NumPy 数据归一化、可视化-轻识

仅使用 NumPy，下载数据，归一化，使用 seaborn 展示数据分布。

下载数据

import numpy as np

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
wid = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[1])

仅提取 iris 数据集的第二列 usecols = [1]

展示数据

array([3.5, 3. , 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3. ,
       3. , 4. , 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3. ,
       3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.1, 3. ,
       3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3. , 3.8, 3.2, 3.7, 3.3, 3.2, 3.2,
       3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2. , 3. , 2.2, 2.9, 2.9,
       3.1, 3. , 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3. , 2.8, 3. ,
       2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3. , 3.4, 3.1, 2.3, 3. , 2.5, 2.6,
       3. , 2.6, 2.3, 2.7, 3. , 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3. , 2.9,
       3. , 3. , 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3. , 2.5, 2.8, 3.2, 3. ,
       3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3. , 2.8, 3. ,
       2.8, 3.8, 2.8, 2.8, 2.6, 3. , 3.4, 3.1, 3. , 3.1, 3.1, 3.1, 2.7,
       3.2, 3.3, 3. , 2.5, 3. , 3.4, 3. ])

这是单变量(univariate)长度为 150 的一维 NumPy 数组。

归一化

求出最大值、最小值

smax = np.max(wid)
smin = np.min(wid)

In [51]: smax,smin
Out[51]: (4.4, 2.0)

归一化公式：

s = (wid - smin) / (smax - smin)

只打印小数点后三位设置：

np.set_printoptions(precision=3)

归一化结果：

array([0.625, 0.417, 0.5  , 0.458, 0.667, 0.792, 0.583, 0.583, 0.375,
       0.458, 0.708, 0.583, 0.417, 0.417, 0.833, 1.   , 0.792, 0.625,
       0.75 , 0.75 , 0.583, 0.708, 0.667, 0.542, 0.583, 0.417, 0.583,
       0.625, 0.583, 0.5  , 0.458, 0.583, 0.875, 0.917, 0.458, 0.5  ,
       0.625, 0.458, 0.417, 0.583, 0.625, 0.125, 0.5  , 0.625, 0.75 ,
       0.417, 0.75 , 0.5  , 0.708, 0.542, 0.5  , 0.5  , 0.458, 0.125,
       0.333, 0.333, 0.542, 0.167, 0.375, 0.292, 0.   , 0.417, 0.083,
       0.375, 0.375, 0.458, 0.417, 0.292, 0.083, 0.208, 0.5  , 0.333,
       0.208, 0.333, 0.375, 0.417, 0.333, 0.417, 0.375, 0.25 , 0.167,
       0.167, 0.292, 0.292, 0.417, 0.583, 0.458, 0.125, 0.417, 0.208,
       0.25 , 0.417, 0.25 , 0.125, 0.292, 0.417, 0.375, 0.375, 0.208,
       0.333, 0.542, 0.292, 0.417, 0.375, 0.417, 0.417, 0.208, 0.375,
       0.208, 0.667, 0.5  , 0.292, 0.417, 0.208, 0.333, 0.5  , 0.417,
       0.75 , 0.25 , 0.083, 0.5  , 0.333, 0.333, 0.292, 0.542, 0.5  ,
       0.333, 0.417, 0.333, 0.417, 0.333, 0.75 , 0.333, 0.333, 0.25 ,
       0.417, 0.583, 0.458, 0.417, 0.458, 0.458, 0.458, 0.292, 0.5  ,
       0.542, 0.417, 0.208, 0.417, 0.583, 0.417])

分布可视化

import seaborn as sns
sns.distplot(s,kde=False,rug=True)

频率分布直方图：

sns.distplot(s,hist=True,kde=True,rug=True)

带高斯密度核函数的直方图：

分布 fit 图

拿 gamma 分布去 fit ：

from scipy import stats
sns.distplot(s, kde=False, fit = stats.gamma)

拿双 gamma 去 fit：

from scipy import stats
sns.distplot(s, kde=False, fit = stats.dgamma)