使用Tu开发Python中的散点图

Question

我正在学习“如何像一个计算机科学家一样思考”课程，并被困在这个问题上：

解释数据文件标签数据.txt使每一行包含一个x，y坐标对。编写一个名为plotRegression的函数，该函数从该文件中读取数据，并根据以下公式使用海龟绘制这些点和最佳拟合线：

y=y‘+m（x−x’

m=∑西仪−nx´y∑x2i−nx´2

您的程序应该分析这些点，并使用setworld坐标正确缩放窗口，以便可以绘制每个点。然后你应该用不同的颜色画出最合适的线，穿过这些点。在

这是到目前为止我得到的，但是我一直得到一个'int'不支持索引错误。我已经在这里使用了各种在线资源和一些解决方案，但似乎无法正常工作。在

谁能帮我弄清楚该怎么改吗？在

import turtle


def plotRegression(data):
    win = turtle.Screen()
    win.bgcolor('pink')

    t = turtle.Turtle()
    t.shape('circle')
    # t.turtlesize(0.2)

    x_list, y_list = [int(i[0]) for i in plot_data], [int(i[1]) for i in plot_data]
    x_list, y_list = [float(i) for i in x_list], [float(i) for i in y_list]
    x_sum, y_sum = sum(x_list), sum(y_list)
    x_bar, y_bar = x_sum / len(x_list), y_sum / len(y_list)
    x_list_square = [i ** 2 for i in x_list]
    x_list_square_sum = sum(x_list_square)
    xy_list = [x_list[i] * y_list[i] for i in range(len(x_list))]
    xy_list_sum = sum(xy_list)

    m = (xy_list_sum - len(x_list) * x_bar * y_bar) / (x_list_square_sum - len(x_list) * x_bar ** 2)
    # best y
    y_best = [(y_bar + m * (x_list[i] - x_bar)) for i in range(len(x_list))]

    # plot points

    max_x = max(x_list)
    max_y = max(y_list)
    win.setworldcoordinates(0, 0, max_x, max_y)
    for i in range(len(x_list)):
        t.penup()
        t.setposition(x_list[i], y_list[i])
        t.stamp()

    # plot best y
    t.penup()
    t.setposition(0, 0)
    t.color('blue')
    for i in range(len(x_list)):
        t.setposition(x_list[i], y_best[i])
        t.pendown()

    win.exitonclick()


f = open("labdata.txt", "r")
for aline in f:
    plot_data = map(int, aline.split())
plotRegression(plot_data)

Answer 1

我认为你的海龟图形是第二个问题，你没有正确地读入你的数据。你把最后一对x，y都扔了。而且map()不是您的朋友，因为您需要在plotRegression()中索引结果。另外，您还直接在函数中访问plot_data，而不是形式参数data和其他细节。在

下面是我对你的代码的修改，看看它是否能让你朝着更好的方向前进：

from turtle import Turtle, Screen

def plotRegression(data):

    x_list, y_list = [int(i[0]) for i in data], [int(i[1]) for i in data]
    x_list, y_list = [float(i) for i in x_list], [float(i) for i in y_list]
    x_sum, y_sum = sum(x_list), sum(y_list)
    x_bar, y_bar = x_sum / len(x_list), y_sum / len(y_list)
    x_list_square = [i ** 2 for i in x_list]
    x_list_square_sum = sum(x_list_square)
    xy_list = [x_list[i] * y_list[i] for i in range(len(x_list))]
    xy_list_sum = sum(xy_list)

    m = (xy_list_sum - len(x_list) * x_bar * y_bar) / (x_list_square_sum - len(x_list) * x_bar ** 2)
    # best y
    y_best = [(y_bar + m * (x_list[i] - x_bar)) for i in range(len(x_list))]

    # plot points

    turtle = Turtle(shape = 'circle')

    for i in range(len(x_list)):
        turtle.penup()
        turtle.setposition(x_list[i], y_list[i])
        turtle.stamp()

    # plot best y
    turtle.penup()
    turtle.setposition(0, 0)
    turtle.color('blue')
    for i in range(len(x_list)):
        turtle.setposition(x_list[i], y_best[i])
        turtle.pendown()

    return (min(x_list), min(y_list), max(x_list), max(y_list))

screen = Screen()

screen.bgcolor('pink')

f = open("labdata.txt", "r")

plot_data = []

for aline in f:
    x, y = aline.split()
    plot_data.append((x, y))

# This next line should be something like:

# screen.setworldcoordinates(*plotRegression(plot_data))

# but setworldcoordinates() is so tricky to work with
# that I'm going to leave it at:

print(*plotRegression(plot_data))

# and suggest you trace a rectangle with the return
# values to get an idea what's going to happen to
# your coordinate system

screen.exitonclick()