爱坤都爱看的40张图表

爱坤都爱看的40张图表## 标题

简介

1.条形图

# libraries
import matplotlib.pyplot as plt
import numpy as np

# create dataset
height = [3, 12, 5, 18, 45]
bars = ('A', 'B', 'C', 'D', 'E')
y_pos = np.arange(len(bars))
 
# Create horizontal bars
plt.barh(y_pos, height)
 
# Create names on the x-axis
plt.yticks(y_pos, bars)
 
# Show graphic
plt.show()

2.条形图

# library
import matplotlib.pyplot as plt
 
# Create bars
barWidth = 0.9
bars1 = [3, 3, 1]
bars2 = [4, 2, 3]
bars3 = [4, 6, 7, 10, 4, 4]
bars4 = bars1 + bars2 + bars3
 
# The X position of bars
r1 = [1,5,9]
r2 = [2,6,10]
r3 = [3,4,7,8,11,12]
r4 = r1 + r2 + r3
 
# Create barplot
plt.bar(r1, bars1, width = barWidth, color = (0.3,0.1,0.4,0.6), label='Alone')
plt.bar(r2, bars2, width = barWidth, color = (0.3,0.5,0.4,0.6), label='With Himself')
plt.bar(r3, bars3, width = barWidth, color = (0.3,0.9,0.4,0.6), label='With other genotype')
# Note: the barplot could be created easily. See the barplot section for other examples.
 
# Create legend
plt.legend()
 
# Text below each barplot with a rotation at 90°
plt.xticks([r + barWidth for r in range(len(r4))], ['DD', 'with himself', 'with DC', 'with Silur', 'DC', 'with himself', 'with DD', 'with Silur', 'Silur', 'with himself', 'with DD', 'with DC'], rotation=90)
 
# Create labels
label = ['n = 6', 'n = 25', 'n = 13', 'n = 36', 'n = 30', 'n = 11', 'n = 16', 'n = 37', 'n = 14', 'n = 4', 'n = 31', 'n = 34']
 
# Text on the top of each bar
for i in range(len(r4)):
    plt.text(x = r4[i]-0.5 , y = bars4[i]+0.1, s = label[i], size = 6)

# Adjust the margins
plt.subplots_adjust(bottom= 0.2, top = 0.98)
 
# Show graphic
plt.show()

3.堆叠条形图

# libraries
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import pandas as pd
 
# Dataset:
a = pd.DataFrame({ 'group' : np.repeat('A',500), 'value': np.random.normal(10, 5, 500) })
b = pd.DataFrame({ 'group' : np.repeat('B',500), 'value': np.random.normal(13, 1.2, 500) })
c = pd.DataFrame({ 'group' : np.repeat('B',500), 'value': np.random.normal(18, 1.2, 500) })
d = pd.DataFrame({ 'group' : np.repeat('C',20), 'value': np.random.normal(25, 4, 20) })
e = pd.DataFrame({ 'group' : np.repeat('D',100), 'value': np.random.uniform(12, size=100) })
df=a.append(b).append(c).append(d).append(e)

# plot violin chart
sns.violinplot( x='group', y='value', data=df)

# add title
plt.title("Violin plot", loc="left")

# show the graph
plt.show()

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\347106830.py:13: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df=a.append(b).append(c).append(d).append(e)
C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\347106830.py:13: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df=a.append(b).append(c).append(d).append(e)
C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\347106830.py:13: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df=a.append(b).append(c).append(d).append(e)

4.-隐藏数据框图下

# libraries
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import rc
import pandas as pd
 
# Data
r = [0,1,2,3,4]
raw_data = {'greenBars': [20, 1.5, 7, 10, 5], 'orangeBars': [5, 15, 5, 10, 15],'blueBars': [2, 15, 18, 5, 10]}
df = pd.DataFrame(raw_data)
 
# From raw value to percentage
totals = [i+j+k for i,j,k in zip(df['greenBars'], df['orangeBars'], df['blueBars'])]
greenBars = [i / j * 100 for i,j in zip(df['greenBars'], totals)]
orangeBars = [i / j * 100 for i,j in zip(df['orangeBars'], totals)]
blueBars = [i / j * 100 for i,j in zip(df['blueBars'], totals)]
 
# plot
barWidth = 0.85
names = ('A','B','C','D','E')
# Create green Bars
plt.bar(r, greenBars, color='#b5ffb9', edgecolor='white', width=barWidth)
# Create orange Bars
plt.bar(r, orangeBars, bottom=greenBars, color='#f9bc86', edgecolor='white', width=barWidth)
# Create blue Bars
plt.bar(r, blueBars, bottom=[i+j for i,j in zip(greenBars, orangeBars)], color='#a3acff', edgecolor='white', width=barWidth)
 
# Custom x axis
plt.xticks(r, names)
plt.xlabel("group")
 
# Show graphic
plt.show()

5.方块散点图

# libraries
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import seaborn as sns
 
# Create data frame with randomly selected x and y positions
df = pd.DataFrame(np.random.random((100,2)), columns=["x","y"])
 
# Add a column: the color depends on x and y values, but you can use any function you want
value=(df['x']>0.2) & (df['y']>0.4)
df['color']= np.where( value==True , "#9b59b6", "#3498db")
 
# plot
sns.regplot(data=df, x="x", y="y", fit_reg=False, scatter_kws={'facecolors':df['color']})

plt.show()

6.聚集散点图

# basic plot
sns.regplot(data=df, x="x", y="y", fit_reg=False, marker="o", color="skyblue", scatter_kws={'s':400})
 
# add text annotation
plt.text(3+0.2, 4.5, "An annotation", horizontalalignment='left', size='medium', color='black', weight='semibold')

plt.show()

7.密度绘图与 matplotlib

# libraries
import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import kde
 
# create data
x = np.random.normal(size=500)
y = x * 3 + np.random.normal(size=500)
 
# Evaluate a gaussian kde on a regular grid of nbins x nbins over data extents
nbins=300
k = kde.gaussian_kde([x,y])
xi, yi = np.mgrid[x.min():x.max():nbins*1j, y.min():y.max():nbins*1j]
zi = k(np.vstack([xi.flatten(), yi.flatten()]))
 
# Make the plot
plt.pcolormesh(xi, yi, zi.reshape(xi.shape), shading='auto')
plt.show()
 
# Change color palette
plt.pcolormesh(xi, yi, zi.reshape(xi.shape), shading='auto', cmap=plt.cm.Greens_r)
plt.show()

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\1895255686.py:12: DeprecationWarning: Please use `gaussian_kde` from the `scipy.stats` namespace, the `scipy.stats.kde` namespace is deprecated.
  k = kde.gaussian_kde([x,y])

8. 避免重叠散点图中具有 2D 密度

# Libraries
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import kde
 
# Create data: 200 points
data = np.random.multivariate_normal([0, 0], [[1, 0.5], [0.5, 3]], 200)
x, y = data.T
 
# Create a figure with 6 plot areas
fig, axes = plt.subplots(ncols=6, nrows=1, figsize=(21, 5))
 
# Everything starts with a Scatterplot
axes[0].set_title('Scatterplot')
axes[0].plot(x, y, 'ko')
# As you can see there is a lot of overlapping here!
 
# Thus we can cut the plotting window in several hexbins
nbins = 20
axes[1].set_title('Hexbin')
axes[1].hexbin(x, y, gridsize=nbins, cmap=plt.cm.BuGn_r)
 
# 2D Histogram
axes[2].set_title('2D Histogram')
axes[2].hist2d(x, y, bins=nbins, cmap=plt.cm.BuGn_r)
 
# Evaluate a gaussian kde on a regular grid of nbins x nbins over data extents
k = kde.gaussian_kde(data.T)
xi, yi = np.mgrid[x.min():x.max():nbins*1j, y.min():y.max():nbins*1j]
zi = k(np.vstack([xi.flatten(), yi.flatten()]))
 
# plot a density
axes[3].set_title('Calculate Gaussian KDE')
axes[3].pcolormesh(xi, yi, zi.reshape(xi.shape), shading='auto', cmap=plt.cm.BuGn_r)
 
# add shading
axes[4].set_title('2D Density with shading')
axes[4].pcolormesh(xi, yi, zi.reshape(xi.shape), shading='gouraud', cmap=plt.cm.BuGn_r)
 
# contour
axes[5].set_title('Contour')
axes[5].pcolormesh(xi, yi, zi.reshape(xi.shape), shading='gouraud', cmap=plt.cm.BuGn_r)
axes[5].contour(xi, yi, zi.reshape(xi.shape) )

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\129967845.py:28: DeprecationWarning: Please use `gaussian_kde` from the `scipy.stats` namespace, the `scipy.stats.kde` namespace is deprecated.
  k = kde.gaussian_kde(data.T)





<matplotlib.contour.QuadContourSet at 0x15254b60790>

9.具有各种输入格式的 90 热图

# library
import seaborn as sns
import pandas as pd
import numpy as np
 
# Create a dataset
df = pd.DataFrame(np.random.random((5,5)), columns=["a","b","c","d","e"])
 
# Default heatmap: just a visualization of this square matrix
sns.heatmap(df)

<Axes: >

10.自定义海生热图

# libraries
import seaborn as sns
import pandas as pd
import numpy as np
 
# Create a dataset
df = pd.DataFrame(np.random.random((10,10)), columns=["a","b","c","d","e","f","g","h","i","j"])

# plot a heatmap with annotation
sns.heatmap(df, annot=True, annot_kws={"size": 7})

<Axes: >

11.控制海生颜色热图

# libraries
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
 
# Create a dataset
df = pd.DataFrame(np.random.random((10,10)), columns=["a","b","c","d","e","f","g","h","i","j"])

# plot using a color palette
sns.heatmap(df, cmap="YlGnBu")
plt.show()

sns.heatmap(df, cmap="Blues")
plt.show()

sns.heatmap(df, cmap="BuPu")
plt.show()

sns.heatmap(df, cmap="Greens")
plt.show()

12.制作调色板与海生

# Libraries
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
 
# create data
x = np.random.rand(80) - 0.5
y = x+np.random.rand(80)
z = x+np.random.rand(80)
df = pd.DataFrame({'x':x, 'y':y, 'z':z})
 
# Plot with palette
sns.lmplot( x='x', y='y', data=df, fit_reg=False, hue='x', legend=False, palette="Blues")
plt.show()
 
# reverse palette
sns.lmplot( x='x', y='y', data=df, fit_reg=False, hue='x', legend=False, palette="Blues_r")
plt.show()

13.海生主题

# libraries
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
 
# Data
data = np.random.normal(size=(20, 6)) + np.arange(6) / 2
 
# Proposed themes: darkgrid, whitegrid, dark, white, and ticks
 
sns.set_style("whitegrid")
sns.boxplot(data=data)
plt.title("whitegrid")
plt.show()
 
sns.set_style("darkgrid")
sns.boxplot(data=data);
plt.title("darkgrid")
plt.show()
 
sns.set_style("white")
sns.boxplot(data=data);
plt.title("white")
plt.show()

sns.set_style("dark")
sns.boxplot(data=data);
plt.title("dark")
plt.show()

sns.set_style("ticks")
sns.boxplot(data=data);
plt.title("ticks")
plt.show()

14.seaborn-style-on-matplotlib-plot

# library and dataset
from matplotlib import pyplot as plt
import pandas as pd
import numpy as np
 
# Create data
df=pd.DataFrame({'x_axis': range(1,101), 'y_axis': np.random.randn(100)*15+range(1,101), 'z': (np.random.randn(100)*15+range(1,101))*2 })
 
# plot with matplotlib
plt.plot( 'x_axis', 'y_axis', data=df, marker='o', color='mediumvioletred')
plt.show()

15.线图与 matplotlib

# libraries
import matplotlib.pyplot as plt
import numpy as np
 
# create data
values=np.cumsum(np.random.randn(1000,1))
 
# use the plot function
plt.plot(values)

# show the graph
plt.show()

16.折线图自定义

# Libraries and data
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
df=pd.DataFrame({'x_values': range(1,11), 'y_values': np.random.randn(10) })

# Draw plot
plt.plot( 'x_values', 'y_values', data=df, color='skyblue')
plt.show()

# Draw line chart by modifiying transparency of the line
plt.plot( 'x_values', 'y_values', data=df, color='skyblue', alpha=0.3)

# Show plot
plt.show()

17.多折线图

# libraries
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
 
# Data
df=pd.DataFrame({'x_values': range(1,11), 'y1_values': np.random.randn(10), 'y2_values': np.random.randn(10)+range(1,11), 'y3_values': np.random.randn(10)+range(11,21) })
 
# multiple line plots
plt.plot( 'x_values', 'y1_values', data=df, marker='o', markerfacecolor='blue', markersize=12, color='skyblue', linewidth=4)
plt.plot( 'x_values', 'y2_values', data=df, marker='', color='olive', linewidth=2)
plt.plot( 'x_values', 'y3_values', data=df, marker='', color='olive', linewidth=2, linestyle='dashed', label="toto")

# show legend
plt.legend()

# show graph
plt.show()

18.突出显示线中线图

# libraries
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
 
# Make a data frame
df=pd.DataFrame({'x': range(1,11), 'y1': np.random.randn(10), 'y2': np.random.randn(10)+range(1,11), 'y3': np.random.randn(10)+range(11,21), 'y4': np.random.randn(10)+range(6,16), 'y5': np.random.randn(10)+range(4,14)+(0,0,0,0,0,0,0,-3,-8,-6), 'y6': np.random.randn(10)+range(2,12), 'y7': np.random.randn(10)+range(5,15), 'y8': np.random.randn(10)+range(4,14) })

# Change the style of plot
plt.style.use('seaborn-darkgrid')

# set figure size
my_dpi=96
plt.figure(figsize=(480/my_dpi, 480/my_dpi), dpi=my_dpi)
 
# plot multiple lines
for column in df.drop('x', axis=1):
    plt.plot(df['x'], df[column], marker='', color='grey', linewidth=1, alpha=0.4)

# Now re do the interesting curve, but biger with distinct color
plt.plot(df['x'], df['y5'], marker='', color='orange', linewidth=4, alpha=0.7)
 
# Change x axis limit
plt.xlim(0,12)
 
# Let's annotate the plot
num=0
for i in df.values[9][1:]:
    num+=1
    name=list(df)[num]
    if name != 'y5':
        plt.text(10.2, i, name, horizontalalignment='left', size='small', color='grey')

# And add a special annotation for the group we are interested in
plt.text(10.2, df.y5.tail(1), 'Mr Orange', horizontalalignment='left', size='small', color='orange')
 
# Add titles
plt.title("Evolution of Mr Orange vs other students", loc='left', fontsize=12, fontweight=0, color='orange')
plt.xlabel("Time")
plt.ylabel("Score")

# Show the graph
plt.show()

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\876129807.py:10: MatplotlibDeprecationWarning: The seaborn styles shipped by Matplotlib are deprecated since 3.6, as they no longer correspond to the styles shipped by seaborn. However, they will remain available as 'seaborn-v0_8-<style>'. Alternatively, directly use the seaborn API instead.
  plt.style.use('seaborn-darkgrid')

19.基本连接散点图

plt.plot(
    x, z, ls="--", lw=3, 
    marker="X", markersize=10, markerfacecolor="red", markeredgecolor="black",
    label="Income"
)
plt.plot(
    x, y, ls=":", 
    marker="o", markersize=15, markerfacecolor="None", 
    label="Expenses"
)
plt.legend()
plt.show()

20.如何避免使用python过度绘制

# libraries
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import pandas as pd
 
# Dataset:
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=df.append(tmp1).append(tmp2)

# Plot with small marker size
plt.plot( 'x', 'y', "", data=df, linestyle='', marker='o', markersize=0.7)
plt.xlabel('Value of X')
plt.ylabel('Value of Y')
plt.title('Overplotting? Try to reduce the dot size', loc='left')
plt.show()

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\2806375468.py:11: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df=df.append(tmp1).append(tmp2)
C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\2806375468.py:14: UserWarning: linestyle is redundantly defined by the 'linestyle' keyword argument and the fmt string "" (-> linestyle='-'). The keyword argument will take precedence.
  plt.plot( 'x', 'y', "", data=df, linestyle='', marker='o', markersize=0.7)

21.基本饼图

# library
import pandas as pd
import matplotlib.pyplot as plt
 
# --- dataset 2: 3 columns and rownames
df = pd.DataFrame({'var1':[8,3,4,2], 'var2':[1,3,4,1]}, index=['a', 'b', 'c', 'd'] )
 
# make the multiple plot
df.plot(kind='pie', subplots=True, figsize=(16,8))

# show the plot
plt.show()

22.基本甜甜圈图

# library
import matplotlib.pyplot as plt
 
# create data
size_of_groups=[12,11,3,30]
 
# Create a pie plot
plt.pie(size_of_groups)
#plt.show()
 
# add a white circle at the center
my_circle=plt.Circle( (0,0), 0.7, color='white')
p=plt.gcf()
p.gca().add_artist(my_circle)

# show the graph
plt.show()

23.改变甜甜圈图的背景

# library
import matplotlib.pyplot as plt
 
# Data
names = 'groupA', 'groupB', 'groupC', 'groupD',
size = [12,11,3,30]
 
# create a figure and set different background
fig = plt.figure()
fig.patch.set_facecolor('black')
 
# Change color of text
plt.rcParams['text.color'] = 'white'
 
# Create a circle at the center of the plot
my_circle=plt.Circle( (0,0), 0.7, color='black')
 
# Pieplot + circle on it
plt.pie(size, labels=names)
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.show()

24.甜甜圈图与子组

# Libraries
import matplotlib.pyplot as plt
 
# Make data: I have 3 groups and 7 subgroups
group_names=['groupA', 'groupB', 'groupC']
group_size=[12,11,30]
subgroup_names=['A.1', 'A.2', 'A.3', 'B.1', 'B.2', 'C.1', 'C.2', 'C.3', 'C.4', 'C.5']
subgroup_size=[4,3,5,6,5,10,5,5,4,6]
 
# Create colors
a, b, c=[plt.cm.Blues, plt.cm.Reds, plt.cm.Greens]
 
# First Ring (outside)
fig, ax = plt.subplots()
ax.axis('equal')
mypie, _ = ax.pie(group_size, radius=1.3, labels=group_names, colors=[a(0.6), b(0.6), c(0.6)] )
plt.setp( mypie, width=0.3, edgecolor='white')
 
# Second Ring (Inside)
mypie2, _ = ax.pie(subgroup_size, radius=1.3-0.3, labels=subgroup_names, labeldistance=0.7, colors=[a(0.5), a(0.4), a(0.3), b(0.5), b(0.4), c(0.6), c(0.5), c(0.4), c(0.3), c(0.2)])
plt.setp( mypie2, width=0.4, edgecolor='white')
plt.margins(0,0)
 
# show it
plt.show()

25.基本棒棒糖剧情

# libraries
import matplotlib.pyplot as plt
import numpy as np
 
# create data
x=range(1,41)
values=np.random.uniform(size=40)
 
# stem function
plt.stem(x, values)
plt.ylim(0, 1.2)
plt.show()
 
# stem function: If x is not provided, a sequence of numbers is created by python:
plt.stem(values)
plt.show()

26.自定义棒棒糖剧情

# libraries
import matplotlib.pyplot as plt
import numpy as np
 
# create data
values=np.random.uniform(size=40)
 
# plot without markers
plt.stem(values, markerfmt=' ')
plt.show()
 
# change color and shape and size and edges
(markers, stemlines, baseline) = plt.stem(values)
plt.setp(markers, marker='D', markersize=10, markeredgecolor="orange", markeredgewidth=2)
plt.show()

27.垂直棒棒糖图

# libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
 
# Create a dataframe
df = pd.DataFrame({'group':list(map(chr, range(65, 85))), 'values':np.random.uniform(size=20) })
 
# Reorder it based on the values
ordered_df = df.sort_values(by='values')
my_range=range(1,len(df.index)+1)
 
# The horizontal plot is made using the hline function
plt.hlines(y=my_range, xmin=0, xmax=ordered_df['values'], color='skyblue')
plt.plot(ordered_df['values'], my_range, "o")
 
# Add titles and axis names
plt.yticks(my_range, ordered_df['group'])
plt.title("A vertical lolipop plot", loc='left')
plt.xlabel('Value of the variable')
plt.ylabel('Group')

# Show the plot
plt.show()

28.棒棒糖-2组

# libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
 
# Create a dataframe
value1=np.random.uniform(size=20)
value2=value1+np.random.uniform(size=20)/4
df = pd.DataFrame({'group':list(map(chr, range(65, 85))), 'value1':value1 , 'value2':value2 })
 
# Reorder it following the values of the first value:
ordered_df = df.sort_values(by='value1')
my_range=range(1,len(df.index)+1)
 
# The horizontal plot is made using the hline function
plt.hlines(y=my_range, xmin=ordered_df['value1'], xmax=ordered_df['value2'], color='grey', alpha=0.4)
plt.scatter(ordered_df['value1'], my_range, color='skyblue', alpha=1, label='value1')
plt.scatter(ordered_df['value2'], my_range, color='green', alpha=0.4 , label='value2')
plt.legend()
 
# Add title and axis names
plt.yticks(my_range, ordered_df['group'])
plt.title("Comparison of the value 1 and the value 2", loc='left')
plt.xlabel('Value of the variables')
plt.ylabel('Group')

# Show the graph
plt.show()

29.棒棒糖-带条件颜色的情节

# libraries
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
 
# Data
x = np.linspace(0, 2*np.pi, 100)
y = np.sin(x) + np.random.uniform(size=len(x)) - 0.2
 
# Create a color if the y axis value is equal or greater than 0
my_color = np.where(y>=0, 'orange', 'skyblue')
 
# The vertical plot is made using the vline function
plt.vlines(x=x, ymin=0, ymax=y, color=my_color, alpha=0.4)
plt.scatter(x, y, color=my_color, s=1, alpha=1)
 
# Add title and axis names
plt.title("Evolution of the value of ...", loc='left')
plt.xlabel('Value of the variable')
plt.ylabel('Group')

# Show the graph
plt.show()

30.基本面积图

# libraries
import numpy as np
import matplotlib.pyplot as plt
 
# Create data
x=range(1,6)
y=[1,4,6,8,4]
 
# Area plot
plt.fill_between(x, y)

# Show the graph
plt.show()
 
# Note that we could also use the stackplot function
# but fill_between is more convenient for future customization.
#plt.stackplot(x,y)
#plt.show()

31.改进面积图

# libraries
import numpy as np
import matplotlib.pyplot as plt
 
# create data
x=range(1,15)
y=[1,4,6,8,4,5,3,2,4,1,5,6,8,7]
 
# Change the color and its transparency
plt.fill_between( x, y, color="skyblue", alpha=0.4)

# Show the graph
plt.show()
 
# Same, but add a stronger line on top (edge)
plt.fill_between( x, y, color="skyblue", alpha=0.2)
plt.plot(x, y, color="Slateblue", alpha=0.6)
# See the line plot function to learn how to customize the plt.plot function

# Show the graph
plt.show()

32.面积图和刻面

# libraries
import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
 
# Create a dataset
my_count=["France","Australia","Japan","USA","Germany","Congo","China","England","Spain","Greece","Marocco","South Africa","Indonesia","Peru","Chili","Brazil"]
df = pd.DataFrame({
"country":np.repeat(my_count, 10),
"years":list(range(2000, 2010)) * 16,
"value":np.random.rand(160)
})
 
# Create a grid : initialize it
g = sns.FacetGrid(df, col='country', hue='country', col_wrap=4, )

# Add the line over the area with the plot function
g = g.map(plt.plot, 'years', 'value')
 
# Fill the area with fill_between
g = g.map(plt.fill_between, 'years', 'value', alpha=0.2).set_titles("{col_name} country")
 
# Control the title of each facet
g = g.set_titles("{col_name}")
 
# Add a title for the whole plot
plt.subplots_adjust(top=0.92)
g = g.fig.suptitle('Evolution of the value of stuff in 16 countries')

# Show the graph
plt.show()

33.带白色网格的区域图

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

# set the seaborn style
sns.set_style("whitegrid")
 
# Color palette
blue, = sns.color_palette("muted", 1)
 
# Create data
x = np.arange(23)
y = np.random.randint(8, 20, 23)
 
# Make the plot
fig, ax = plt.subplots()
ax.plot(x, y, color=blue, lw=3)
ax.fill_between(x, 0, y, alpha=.3)
ax.set(xlim=(0, len(x) - 1), ylim=(0, None), xticks=x)

# Show the graph
plt.show()

34.基本堆积面积图

# libraries
import numpy as np
import matplotlib.pyplot as plt
 
# --- FORMAT 1
 
# Your x and y axis
x=range(1,6)
y=[ [1,4,6,8,9], [2,2,7,10,12], [2,8,5,10,6] ]
 
# Basic stacked area chart.
plt.stackplot(x,y, labels=['A','B','C'])
plt.legend(loc='upper left')
plt.show()
 
# --- FORMAT 2
x=range(1,6)
y1=[1,4,6,8,9]
y2=[2,2,7,10,12]
y3=[2,8,5,10,6]
 
# Basic stacked area chart.
plt.stackplot(x,y1, y2, y3, labels=['A','B','C'])
plt.legend(loc='upper left')
plt.show()

35.堆积面积图的基线选项

# libraries
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
 
# Create data
X = np.arange(0, 10, 1)
Y = X + 5 * np.random.random((5, X.size))
 
# There are 4 types of baseline we can use:
baseline = ["zero", "sym", "wiggle", "weighted_wiggle"]
 
# Let's make 4 plots, 1 for each baseline
for n, v in enumerate(baseline):
    if n<3 :
        plt.tick_params(labelbottom='off')
    plt.subplot(2 ,2, n + 1)
    plt.stackplot(X, *Y, baseline=v)
    plt.title(v)
    plt.tight_layout()

C:\Users\ASUS\AppData\Local\Temp\ipykernel_11108\3218836517.py:17: MatplotlibDeprecationWarning: Auto-removal of overlapping axes is deprecated since 3.6 and will be removed two minor releases later; explicitly call ax.remove() as needed.
  plt.subplot(2 ,2, n + 1)

36.大熊猫堆积面积图

# libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
 
# Dataset
df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
 
# plot
df.plot.area()

# show the graph
plt.show()

37.堆积面积图

# libraries
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
 
# Make data
data = pd.DataFrame({  'group_A':[1,4,6,8,9], 'group_B':[2,24,7,10,12], 'group_C':[2,8,5,10,6], }, index=range(1,6))
 
# We need to transform the data from raw data to percentage (fraction)
data_perc = data.divide(data.sum(axis=1), axis=0)
 
# Make the plot
plt.stackplot(range(1,6),  data_perc["group_A"],  data_perc["group_B"],  data_perc["group_C"], labels=['A','B','C'])
plt.legend(loc='upper left')
plt.margins(0,0)
plt.title('100 % stacked area chart')
plt.show()

38.散点图动画

# libraries
import matplotlib.pyplot as plt
import seaborn as sns

# grey background
sns.set(style="darkgrid")

# Scatterplot with 1 data point
plt.scatter(1, 10, s=600, alpha=0.5, edgecolors="grey", linewidth=2)
plt.xlim(0, 10)
plt.ylim(0, 100)
plt.show();

39.3D散点图

# libraries
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
 
# Dataset
df=pd.DataFrame({'X': range(1,101), 'Y': np.random.randn(100)*15+range(1,101), 'Z': (np.random.randn(100)*15+range(1,101))*2 })
 
# plot
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(df['X'], df['Y'], df['Z'], c='skyblue', s=60)
plt.show()

40.基本雷达图

# Libraries
import matplotlib.pyplot as plt
import pandas as pd
from math import pi
 
# Set data
df = pd.DataFrame({
'group': ['A','B','C','D'],
'var1': [38, 1.5, 30, 4],
'var2': [29, 10, 9, 34],
'var3': [8, 39, 23, 24],
'var4': [7, 31, 33, 14],
'var5': [28, 15, 32, 14]
})
 
# number of variable
categories=list(df)[1:]
N = len(categories)
 
# We are going to plot the first line of the data frame.
# But we need to repeat the first value to close the circular graph:
values=df.loc[0].drop('group').values.flatten().tolist()
values += values[:1]
values
 
# What will be the angle of each axis in the plot? (we divide the plot / number of variable)
angles = [n / float(N) * 2 * pi for n in range(N)]
angles += angles[:1]
 
# Initialise the spider plot
ax = plt.subplot(111, polar=True)
 
# Draw one axe per variable + add labels
plt.xticks(angles[:-1], categories, color='grey', size=8)
 
# Draw ylabels
ax.set_rlabel_position(0)
plt.yticks([10,20,30], ["10","20","30"], color="grey", size=7)
plt.ylim(0,40)
 
# Plot data
ax.plot(angles, values, linewidth=1, linestyle='solid')
 
# Fill area
ax.fill(angles, values, 'b', alpha=0.1)

# Show the graph
plt.show()