import numpy as np
import random
import matplotlib.pyplot as pyplot
from numpy import array
from numpy.random import normal
from collections import Counter
def genData():
heights = []
weights = []
grades = []
N = 10000
for i in range(N):
while True:
#身高服从均值172，标准差为6的正态分布
height = normal(172, 6)
if 0 < height: break
while True:
#体重由身高作为自变量的线性回归模型产生，误差服从标准正态分布
weight = (height - 80) * 0.7 + normal(0, 1)
if 0 < weight: break
while True:
#分数服从均值为70，标准差为15的正态分布
score = normal(70, 15)
if 0 <= score and score <= 100:
grade = 'E' if score < 60 else ('D' if score < 70 else ('C' if score < 80 else ('B' if score < 90 else 'A')))
break
heights.append(height)
weights.append(weight)
grades.append(grade)
return array(heights), array(weights), array(grades)
heights, weights, grades = genData()
#绘制柱状图
def drawBar(grades):
t = Counter(grades)
xticks = ['A', 'B', 'C', 'D', 'E']
gradeGroup = {}
for i in range(len(xticks)):
gradeGroup[xticks[i]] = t.get(xticks[i])
print(gradeGroup)
#创建柱状图
#第一个参数为柱的横坐标
#第二个参数为柱的高度
#参数align为柱的对齐方式，以第一个参数为参考标准
pyplot.bar(range(5), [gradeGroup.get(xtick) for xtick in xticks], align='center')
#设置柱的文字说明
#第一个参数为文字说明的横坐标
#第二个参数为文字说明的内容
pyplot.xticks(range(5), xticks)
pyplot.xlabel('Grade')
pyplot.ylabel('Frequency')
pyplot.title('Grades Of Male Students')
pyplot.show()
drawBar(grades)
# 绘制饼形图
def drawPie(grades):
labels = ['A', 'B', 'C', 'D', 'E']
t = Counter(grades)
xticks = ['A', 'B', 'C', 'D', 'E']
gradeGroup = {}
for i in range(len(xticks)):
gradeGroup[xticks[i]] = t.get(xticks[i])
# 创建饼形图
# 第一个参数为扇形的面积
# labels参数为扇形的说明文字
# autopct参数为扇形占比的显示格式
pyplot.pie([gradeGroup.get(label) for label in labels], labels=labels, autopct='%1.1f%%')
pyplot.title('Grades Of Male Students')
pyplot.show()
drawPie(grades)
#绘制直方图
def drawHist(heights):
#创建直方图
#第一个参数为待绘制的定量数据，不同于定性数据，这里并没有事先进行频数统计
#第二个参数为划分的区间个数
pyplot.hist(heights, 100)
pyplot.xlabel('Heights')
pyplot.ylabel('Frequency')
pyplot.title('Heights Of Male Students')
pyplot.show()
drawHist(heights)
#绘制累积曲线
def drawCumulativeHist(heights):
#创建累积曲线
#第一个参数为待绘制的定量数据
#第二个参数为划分的区间个数
#normed参数为是否无量纲化
#histtype参数为'step'，绘制阶梯状的曲线
#cumulative参数为是否累积
pyplot.hist(heights, 20, density=True, histtype='step', cumulative=True)
pyplot.xlabel('Heights')
pyplot.ylabel('Frequency')
pyplot.title('Heights Of Male Students')
pyplot.show()
drawCumulativeHist(heights)
#绘制散点图
def drawScatter(heights, weights):
#创建散点图
#第一个参数为点的横坐标
#第二个参数为点的纵坐标
pyplot.scatter(heights, weights)
pyplot.xlabel('Heights')
pyplot.ylabel('Weights')
pyplot.title('Heights & Weights Of Male Students')
pyplot.show()
drawScatter(heights, weights)
#绘制箱形图
def drawBox(heights):
#创建箱形图
#第一个参数为待绘制的定量数据
#第二个参数为数据的文字说明
pyplot.boxplot([heights], labels=['Heights'])
pyplot.title('Heights Of Male Students')
pyplot.show()
drawBox(heights)
