Question

我无法运行代码。我不断收到错误，我的x变量如'hsGPA'未定义。以下是我的代码。我已经尝试了在麻烦线程上发布的解决方案，没有人帮助过，所以请不要将此标记为重复。谢谢！

def readData(fileName):


    hsGPA = []   #High School GPA
    mathSAT = []  #Math SAT scores
    crSAT = []  #Verbal SAT scores
    collegeGPA = []  #College GPA
    FullList=[] 
    inputFile = open(fileName, 'r', encoding = 'utf-8')

    for line in inputFile:
        FullList=line.split(',')
        hsGPA.append(float(FullList[0]))
        mathSAT.append(int(FullList[1]))
        crSAT.append(int(FullList[2]))
        collegeGPA.append(float(FullList[3]))
    return hsGPA, mathSAT, crSAT, collegeGPA 



def plotData(hsGPA, mathSAT, crSAT, collegeGPA):

    GPA1 = []   #High School GPA
    Score1 = []  #Math SAT scores
    Score2= []  #Verbal SAT scores
    GPA2 = []  #College GPA

    hsGPA, mathGPA, crSAT, collegeGPA = readData('SAT.txt')
    pyplot.figure(1)

    pyplot.subplot(4,1,1)
    for line in range(len(hsGPA)):
        GPA1.append(line)
    pyplot.plot(GPA1,hsGPA)

    pyplot.subplot(4,1,2)
    for line in range(len(mathSAT)):
        Score1.append(line)
    pyplot.plot(Score1,mathSAT)

    pyplot.subplot(4,1,3)
    for line in range(len(crSAT)):
        Score2.append(line)       
    pyplot.plot(Score2,crSAT)

    pyplot.subplot(4,1,4)
    for line in range(len(collegeGPA)):
        GPA2.append(line)
    pyplot.plot(GPA2,collegeGPA)

    pyplot.show()

def LinearRegression(xList, yList):
    '''
    This function finds the constants in the y = mx+b, or linear regression
    forumula

    xList - a list of the x values
    yList - a list of the y values
    m - the slope f the line
    b - where the line intercepts the y axis
    '''

    n = len(xList)
    sumX = 0
    sumXX = 0
    sumXY = 0
    sumY = 0

    for index in range(n):
        sumX += xList[index]
        sumXY += xList[index] * yList[index]
        sumXX += xList[index]**2
        sumY += yList[index]
        #the components needed to find m and b

    m = (n*(sumXY - (sumX*sumY)))/(n*(sumXX - (sumX**2)))
    b = (sumY - (m*sumX))/n
    #actually implements formula

    return m, b


def plotRegression(x,y, xLabel, yLabel):
    ScoreT = []

    pyplot.scatter(x,y)
    m,b = linearRegression(xList,yList)
    minX = min(x)
    maxX = max(x)
    pyplot.plot([minX, maxX], [m * minX + b, m * maxX + b], color ='red')
    pyplot.xlabel(xLabel)
    pyplot.ylabel(yLabel)
    pyplot.show()

    for index in range(len(mathSAT)):
        sumscore = mathSAT[index] + crSAT[index]
        ScoreT.append(sumscore)
    return ScoreT


def rSquared(x,y,m,b):

    n = len(x)
    R=0
    sumS=0
    sumT=0
    sumY=0

    for index in range(n):
        a=(y[index]-((m*x[index])+b))**2
        sumS = sumS+a


    for index in range(len(y)):
        sumY = sumY= y[index]
        MeanY= sumY/(len(y))
        e=(y[index]-MeanY)**2
        sumT = sumT+e




    m,b= LinearRegression(xList, yList)

    RG=1-(sumS/sumT)





def main():
    print(readData('SAT.txt'))
    plotData(*readData('SAT.txt'))
    plotRegression(hsGPA,collegeGPA, 'highGPA', 'collegeGPA')
    plotRegression(mathSAT,collegeGPA, 'highGPA' , 'collegeGPA')
    plotRegression(crSAT,collegeGPA, 'highGPA' , 'collegeGPA')
    plotRegression(ScoreT,collegeGPA, 'highGPA' , 'collegeGPA')



main()

在每个x变量的plotRegression之后，它给出了main中的错误。请帮忙！谢谢！

Answer 1

试试这个：

def plotRegression(x,y, xLabel, yLabel):
    # I deleted ScoreT = [] here
    pyplot.scatter(x,y)
    m,b = linearRegression(x,y)
    minX = min(x)
    maxX = max(x)
    pyplot.plot([minX, maxX], [m * minX + b, m * maxX + b], color ='red')
    pyplot.xlabel(xLabel)
    pyplot.ylabel(yLabel)
    pyplot.show()
    # I deleted the loop and return statement here

# ....

def main():
    data = readData('SAT.txt')
    print(data)
    plotData(*data)
    hsGPA, mathSAT, crSAT, collegeGPA = data
    # added ScoreT calculation here
    ScoreT = [sum(x) for x in zip(mathSAT, crSAT)]
    plotRegression(hsGPA,collegeGPA, 'highGPA', 'collegeGPA')
    plotRegression(mathSAT,collegeGPA, 'highGPA' , 'collegeGPA')
    plotRegression(crSAT,collegeGPA, 'highGPA' , 'collegeGPA')
    plotRegression(ScoreT,collegeGPA, 'highGPA' , 'collegeGPA')

Answer 2

在您的main()中，永远不会定义hsGPA。它在其他函数中定义，不在全局上下文中共享。所以主要无法访问它。

你需要从readData()返回

Python-名称未定义

2 个答案: