
     dataframe = pandas.read_csv(url, names=names)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     array = dataframe.values
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 数组分成输入和输出组件
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     X = array[:,0:8]
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     Y = array[:,8]
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     scaler = StandardScaler().fit(X)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 通过定心和定标来实现标准化
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     rescaledX = scaler.transform(X)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 汇总转换后的数据
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     # 设置打印选项
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     numpy.set_printoptions(precision=3)
    
    
   
   

   
   
    
    
   
   
   
   
    
    
     
     print(rescaledX[0:5,:])