使用python删除曲线下方的数据点

Both the theoretical curves and the data points are arrays of
different length.

我会做以下事情：

>截断数据集,使其x值位于理论集的最大值和最小值之内.
>使用scipy.interpolate.interp1d和上面截断的数据x值插值理论曲线.步骤(1)的原因是满足interp1d的约束.
>使用numpy.where查找超出可接受理论值范围的数据y值.
>不要像评论和其他答案中所建议的那样丢弃这些价值观.如果你想要清晰,可以通过绘制’内衬’一种颜色和’异常值’另一种颜色来指出它们.

我认为这是一个接近你所寻找的脚本.它有望帮助您实现您想要的目标：

import numpy as np
import scipy.interpolate as interpolate
import matplotlib.pyplot as plt

# make up data
def makeUpData():
    '''Make many more data points (x,y,yerr) than theory (x,y),with theory yerr corresponding to a constant "sigma" in y,about x,y value'''
    NX= 150
    dataX = (np.random.rand(NX)*1.1)**2
    dataY = (1.5*dataX+np.random.rand(NX)**2)*dataX
    dataErr = np.random.rand(NX)*dataX*1.3
    theoryX = np.arange(0,1,0.1)
    theoryY = theoryX*theoryX*1.5
    theoryErr = 0.5
    return dataX,dataY,dataErr,theoryX,theoryY,theoryErr

def makeSameXrange(theoryX,dataX,dataY):
    '''
    Truncate the dataX and dataY ranges so that dataX min and max are with in
    the max and min of theoryX.
    '''
    minT,maxT = theoryX.min(),theoryX.max()
    goodIdxMax = np.where(dataX<maxT)
    goodIdxMin = np.where(dataX[goodIdxMax]>minT)
    return (dataX[goodIdxMax])[goodIdxMin],(dataY[goodIdxMax])[goodIdxMin]

# take 'theory' and get values at every 'data' x point
def theoryYatDataX(theoryX,dataX):
    '''For every dataX point,find interpolated thoeryY value. theoryx needed
    for interpolation.'''
    f = interpolate.interp1d(theoryX,theoryY)
    return f(dataX[np.where(dataX<np.max(theoryX))])

# collect valid points
def findInlierSet(dataX,interpTheoryY,thoeryErr):
    '''Find where theoryY-theoryErr < dataY theoryY+theoryErr and return
    valid indicies.'''
    withinUpper = np.where(dataY<(interpTheoryY+theoryErr))
    withinLower = np.where(dataY[withinUpper]
                    >(interpTheoryY[withinUpper]-theoryErr))
    return (dataX[withinUpper])[withinLower],(dataY[withinUpper])[withinLower]

def findOutlierSet(dataX,thoeryErr):
    '''Find where theoryY-theoryErr < dataY theoryY+theoryErr and return
    valid indicies.'''
    withinUpper = np.where(dataY>(interpTheoryY+theoryErr))
    withinLower = np.where(dataY<(interpTheoryY-theoryErr))
    return (dataX[withinUpper],dataY[withinUpper],dataX[withinLower],dataY[withinLower])
if __name__ == "__main__":

    dataX,theoryErr = makeUpData()

    TruncDataX,TruncDataY = makeSameXrange(theoryX,dataY)

    interpTheoryY = theoryYatDataX(theoryX,TruncDataX)

    inDataX,inDataY = findInlierSet(TruncDataX,TruncDataY,theoryErr)

    outUpX,outUpY,outDownX,outDownY = findOutlierSet(TruncDataX,theoryErr)
    #print inlierIndex
    fig = plt.figure()
    ax = fig.add_subplot(211)

    ax.errorbar(dataX,fmt='.',color='k')
    ax.plot(theoryX,'r-')
    ax.plot(theoryX,theoryY+theoryErr,'r--')
    ax.plot(theoryX,theoryY-theoryErr,'r--')
    ax.set_xlim(0,1.4)
    ax.set_ylim(-.5,3)
    ax = fig.add_subplot(212)

    ax.plot(inDataX,inDataY,'ko')
    ax.plot(outUpX,'bo')
    ax.plot(outDownX,outDownY,'ro')
    ax.plot(theoryX,3)
    fig.savefig('findInliers.png')

这个数字是结果：