# 导入numpy库, 命名为np import numpy as np import matplotlib.pyplt as plt import pandas as pd
#用panda来读取‘weight.txt’文件的数据, 函数read_table weight_data = pd.read_table(‘weight.txt’)
weight_data.shape()
#有一列数,80个 (80,1)
weight_data['weight']mean()
50.7
weight_data[weight].var()
weight 39.275949
weight_data[weight].median()
weight 50.0
*设置图标尺寸和DPI, 设置600 * 300 像素,每英寸100像素* fig = plt.figure(figsize = (6,3) ,dpi = 100)*
x = weight_data['weight']
# 将画布分割成1行1列,从左到右从上到下第1块 ax= fig.add_subplot(111)
#bins-直方个数,alpha-颜色的深浅度,rwidth-宽度,normed - 是否对数据标准化 ax.hist(x,bins = 15, color = 'red',alpha = 0.5,rwidth = 0.8,normed=False)
plt.grid(True) plt.title(u'weight') plt.show()
import numpy as np import pandas as pd import matplotlib.pyplot as plt from scipy import stats passengers_data = pd.read_csv('AirPassengers.csv') passengers_data.shape
(144,2)
passengers_data['NumPassengers'].mean()
280.2986111111111
passengers_data['NumPassengers'].var()
14391.917200854701
passengers_data['NumPassengers'].median()
265.5
fig = plt.figure(figsize = (6, 3), dpi = 100) x = passengers_data['NumPassengers'] ax = fig.add_subplot(111) ax.hist(x , bins = 50, color = 'red', alpha = 0.5, rwidth = 0.8, normed = False) plt.grid(True) plt.title('passenger') plt.show()
参考文档: 文档 matplotlib绘图总结; 文档 Python数据可视化分析 matplotlib教程; 文档PANDAS常用手册 I –读写文本数据 ; 文档 matplotlib.pyplot中add_subplot方法参数111的含义 ; 文档 Matplotlib使用教程; 书籍:《极简统计学》