关系（一）利用python绘制散点图

import seaborn as sns
import matplotlib.pyplot as plt

# 导入数据
df = sns.load_dataset('iris')

# 基于scatterplot函数绘制散点图
sns.scatterplot(x=df["sepal_length"], y=df["sepal_width"])

plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

# 导入数据
df = sns.load_dataset('iris')

# 基于plot函数绘制散点图
plt.plot( 'sepal_length', 'sepal_width', data=df, linestyle='none', marker='o')

plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

sns.set(font='SimHei', font_scale=0.8, style="darkgrid") # 解决Seaborn中文显示问题

# 导入数据
df = sns.load_dataset("iris")

# 构造子图
fig, ax = plt.subplots(2,2,constrained_layout=True, figsize=(8, 8))

# 增加趋势拟合线
ax_sub = sns.regplot(x=df["sepal_length"], y=df["sepal_width"], fit_reg=True,
                         line_kws={"color":"r","alpha":0.7,"lw":5},ax=ax[0][0])
ax_sub.set_title('增加趋势拟合线')

# 自定义标记类型
ax_sub = sns.regplot(x=df["sepal_length"], y=df["sepal_width"], marker="+", fit_reg=False, ax=ax[0][1])
ax_sub.set_title('自定义标记类型')

# 自定义标记外形
ax_sub = sns.regplot(x=df["sepal_length"], y=df["sepal_width"], fit_reg=False, 
                        scatter_kws={"color":"darkred", # 颜色
                                  "alpha":0.3, # 透明度
                                  "s":200}, # 点大小
                        ax=ax[1][0]
                    )
ax_sub.set_title('自定义标记外形')

# 自定义每个点颜色
value=(df['sepal_length']>6) & (df['sepal_width']>3) # 构造特殊的点
df['color']= np.where( value==True , "#9b59b6", "#3498db") # 颜色区分

ax_sub = sns.regplot(data=df, x=df["sepal_length"], y=df["sepal_width"], fit_reg=False,
                scatter_kws={'facecolors':df['color']},ax=ax[1][1])
ax_sub.set_title('自定义每个点颜色')

plt.show()

import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.gridspec as gridspec

# 导入自定义模块
import SeabornFig2Grid as sfg

sns.set(font='SimHei', font_scale=0.8, style="darkgrid") # 解决Seaborn中文显示问题

# 导入数据
df = sns.load_dataset('iris')

fig = plt.figure(figsize=(8, 8))
gs = gridspec.GridSpec(2, 2)

# 默认的分组散点图
scatter1 =sns.lmplot( x="sepal_length", y="sepal_width", data=df, fit_reg=False, hue='species', legend=False)
scatter1.ax.set_title('默认的分组散点图')

# 自定义每组的标记
scatter2 = sns.lmplot( x="sepal_length", y="sepal_width", data=df, fit_reg=False, hue='species', legend=False, markers=["o", "x", "1"])
scatter2.ax.set_title('自定义每组的标记')

# 自定义调色板
scatter3 = sns.lmplot( x="sepal_length", y="sepal_width", data=df, fit_reg=False, hue='species', legend=False, palette="Set2")
scatter3.ax.set_title('自定义调色板')

# 自定义颜色
scatter4 = sns.lmplot( x="sepal_length", y="sepal_width", data=df, fit_reg=False, hue='species', legend=False, palette=dict(setosa="#9b59b6", virginica="#3498db", versicolor="#95a5a6"))
scatter4.ax.set_title('自定义颜色')

# 使用SeabornFig2Grid转换 seaborn 图为 matplotlib 子图
mg1 = sfg.SeabornFig2Grid(scatter1, fig, gs[0])
mg2 = sfg.SeabornFig2Grid(scatter2, fig, gs[1])
mg3 = sfg.SeabornFig2Grid(scatter3, fig, gs[2])
mg4 = sfg.SeabornFig2Grid(scatter4, fig, gs[3])

gs.tight_layout(fig)
plt.show()

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import seaborn as sns

# 自定义数据
df = pd.DataFrame({
'x': [1, 1.5, 3, 4, 5],
'y': [5, 15, 5, 10, 2],
'group': ['A','other group','B','C','D']
})

# 绘制基本散点图
sns.regplot(data=df, x="x", y="y", fit_reg=False, marker="o", color="skyblue", scatter_kws={'s':400})

# 为每个点添加注释
for line in range(0,df.shape[0]):
     plt.text(df.x[line]+0.2, df.y[line], df.group[line], horizontalalignment='left', size='medium', color='black', weight='semibold')

plt.show()

import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import numpy as np 
import pandas as pd
import palmerpenguins

mpl.rcParams.update(mpl.rcParamsDefault) # 恢复默认的matplotlib样式
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签

# 设置随机种子
np.random.seed(0)

# 自定义数据
df=pd.DataFrame({'x_pos': range(1,101), 'y_pos': np.random.randn(100)*80+range(1,101) })

# 初始化
fig = plt.figure(figsize=(12,8))

# 1、自定义标记
ax = plt.subplot2grid((2, 2), (0, 0), colspan=1)
plt.plot( 'x_pos', 'y_pos', data=df, linestyle='none', marker='*', # 标记形状
                markersize=12, # 标记大小
                markerfacecolor='skyblue', # 标记颜色
                markeredgewidth=0.3, # 标记边缘
                markeredgecolor="orange", # 标记边缘颜色
                 )
ax.set_title('自定义标记')


# 2、添加注释信息
ax = plt.subplot2grid((2, 2), (0, 1), colspan=1)
plt.plot( 'x_pos', 'y_pos', data=df, linestyle='none', marker='o')
# 文本
plt.annotate('有趣的点！', xy=(25, 200), xytext=(0, 300),
                      # 自定义箭头
                     arrowprops=dict(facecolor='black', shrink=0.005))
# 公式
plt.text(70, -120, r'equation: $\sum_{i=0}^\infty x_i$', fontsize=12)
# 正方形边缘框 
# patches.Circle为圆形边框，patches.Ellipse为椭圆形边框
ax.add_patch(
                patches.Rectangle(
                (70, 100), # (x,y)
                25, # 宽
                50, # 高
                alpha=0.3, facecolor="red", edgecolor="black", linewidth=3, linestyle='solid')
        )
# 坐标线（水平与垂直线）
plt.axvline(40, color='r'),plt.axhline(40, color='r')
ax.set_title('添加注释信息')


# 3、自定义图例
# 导入数据
data = palmerpenguins.load_penguins() 
# 数据定义
FLIPPER_LENGTH = data["flipper_length_mm"].values # flipper长度数据
BILL_LENGTH = data["bill_length_mm"].values # bill长度数据
SPECIES = data["species"].values # 物种类别数据
SPECIES_ = np.unique(SPECIES) # 物种唯一值
COLORS = ["#1B9E77", "#D95F02", "#7570B3"] # 颜色列表

ax = plt.subplot2grid((2, 2), (1, 0), colspan=1)
for species, color in zip(SPECIES_, COLORS):
    idxs = np.where(SPECIES == species)
    ax.scatter(
        FLIPPER_LENGTH[idxs], BILL_LENGTH[idxs], label=species,
        s=50, color=color, alpha=0.7
    )
# 位置、大小等图例参数
legend = ax.legend(loc="lower right", fontsize=6, markerscale=2, labelspacing=2, frameon=False)
handles = legend.legendHandles
# 自定义标识
hatches = ["+", "x", "o"]
for i, handle in enumerate(handles):
    handle.set_edgecolor("#6c2167")
    handle.set_facecolor(COLORS[i])
    handle.set_hatch(hatches[i])
    handle.set_alpha(0.7)
ax.set_title('自定义图例')


# 4、回归拟合线
# 自定义数据
rng = np.random.default_rng(1234)
x = rng.uniform(0, 10, size=100)
y = x + rng.normal(size=100)

# 绘制散点图
ax = plt.subplot2grid((2, 2), (1, 1), colspan=1)
ax.scatter(x, y, s=60, alpha=0.7, edgecolors="k")

# 拟合-polyfit返回斜率b和截距a
b, a = np.polyfit(x, y, deg=1)

# 绘制回归线
xseq = np.linspace(0, 10, num=100) # x轴
ax.plot(xseq, a + b * xseq, color="k", lw=2.5)
ax.set_title('回归拟合线')

plt.show()

import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import numpy as np 
import pandas as pd

plt.rcParams['font.sans-serif'] = ['DejaVu Sans'] # 用来正常显示'-' [U+2212]问题

# 自定义数据
rng = np.random.default_rng(1234)
x = rng.lognormal(size=200)
y = x + rng.normal(scale=5 * (x / np.max(x)), size=200)

# 初始化
fig = plt.figure(figsize=(10,6))

# 原始散点图
ax = plt.subplot2grid((2, 2), (0, 0), colspan=1)
ax.scatter(x, y, s=60, alpha=0.7, edgecolors="k")
ax.set_title('default')

# x轴对数刻度
ax = plt.subplot2grid((2, 2), (0, 1), colspan=1)
ax.scatter(x, y, s=60, alpha=0.7, edgecolors="k")
ax.set_xscale("log")
ax.set_title('logarithmic scale for x axes')

# y轴对数刻度
ax = plt.subplot2grid((2, 2), (1, 0), colspan=1)
ax.scatter(x, y, s=60, alpha=0.7, edgecolors="k")
ax.set_yscale("log")
ax.set_title('logarithmic scale for y axes')

# xy轴对数刻度
ax = plt.subplot2grid((2, 2), (1, 1), colspan=1)
ax.scatter(x, y, s=60, alpha=0.7, edgecolors="k")
ax.set_xscale("log")
ax.set_yscale("log")
ax.set_title('logarithmic scale for x/y axes')


fig.tight_layout() # 自动调整间距
plt.show()

# 曼哈顿图是散点图的一种变体，可联想曼哈顿鳞次栉比的大楼
# 一般用于基因相关研究，如GWAS。每组表示一个染色体，每个点表示一个基因
# x轴为该点在染色体的位置，y轴值代表其P值的-log10，越高相关性越强

from pandas import DataFrame
from scipy.stats import uniform
from scipy.stats import randint
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
import matplotlib.cm as cm

mpl.rcParams.update(mpl.rcParamsDefault) # 恢复默认的matplotlib样式

# 自定义数据
df = DataFrame({'gene' : ['gene-%i' % i for i in np.arange(10000)],
                'pvalue' : uniform.rvs(size=10000),
                'chromosome' : ['ch-%i' % i for i in randint.rvs(0,12,size=10000)]})

# p值对数化
df['minuslog10pvalue'] = -np.log10(df.pvalue)
# 染色体组
df.chromosome = df.chromosome.astype('category') # 转category类型
df.chromosome = df.chromosome.cat.set_categories(['ch-%i' % i for i in range(12)], ordered=True) # 排序
df = df.sort_values('chromosome') # 数据排序

# 如何绘制基因与 -log10(pvalue) 的关系并按染色体着色
df['ind'] = range(len(df))
df_grouped = df.groupby(('chromosome'))

# 绘制曼哈顿图
fig = plt.figure(figsize=(14, 8))
ax = fig.add_subplot(111)
cmap = cm.get_cmap('rainbow', 12) # 获取调色板
colors = [cmap(i) for i in range(12)] # 分配颜色
x_labels = []
x_labels_pos = []

for num, (name, group) in enumerate(df_grouped):
    group.plot(kind='scatter', x='ind', y='minuslog10pvalue',color=colors[num % len(colors)], ax=ax)
    x_labels.append(name)
    x_labels_pos.append((group['ind'].iloc[-1] - (group['ind'].iloc[-1] - group['ind'].iloc[0])/2))
ax.set_xticks(x_labels_pos)
ax.set_xticklabels(x_labels)

# 设置轴
ax.set_xlim([0, len(df)])
ax.set_ylim([0, 3.5])
ax.set_xlabel('Chromosome')

plt.show()

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import random

# 自定义数据
days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
hours = list(range(24))
sales_data = []

for day in days:
    for hour in hours:
        rand_num = random.random()  # 生成0-1之间的随机数
        if rand_num <= 0.8:  # 80%的概率生成0-100之间的销售量
            sales_volume = random.randint(0, 20)
        else:  # 20%的概率生成100-600之间的销售量
            sales_volume = random.randint(40, 500)
        sales_data.append([day, hour, sales_volume])

df = pd.DataFrame(sales_data, columns=['Day', 'Hour', 'Sales Volume'])


# 将一周的数据映射成数值类型，方便Y轴显示
day_to_num = {day: num for num, day in enumerate(days)}
df['Day_num'] = df['Day'].map(day_to_num)

# 创建一个新的figure
plt.figure(figsize=(10,6))

# 移除边框
spines = plt.gca().spines
for side in ['top','right']:
    spines[side].set_visible(False)

# 为每一天绘制散点图
for day in days:
    day_data = df[df['Day'] == day]
    plt.scatter(day_data['Hour'], day_data['Day_num'], s=day_data['Sales Volume'], label=day)

plt.yticks(np.arange(len(days)), days)    # 设置y轴的刻度和标签

# 自定义图里
plt.legend(bbox_to_anchor=(1.02,1), loc="upper left", borderaxespad=0)

plt.show()

# 当数据集较大时，绘制散点图容易出现重叠造成不可读
import matplotlib.pyplot as plt
import matplotlib as mpl
import numpy as np
import seaborn as sns
import pandas as pd
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签

# 自定义数据
df=pd.DataFrame({'x': np.random.normal(10, 1.2, 20000), 
                 'y': np.random.normal(10, 1.2, 20000), 'group': np.repeat('A',20000) })
tmp1=pd.DataFrame({'x': np.random.normal(14.5, 1.2, 20000), 
                   'y': np.random.normal(14.5, 1.2, 20000), 'group': np.repeat('B',20000) })
tmp2=pd.DataFrame({'x': np.random.normal(9.5, 1.5, 20000), 
                   'y': np.random.normal(15.5, 1.5, 20000), 'group': np.repeat('C',20000) })
df=pd.concat([df,tmp1,tmp2], ignore_index=True)


# 初始化
fig = plt.figure(figsize=(8,8))

# 过度绘制
ax = plt.subplot2grid((2, 2), (0, 0), colspan=1)
plt.plot('x', 'y', "o", data=df, linestyle='')
ax.set_title('过度绘制')

# 减小标记与透明度
ax = plt.subplot2grid((2, 2), (0, 1), colspan=1)
plt.plot( 'x', 'y', "o", data=df, linestyle='', markersize=3, alpha=0.05, color="purple")
ax.set_title('减小标记与透明度')

# 2D密度图
ax = plt.subplot2grid((2, 2), (1, 0), colspan=1)
sns.kdeplot(data = df, x="x", y="y", cmap="Reds", fill=True)
ax.set_title('2D密度图')

# 样本采样
df_sample=df.sample(1000) # 样本采样
ax = plt.subplot2grid((2, 2), (1, 1), colspan=1)
plt.plot('x', 'y', "o", data=df_sample, linestyle='')
ax.set_title('样本采样')


fig.tight_layout() # 自动调整间距
plt.show()

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.gridspec as gridspec

# 导入自定义模块
import SeabornFig2Grid as sfg

sns.set(font='SimHei', font_scale=0.8, style="darkgrid") # 解决Seaborn中文显示问题
 
# 自定义数据
df=pd.DataFrame({'x': np.random.normal(10, 1.2, 20000), 
                 'y': np.random.normal(10, 1.2, 20000), 'group': np.repeat('A',20000) })
tmp1=pd.DataFrame({'x': np.random.normal(14.5, 1.2, 20000), 
                   'y': np.random.normal(14.5, 1.2, 20000), 'group': np.repeat('B',20000) })
tmp2=pd.DataFrame({'x': np.random.normal(9.5, 1.5, 20000), 
                   'y': np.random.normal(15.5, 1.5, 20000), 'group': np.repeat('C',20000) })
df=pd.concat([df,tmp1,tmp2], ignore_index=True)

# 子图, 使用 gridspec 进行比例分配
fig = plt.figure(figsize=(8, 8))
gs = gridspec.GridSpec(2, 1, height_ratios=[4, 1])

# 绘制分组散点图
scatter1 = sns.lmplot( x="x", y="y", data=df, fit_reg=False, hue='group', 
               legend=False, palette="Accent", scatter_kws={"alpha":0.1,"s":15} )
scatter1.ax.legend(loc='lower right', markerscale=2)
scatter1.ax.set_title('分组散点图')

# 绘制分位面散点图
g = sns.FacetGrid(df, col="group", hue="group")
scatter2 = (g.map(plt.scatter, "x", "y", edgecolor="w"))
g.set_titles('分位面散点图-group {col_name}')
 
# 使用SeabornFig2Grid转换 seaborn 图为 matplotlib 子图
mg1 = sfg.SeabornFig2Grid(scatter1, fig, gs[0])
mg2 = sfg.SeabornFig2Grid(scatter2, fig, gs[1]) 
    
gs.tight_layout(fig)
plt.show()

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import pandas as pd

sns.set(font='SimHei', font_scale=0.8, style="darkgrid") # 解决Seaborn中文显示问题

# 自定义数据
a=np.concatenate([np.random.normal(2, 4, 1000), 
                  np.random.normal(4, 4, 1000), 
                  np.random.normal(1, 2, 500), 
                  np.random.normal(10, 2, 500), 
                  np.random.normal(8, 4, 1000), 
                  np.random.normal(10, 4, 1000)])
df=pd.DataFrame({'x': np.repeat( range(1,6), 1000), 'y': a })

fig, axs = plt.subplots(ncols=2, figsize=(8, 4)) # 创建1行2列的子图

# 原始散点图
axs[0].plot( 'x', 'y', "o", data=df, linestyle='')
axs[0].set_title('原始散点图')

# 抖动散点图
sns.stripplot(data =df, x="x", y="y", jitter=0.2, size=2, ax=axs[1])
axs[1].set_title('抖动散点图')

plt.tight_layout()
plt.show()

# 3D图
from scipy.stats import gaussian_kde
from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl

mpl.rcParams.update(mpl.rcParamsDefault) # 恢复默认的matplotlib样式
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签

# 自定义数据
nbins=300
k = gaussian_kde([df.x,df.y])
xi, yi = np.mgrid[ df.x.min():df.x.max():nbins*1j, df.y.min():df.y.max():nbins*1j]
zi = k(np.vstack([xi.flatten(), yi.flatten()]))
data=pd.DataFrame({'x': xi.flatten(), 'y': yi.flatten(), 'z': zi })

# 绘制3D图
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot_trisurf(data.x, data.y, data.z, cmap=plt.cm.Spectral, linewidth=0.2)

ax.view_init(30, 80)

plt.title('3D图')
plt.show()