Python中不同图表的数据可视化的实现_python

# 导入 pandas 和 matplotlib
import pandas as pd
import matplotlib.pyplot as plt

# 创建上面给出的表的二维数组
data = [['E001', 'M', 34, 123, 'Normal', 350],
		['E002', 'F', 40, 114, 'Overweight', 450],
		['E003', 'F', 37, 135, 'Obesity', 169],
		['E004', 'M', 30, 139, 'Underweight', 189],
		['E005', 'F', 44, 117, 'Underweight', 183],
		['E006', 'M', 36, 121, 'Normal', 80],
		['E007', 'M', 32, 133, 'Obesity', 166],
		['E008', 'F', 26, 140, 'Normal', 120],
		['E009', 'M', 32, 133, 'Normal', 75],
		['E010', 'M', 36, 133, 'Underweight', 40] ]

# 使用上述数据数组创建的数据框
df = pd.DataFrame(data, columns = ['EMPID', 'Gender',
									'Age', 'Sales',
									'BMI', 'Income'] )

# 为数值数据创建直方图
df.hist()

# show plot
plt.show()

# 此处使用之前代码的数据框

# 绘制数值条形图，将显示所有 3 个年龄、收入、销售额之间的比较
df.plot.bar()

# 在 2 个属性之间绘制
plt.bar(df['Age'], df['Sales'])
plt.xlabel("Age")
plt.ylabel("Sales")
plt.show()

# 对于数据框的每个数字属性
df.plot.box()

# 单个属性箱线图
plt.boxplot(df['Income'])
plt.show()

plt.pie(df['Age'], labels = {"A", "B", "C",
							"D", "E", "F",
							"G", "H", "I", "J"},
							
autopct ='% 1.1f %%', shadow = True)
plt.show()

plt.pie(df['Income'], labels = {"A", "B", "C",
								"D", "E", "F",
								"G", "H", "I", "J"},
								
autopct ='% 1.1f %%', shadow = True)
plt.show()

plt.pie(df['Sales'], labels = {"A", "B", "C",
							"D", "E", "F",
							"G", "H", "I", "J"},
autopct ='% 1.1f %%', shadow = True)
plt.show()

# 收入和年龄之间的散点图
plt.scatter(df['income'], df['age'])
plt.show()

# 收入和销售额之间的散点图
plt.scatter(df['income'], df['sales'])
plt.show()

# 销售额和年龄之间的散点图
plt.scatter(df['sales'], df['age'])
plt.show()