matplotlib模块
matplotlib模块
一、导入方式
import matplotlib.pyplot as plt # 默认支持英文,不支持中文
二、作用
可视化分析
三、方法
中文转英文的方法
from matplotlib.font_manager import FontProperties
font = FontProperties(fname='中文字体所在的路径')
3.1 条形图
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')
# 修改背景为条纹
plt.style.use('ggplot')
classes = ['3班', '4班', '5班', '6班']
classes_index = range(len(classes))
print(list(classes_index))
student_amounts = [66, 55, 45, 70]
# 画布设置
fig = plt.figure()
# 1,1,1表示一张画布切割成1行1列共一张图的第1个;2,2,1表示一张画布切割成2行2列共4张图的第一个(左上角)
ax1 = fig.add_subplot(1, 1, 1)
ax1.bar(classes_index, student_amounts, align='center', color='darkblue')
ax1.xaxis.set_ticks_position('bottom')
ax1.yaxis.set_ticks_position('left')
plt.xticks(classes_index,
classes,
rotation=0,
fontsize=13,
fontproperties=font)
plt.xlabel('班级', fontproperties=font, fontsize=15)
plt.ylabel('学生人数', fontproperties=font, fontsize=15)
plt.title('班级-学生人数', fontproperties=font, fontsize=20)
# 保存图片,bbox_inches='tight'去掉图形四周的空白
# plt.savefig('classes_students.png?x-oss-process=style/watermark', dpi=400, bbox_inches='tight')
plt.show()
3.2 直方图
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')
# 修改背景为条纹
plt.style.use('ggplot')
mu1, mu2, sigma = 50, 100, 10
# 构造均值为50的符合正态分布的数据
x1 = mu1 + sigma * np.random.randn(10000)
print(x1)
# 构造均值为100的符合正态分布的数据
x2 = mu2 + sigma * np.random.randn(10000)
print(x2)
fig = plt.figure()
ax1 = fig.add_subplot(121)
# bins=50表示每个变量的值分成50份,即会有50根柱子
ax1.hist(x1, bins=50, color='darkgreen')
ax2 = fig.add_subplot(122)
ax2.hist(x2, bins=50, color='orange')
fig.suptitle('两个正态分布', fontproperties=font, fontweight='bold', fontsize=15)
ax1.set_title('绿色的正态分布', fontproperties=font)
ax2.set_title('橙色的正态分布', fontproperties=font)
plt.show()
3.3 折线图
import numpy as np
from numpy.random import randn
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')
# 修改背景为条纹
plt.style.use('ggplot')
np.random.seed(1)
# 使用numpy的累加和,保证数据取值范围不会在(0,1)内波动
plot_data1 = randn(40).cumsum()
print(plot_data1)
plot_data2 = randn(40).cumsum()
plot_data3 = randn(40).cumsum()
plot_data4 = randn(40).cumsum()
plt.plot(plot_data1, marker='o', color='red', linestyle='-', label='红实线')
plt.plot(plot_data2, marker='x', color='orange', linestyle='--', label='橙虚线')
plt.plot(plot_data3, marker='*', color='yellow', linestyle='-.', label='黄点线')
plt.plot(plot_data4, marker='s', color='green', linestyle=':', label='绿点图')
# loc='best'给label自动选择最好的位置
plt.legend(loc='best', prop=font)
plt.show()
3.4 散点图+直线图
import numpy as np
from numpy.random import randn
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')
# 修改背景为条纹
plt.style.use('ggplot')
x = np.arange(1, 20, 1)
print(x)
# 拟合一条水平散点线
np.random.seed(1)
y_linear = x + 10 * np.random.randn(19)
print(y_linear)
# 拟合一条x²的散点线
y_quad = x**2 + 10 * np.random.randn(19)
print(y_quad)
# s是散点大小
fig = plt.figure()
ax1 = fig.add_subplot(121)
plt.scatter(x, y_linear, s=30, color='r', label='蓝点')
plt.scatter(x, y_quad, s=100, color='b', label='红点')
ax2 = fig.add_subplot(122)
plt.plot(x, y_linear, color='r')
plt.plot(x, y_quad, color='b')
# 限制x轴和y轴的范围取值
plt.xlim(min(x) - 1, max(x) + 1)
plt.ylim(min(y_quad) - 10, max(y_quad) + 10)
fig.suptitle('散点图+直线图', fontproperties=font, fontsize=20)
ax1.set_title('散点图', fontproperties=font)
ax1.legend(prop=font)
ax2.set_title('直线图', fontproperties=font)
plt.show()
3.5 饼图
import numpy as np
import matplotlib.pyplot as plt
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei']
fig, ax = plt.subplots(subplot_kw=dict(aspect="equal"))
recipe = ['优', '良', '轻度污染', '中度污染', '重度污染', '严重污染', '缺']
data = [2, 49, 21, 9, 11, 6, 2]
colors = ['lime', 'yellow', 'darkorange', 'red', 'purple', 'maroon', 'grey']
wedges, texts, texts2 = ax.pie(data,
wedgeprops=dict(width=0.5),
startangle=40,
colors=colors,
autopct='%1.0f%%',
pctdistance=0.8)
plt.setp(texts2, size=14, weight="bold")
bbox_props = dict(boxstyle="square,pad=0.3", fc="w", ec="k", lw=0.72)
kw = dict(xycoords='data',
textcoords='data',
arrowprops=dict(arrowstyle="->"),
bbox=None,
zorder=0,
va="center")
for i, p in enumerate(wedges):
ang = (p.theta2 - p.theta1) / 2. + p.theta1
y = np.sin(np.deg2rad(ang))
x = np.cos(np.deg2rad(ang))
horizontalalignment = {-1: "right", 1: "left"}[int(np.sign(x))]
connectionstyle = "angle,angleA=0,angleB={}".format(ang)
kw["arrowprops"].update({"connectionstyle": connectionstyle})
ax.annotate(recipe[i],
xy=(x, y),
xytext=(1.25 * np.sign(x), 1.3 * y),
size=16,
horizontalalignment=horizontalalignment,
fontproperties=font,
**kw)
ax.set_title("饼图示例",fontproperties=font)
plt.show()
# plt.savefig('jiaopie2.png?x-oss-process=style/watermark')
3.6 箱型图
import numpy as np
import pandas as pd
from numpy.random import randn
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')
df = pd.DataFrame(np.random.rand(10, 5), columns=['A', 'B', 'C', 'D', 'E'])
plt.figure(figsize=(10, 4))
# 创建图表、数据
f = df.boxplot(
sym='o', # 异常点形状,参考marker
vert=True, # 是否垂直
whis=1.5, # IQR,默认1.5,也可以设置区间比如[5,95],代表强制上下边缘为数据95%和5%位置
patch_artist=True, # 上下四分位框内是否填充,True为填充
meanline=False,
showmeans=True, # 是否有均值线及其形状
showbox=True, # 是否显示箱线
showcaps=True, # 是否显示边缘线
showfliers=True, # 是否显示异常值
notch=False, # 中间箱体是否缺口
return_type='dict' # 返回类型为字典
)
plt.title('boxplot')
for box in f['boxes']:
box.set(color='b', linewidth=1) # 箱体边框颜色
box.set(facecolor='b', alpha=0.5) # 箱体内部填充颜色
for whisker in f['whiskers']:
whisker.set(color='k', linewidth=0.5, linestyle='-')
for cap in f['caps']:
cap.set(color='gray', linewidth=2)
for median in f['medians']:
median.set(color='DarkBlue', linewidth=2)
for flier in f['fliers']:
flier.set(marker='o', color='y', alpha=0.5)
# boxes, 箱线
# medians, 中位值的横线,
# whiskers, 从box到error bar之间的竖线.
# fliers, 异常值
# caps, error bar横线
# means, 均值的横线
四、图像标注参数
设置图像标题 | plt.title() |
---|---|
设置x轴名称 | plt.xlabel() |
设置y轴名称 | plt.ylabel() |
设置X轴范围 | plt.xlim() |
设置Y轴范围 | plt.ylim() |
设置X轴刻度 | plt.xticks() |
设置Y轴刻度 | plt.yticks() |
设置曲线图例 | plt.legend() |