ValueError:比例<使用高斯分布函数归一化时为0 [英] ValueError: scale < 0 during normalization by using gaussian distribution function

问题描述

我正在尝试读取我的文本文件，并提取3个主要参数并将它们放在单独的列表中，并在分配高斯分布函数后对参数列表(温度，速度，加速度)应用归一化.为了获得良好的结果，我将每个参数列表的正负数分开，并应用高斯分布函数，并选择负数的平均值作为真实的最小值，并选择正数的平均值作为真实的最大值，而不是直接找到最小值和最大值这些参数的主列表中的值可能会重复几次，因为它们不在所需的置信区间内.问题是我遇到了已经避免的RunTimeWarning错误，但是仍然遇到以下错误，我不知道如何解决这些错误，其中包括 ValueError:scale< 0 ，希望有人对错误的解决方案有个好主意，并且可以通过使用高斯分布函数来更好地应用规范化方法.谢谢您的关注:

I'm trying to read my text file and extract 3 main parameters and put them in separate list and apply normalizing on lists of parameters which are (Temperature, Speed, Acceleration) after assigning Gaussian distribution function. For getting good result I split up positive and negative numbers of each parameters' list and apply gaussian distribution function and pick mean value of negative numbers as the real Minimum and pick mean value of positive numbers as the real Maximum instead of directly find Min and Max values in main list of these parameters which could repeat few times due to they're not in desired confidence interval. The problem is I faced RunTimeWarning error which I avoided already but still I have below error(s) which I don't have any clue how I can solve them includes ValueError: scale <0 , hope that someone has good idea about solution for errors ot better way to apply normalization by using gaussian distribution function Thanks for your attention:

File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd_launcher.py", line 45, in <module>
main(ptvsdArgs)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\__main__.py", line 265, in main
wait=args.wait)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\__main__.py", line 258, in handle_args
debug_main(addr, name, kind, *extra, **kwargs)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_local.py", line 45, in debug_main
run_file(address, name, *extra, **kwargs)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_local.py", line 79, in run_file
run(argv, addr, **kwargs)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_local.py", line 140, in _run
_pydevd.main()
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\pydevd.py", line 1925, in main
debugger.connect(host, port)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\pydevd.py", line 1283, in run
return self._exec(is_module, entry_point_fn, module_name, file, globals, locals)
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\pydevd.py", line 1290, in _exec
pydev_imports.execfile(file, globals, locals)  # execute the script
File "c:\Users\majm\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\_pydev_imps\_pydev_execfile.py", line 25, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "p:\Desktop\correctt\news.py", line 142, in <module>
plotgaussianfunction(t_p_mean, t_sigma_Positive)
File "p:\Desktop\correctt\news.py", line 58, in plotgaussianfunction
s = np.random.normal(mu, sigma,1000)
File "mtrand.pyx", line 1656, in mtrand.RandomState.normal
ValueError: scale < 0

所以我的代码是:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import scipy
import warnings
warnings.filterwarnings("ignore",category =RuntimeWarning)

df = pd.read_csv('D:/me.txt', header=None)
id_set = df[df.index % 4 == 0].astype('int').values
speed = df[df.index % 4 == 1].values
acceleration = df[df.index % 4 == 2].values
temperature = df[df.index % 4 == 3].values

m_data={'p_Speed': s_p_results[:,0],'n_Speed': s_n_results[:,0], 'p_Acceleration': a_p_results[:,0],'n_Acceleration': a_n_results[:,0], 'p_Temperature': t_p_results[:,0],'n_Temperature': t_n_results[:,0]}
m_main_data = pd.DataFrame(data, columns=['Speed','Acceleration','Temperature'], index = id_set[:,0])

data = {'Speed': speed[:,0], 'Acceleration': acceleration[:,0], 'Temperature': temperature[:,0]}
main_data = pd.DataFrame(data, columns=['Speed','Acceleration','Temperature'], index = id_set[:,0])
main_data = main_data.replace([np.inf, -np.inf], np.nan)

def normalize(value, min_value, max_value, min_norm, max_norm):
new_value = ((max_norm - min_norm)*((value - min_value)/(max_value - min_value))) + min_norm
return new_value

def createpositiveandnegativelist(listtocreate):
l_negative = []
l_positive = []
for value in listtocreate:
    if (value < 0):
        l_negative.append(value)
    elif (value > 0):
        l_positive.append(value)
#print(t_negative)
#print(t_positive)
return l_negative,l_positive

def calculatemean(listtocalculate):
return sum(listtocalculate)/len(listtocalculate)

def plotgaussianfunction(mu,sigma):
s = np.random.normal(mu, sigma,1000)
abs(mu - np.mean(s))<0.01
abs(sigma - np.std(s,ddof=1))<0.01
#count, bins, ignored = plt.hist(s,30,density=True)
#plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins-mu)**2/(2*sigma**2)),linewidth=2, color= 'r')
#plt.show()
return


def plotboundedCI(s, mu, sigma, lists):
plt.figure()

count, bins, ignored = plt.hist(s,30,density=True)
plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins-mu)**2/(2*sigma**2)),linewidth=2, color= 'r')
#confidential interval calculation
ci = scipy.stats.norm.interval(0.68, loc = mu, scale = sigma)
#confidence interval for left line
one_x12, one_y12 = [ci[0],ci[0]], [0,3]
#confidence interval for right line
two_x12, two_y12 = [ci[1],ci[1]], [0,3]

plt.title("Gaussian 68% Confidence Interval", fontsize=12, color='black', loc='left', style='italic')
plt.plot(one_x12, one_y12, two_x12, two_y12, marker = 'o')
plt.show()


results = []
for value in lists:
    if(ci[0]< value <ci[1]):
        results.append(value)
    else:
        #print("NOT WANTED: ",value)
        pass

return results


t_negative, t_positive = createpositiveandnegativelist(temperature)
a_negative, a_positive = createpositiveandnegativelist(acceleration)
s_negative, s_positive = createpositiveandnegativelist(speed)

#calculating the mean value
t_p_mean = calculatemean(t_positive)
a_p_mean = calculatemean(a_positive)
s_p_mean = calculatemean(s_positive)
t_n_mean = calculatemean(t_negative)
a_n_mean = calculatemean(a_negative)
s_n_mean = calculatemean(s_negative)

#calculating the sigma value
t_sigma_Negative = np.std(t_negative)
t_sigma_Positive = np.std(t_positive)
a_sigma_Negative = np.std(t_negative)
a_sigma_Positive = np.std(t_positive)
s_sigma_Negative = np.std(t_negative)
s_sigma_Positive = np.std(t_positive)

#plot the gaussian function with histograms
plotgaussianfunction(t_p_mean, t_sigma_Positive)
plotgaussianfunction(t_n_mean, t_sigma_Negative)
plotgaussianfunction(a_p_mean, a_sigma_Positive)
plotgaussianfunction(a_n_mean, a_sigma_Negative)
plotgaussianfunction(s_p_mean, s_sigma_Positive)
plotgaussianfunction(s_n_mean, s_sigma_Negative)

#normalization
t_p_s = np.random.normal(t_p_mean, t_sigma_Positive,1000)
t_n_s = np.random.normal(t_n_mean, t_sigma_Negative,1000)
a_p_s = np.random.normal(a_p_mean, a_sigma_Positive,1000)
a_n_s = np.random.normal(a_n_mean, a_sigma_Negative,1000)
s_p_s = np.random.normal(s_p_mean, s_sigma_Positive,1000)
s_n_s = np.random.normal(s_n_mean, s_sigma_Negative,1000)

#histograms minus the outliers
t_p_results = plotboundedCI(t_p_s, t_p_mean, t_sigma_Positive, t_positive)
t_n_results = plotboundedCI(t_n_s, t_n_mean, t_sigma_Negative, t_negative)
a_p_results = plotboundedCI(a_p_s, a_p_mean, a_sigma_Positive, a_positive)
a_n_results = plotboundedCI(a_n_s, a_n_mean, a_sigma_Negative, a_negative)
s_p_results = plotboundedCI(s_p_s, s_p_mean, s_sigma_Positive, s_positive)
s_n_results = plotboundedCI(s_n_s, s_n_mean, s_sigma_Negative, s_negative)

注意:我的值列表中有一些缺少数据(nan或inf)，这些数据已被零替换！但是考虑到当我的参数列表中没有缺失值时，代码可以正常工作！

Note: I have some missing data(nan or inf) in my list of values which are already replaced by zero! but considering that when I have no missing values in my list of parameters , the code works!

推荐答案

来自numpy.random.normal文档:

from documentation of numpy.random.normal:

参数:

loc :浮点数或类似floats的数组

loc : float or array_like of floats

平均值(中心").

scale :浮点数或浮点数的array_like 分布的标准偏差(展开或宽度").

scale : float or array_like of floats Standard deviation (spread or "width") of the distribution.

大小:整数或整数元组，可选 输出形状.如果给定的形状是例如(m，n，k)，则绘制m * n * k个样本.如果size为None(默认值)，并且loc和scale均为标量，则返回单个值.否则，将绘制np.broadcast(loc，scale).size样本.

size : int or tuple of ints, optional Output shape. If the given shape is, e.g., (m, n, k), then m * n * k samples are drawn. If size is None (default), a single value is returned if loc and scale are both scalars. Otherwise, np.broadcast(loc, scale).size samples are drawn.

小数位数是分布的标准偏差，因此不能为负.因此，您得到的错误是:ValueError: scale < 0

the scale is the Standard deviation of the distribution hence it can not be negative. Hence the error you get: ValueError: scale < 0

您可能要检查此参数的符号.尝试一下:

you may want to check the sign of this parameter. give it a try with:

s = np.random.normal(mu, np.abs(sigma),1000)

这篇关于ValueError:比例&lt;使用高斯分布函数归一化时为0的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！