pandas learning

matplotlib

设置中文显示

matlotlib默认不支持中文字符，默认英文字体无法显示汉字

查看inux/mac下面支持的字体：fc-list :lang=zh

# windows、linux、macos系统通用设置
# 导入font_manager => 实例化FontProperties对象my_font => 在设置字体的地方使用这个对象，比如xticks
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="/System/Lirary/Fonts/PingFang.ttc")
lt.xticks(range(2, 25, 1), fontproperties=my_font)

折线图

from matplotlib import pyplot as plt
from matplotlib import font_manager
# 实例化FontProperties
my_font = font_manager.FontProperties(fname="/System/Library/Fonts/PingFang.ttc")
kwargs = {
    "fontproperties": my_font
}
# x,y值，一一对应
x = range(2, 30, 3)
y1 = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22]
y2 = [14, 22, 19.6, 12, 23, 24, 28, 26, 22, 18]
# 设置图像尺寸和像素大小
plt.figure(figsize=(20, 8), dpi=90)
# 设置线条样式：颜色-color，风格-linestyle，粗细-linewidth，透明度-alpha
# linestyle样式有：- -- : -.
plt.plot(x, y1, label="小明", color="orange", linestyle=":", linewidth=5, alpha=0.5)
plt.plot(x, y2, label="小狗", color="cyan", linestyle="-.", linewidth=1, alpha=0.6)
# 设置轴刻度，刻度轴可以使等间距固定，用于标识x和y的数据范围
# 指定刻度轴x-label
x_ticks = range(2, 30, 2)
labels = [f"测试{i}" for i in x_ticks] 
# 参数：rotation-逆时针旋转角度
# 参数：fontproperties-字体属性设置
plt.xticks(x_ticks, labels, rotation=90, **kwargs)
plt.yticks(range(0, 30, 5), **kwargs)
# 设置描述信息：X轴描述、Y轴描述、标题描述
plt.xlabel("ID")    
plt.ylabel("AGE")
plt.title("这是一个测试标题", **kwargs)
# 绘制网格
# alpha-透明度，0~1：完全透明~不透明
plt.grid(alpha=0.4)
# 添加图例，这里需要注意，图例的信息转向的使plt.plot里面的label参数信息，且设置中文字体参数是prop
plt.legend(prop=my_font)
# 输出文件
plt.savefig("./output/demo.svg")
# 绘图显示
plt.show()

散点图

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname="/System/Library/Fonts/PingFang.ttc")
x_3 = range(1, 30)
x_10 = range(34, 63)
y_3 = [11, 17, 16, 11, 12, 11, 12, 6, 6, 7, 8, 9, 12, 15, 14, 17, 18, 21, 16, 17, 20, 14, 15, 15, 15, 19, 21, 22, 22]
y_10 = [26, 26, 28, 19, 21, 17, 16, 19, 18, 20, 20, 19, 22, 23, 17, 20, 21, 20, 22, 15, 11, 15, 11, 15, 5, 13, 17, 10, 11]
plt.figure(figsize=(20, 8), dpi=100)
# 使用scatter方法绘制散点图
plt.scatter(x_3, y_3, label="3月份")
plt.scatter(x_10, y_10, label="10月份")

_x = list(x_3) + list(x_10)
x_tick_labels = [f"3月{i}日" for i in x_3]
x_tick_labels += [f"10月{i - 40}日" for i in x_10]
plt.xticks(_x[::3], x_tick_labels[::3], fontproperties=my_font, rotation=60)
plt.legend(loc="upper left", prop=my_font)
plt.xlabel("时间", fontproperties=my_font)
plt.ylabel("温度", fontproperties=my_font)
plt.title("标题", fontproperties=my_font)
plt.show()

条形图

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname="/System/Library/Fonts/PingFang.ttc")

a = ["A", "B", "C", "D", "E"]
b = [56, 16, 87, 11, 66]
plt.figure(figsize=(16, 9), dpi=80)
# 条形图竖向
_x = list(range(len(a)))
plt.bar(_x, b, width=0.4)
plt.xticks(_x, [f"电影_{i}" for i in a], fontproperties=my_font, rotation=30)

# 条形图横向，横向条形图
_y = list(range(len(a)))
plt.barh(_y, b, height=0.4)
plt.yticks(_y, [f"电影_{i}" for i in a], fontproperties=my_font)

# 一张图画多个条形图
b1 = [56, 16, 87, 11, 66]
b2 = [33, 56, 66, 14, 46]
b3 = [22, 22, 77, 18, 56]
width = 0.2
# 连续加一个宽度，可以让同一个x的3个条形图挨在一起
x_1 = list(range(len(a)))
x_2 = [i + width for i in x_1]
x_3 = [i + width * 2 for i in x_1]
plt.bar(x_1, b1, width=width)
plt.bar(x_2, b2, width=width)
plt.bar(x_3, b3, width=width)
# x_2的位置正好在一个x的3个条形图正中间
plt.xticks(x_2, [f"电影_{i}" for i in a], fontproperties=my_font, rotation=5)
plt.show()

直方图

from matplotlib import pyplot as plt

a = [131, 98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124,
     101, 110, 116, 117, 110, 128, 128, 115, 99, 136, 126, 134, 95, 138, 117, 111, 78, 132, 124, 113, 150, 110, 117, 86,
     95, 144, 105, 126, 130, 126, 130, 126, 116, 123, 106, 112, 138, 123, 86, 101, 99, 136, 123, 117, 119, 105, 137,
     123, 128, 125, 104, 109, 134, 125, 127, 105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114, 105, 115,
     132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134, 156, 106, 117, 127, 144, 139, 139, 119, 140, 83, 110, 102,
     123, 107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133, 112, 114, 122, 109, 106, 123, 116, 131, 127,
     115, 118, 112, 135, 115, 146, 137, 116, 103, 144, 83, 123, 111, 110, 111, 100, 154, 136, 100, 118, 119, 133, 134,
     106, 129, 126, 110, 111, 109, 141, 120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126, 114, 140, 103,
     130, 141, 117, 106, 114, 121, 114, 133, 137, 92, 121, 112, 146, 97, 137, 105, 98, 117, 112, 81, 97, 139, 113, 134,
     106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110, 105, 129, 137, 112, 120, 113, 133, 112, 83, 94, 146,
     133, 101, 131, 116, 111, 84, 137, 115, 122, 106, 144, 109, 123, 116, 111, 111, 133, 150]
# 计算组数
d = 3  # 组数
num_bins = (max(a) - min(a)) // d
plt.hist(a, num_bins)
plt.xticks(range(min(a), max(a), d))
plt.show()

其它绘图库

plotly
seaborn

numpy

一个在Python中做科学计算的基础库，重在数值计算，也是大部分Python科学计算库的基础库，多用于在大型多维数组上执行数值运算

创建numpy数组

import numpy as np

# 几种基本的创建数组方式，使用dtype指定数值类型
arr1 = np.array([1, 2, 3, 4, 5])
arr2 = np.array(range(1, 6), dtype=np.float32)
arr3 = np.arange(1, 6, 0.5)
arr4 = np.array(["1", "2", "3"], dtype=np.string_)
# 数组数值类型获取
print(arr1.dtype)
# 数组数值类型转换，原数组类型不变，返回指定数值类型数组
arr1_1 = arr1.astype(np.int32)
arr1_2 = arr1.astype(arr3.dtype)
arr1_3 =  arr4.astype(np.int32)
print(arr1_1.dtype)
# 数组形状及改变形状
print(arr1.shape)
arr2_1 = arr2.reshape((2, 3))
# 展开成一维数组
arr2_2 = arr2.flatten()

广播原则：如果两个数组的后缘维度（trailing dimension，即从末尾开始算起的维度）的轴长度相符或其中一方的长度为1，则认为它们是广播兼容的。广播会在缺失和（或）长度为1的维度上进行。

# 数组计算
# 数组与数值计算，广播形式每一个元素都进行相同的运算
arr3_1 = arr3 + 1
arr3_2 = arr3 / 0  # 不报错，出现警告，除以0结果为inf
# 数组与数组计算，如果维度不一样，会以广播形式，小维度的扩展维度成大维度，某一维度一样时候才行

热门相关：仙城纪   寂静王冠   寂静王冠   第一神算：纨绔大小姐   时间都知道（唐嫣、窦骁、杨烁主演）