Python可视化35|matplotlib&seaborn-一些有用的图

本文分享一些之前没介绍到的感觉有用的图。

 

本文速览 

1、边界气泡图(Bubble plot with Encircling)

2、边缘箱图(Marginal Boxplot)

3、水平发散型文本(Diverging Texts) 

4、垂直发散型文本(Diverging Texts) 

5、面积图(Area Chart)

6、棒棒糖图(Lollipop Chart)

7、坡图(Slope Chart)

8、哑铃图(Dumbbell Plot)

9、山峰图(joypy)

10、金字塔图(Population Pyramid)

11、树状图(Treemap)

12、同一个图使用双坐标轴

13、堆积面积图(Stacked Area Chart)

---

1、边界气泡图(Bubble plot with Encircling)

# 圈出重点关注的点
from matplotlib import patches
from scipy.spatial import ConvexHull#更多参考scipy.spatial.ConvexHull
sns.set_style("whitegrid")

# Step 1: Prepare Data
midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")

# As many colors as there are unique midwest['category']
categories = np.unique(midwest['category'])
colors = [plt.cm.Set1(i/float(len(categories)-1)) for i in range(len(categories))]

# Step 2: Draw Scatterplot with unique color for each category
fig = plt.figure(figsize=(12, 8), dpi= 80, facecolor='w', edgecolor='k')    

for i, category in enumerate(categories):
    plt.scatter('area', 'poptotal', data=midwest.loc[midwest.category==category, :], s='dot_size', c=colors[i], label=str(category), edgecolors='black', linewidths=.5)

# Step 3: Encircling
# https://stackoverflow.com/questions/44575681/how-do-i-encircle-different-data-sets-in-scatter-plot
def encircle(x,y, ax=None, **kw):#定义encircle函数，圈出重点关注的点
    if not ax: ax=plt.gca()
    p = np.c_[x,y]
    hull = ConvexHull(p)
    poly = plt.Polygon(p[hull.vertices,:], **kw)
    ax.add_patch(poly)

# Select data to be encircled
midwest_encircle_data1 = midwest.loc[midwest.state=='IN', :]  
encircle(midwest_encircle_data1.area, midwest_encircle_data1.poptotal, ec="pink", fc="#74C476", alpha=0.3)
encircle(midwest_encircle_data1.area, midwest_encircle_data1.poptotal, ec="g", fc="none", linewidth=1.5) 

midwest_encircle_data6 = midwest.loc[midwest.state=='WI', :]  
encircle(midwest_encircle_data6.area, midwest_encircle_data6.poptotal, ec="pink", fc="black", alpha=0.3)
encircle(midwest_encircle_data6.area, midwest_encircle_data6.poptotal, ec="black", fc="none", linewidth=1.5, linestyle='--')

# Step 4: Decorations
plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000),
              xlabel='Area', ylabel='Population')

plt.xticks(fontsize=12); plt.yticks(fontsize=12)
plt.title("Bubble Plot with Encircling", fontsize=22)
plt.legend(fontsize=12)    
plt.show()    

2、边缘箱图(Marginal Boxplot)

#中间散点图，右边和下边分别绘制y轴及x轴数据的箱图，
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/mpg_ggplot2.csv")

# Create Fig and gridspec
fig = plt.figure(figsize=(16, 10), dpi= 80)
grid = plt.GridSpec(4, 4, hspace=0.5, wspace=0.2)#这里使用了matplotlib.pyplot.GridSpec分片figure，其实可以直接使用seaborn中的，前面讲过

# Define the axes
ax_main = fig.add_subplot(grid[:-1, :-1])
ax_right = fig.add_subplot(grid[:-1, -1], xticklabels=[], yticklabels=[])
ax_bottom = fig.add_subplot(grid[-1, 0:-1], xticklabels=[], yticklabels=[])

# Scatterplot on main ax
ax_main.scatter('displ', 'hwy', s=df.cty*5, c=df.manufacturer.astype('category').cat.codes, alpha=.9, data=df, cmap="Set1", edgecolors='black', linewidths=.5)

# Add a graph in each part
sns.boxplot(df.hwy, ax=ax_right, orient="v",linewidth=2)
sns.boxplot(df.displ, ax=ax_bottom, orient="h",linewidth=2)

# Decorations ------------------
# Remove x axis name for the boxplot
ax_bottom.set(xlabel='')
ax_right.set(ylabel='')

# Main Title, Xlabel and YLabel
ax_main.set(title='Scatterplot with Histograms \n displ vs hwy', xlabel='displ', ylabel='hwy')

# Set font size of different components
ax_main.title.set_fontsize(20)
for item in ([ax_main.xaxis.label, ax_main.yaxis.label] + ax_main.get_xticklabels() + ax_main.get_yticklabels()):
    item.set_fontsize(14)

plt.show()

3、水平发散型文本(Diverging Texts) 

# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = ['red' if x < 0 else 'green' for x in df['mpg_z']]
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)

# Draw plot
plt.figure(figsize=(10,8), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z,color=df.colors, alpha=0.4, linewidth=5)
for x, y, tex in zip(df.mpg_z, df.index, df.mpg_z):
    t = plt.text(x, y, round(tex, 2), horizontalalignment='right' if x < 0 else 'left', 
                 verticalalignment='center', fontdict={'color':'black' if x < 0 else 'black', 'size':14})

# Decorations    
plt.yticks(df.index, df.cars, fontsize=12)
plt.title('Diverging Text Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.xlim(-2.5, 2.5)
plt.show()

4、垂直发散型文本(Diverging Texts) 

# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = ['red' if x < 0 else 'green' for x in df['mpg_z']]
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)

# Draw plot
plt.figure(figsize=(10,8), dpi= 80)
plt.vlines(x=df.index, ymin=0, ymax=df.mpg_z,color=df.colors, alpha=0.4, linewidth=5)
for y, x, tex in zip(df.mpg_z, df.index, df.mpg_z):
    t = plt.text(x, y, round(tex, 2), horizontalalignment='left' if x < 0 else 'left', 
                 verticalalignment='center', fontdict={'color':'black' if x < 0 else 'black', 'size':14})

# Decorations    
plt.xticks(df.index, df.cars, fontsize=12,rotation=90)
plt.title('Diverging Text Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.show()

5、面积图(Area Chart)

import numpy as np
import pandas as pd

# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv", parse_dates=['date']).head(100)
x = np.arange(df.shape[0])
y_returns = (df.psavert.diff().fillna(0)/df.psavert.shift(1)).fillna(0) * 100

# Plot使用plt.fill_between
plt.figure(figsize=(10,8), dpi= 80)
plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] >= 0, facecolor='green', interpolate=True, alpha=0.7)
plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] <= 0, facecolor='red', interpolate=True, alpha=0.7)

# Annotate
plt.annotate('Peak \n1975', xy=(94.0, 21.0), xytext=(88.0, 28),
             bbox=dict(boxstyle='square', fc='firebrick'),
             arrowprops=dict(facecolor='steelblue', shrink=0.05), fontsize=15, color='white')


# Decorations
xtickvals = [str(m)[:3].upper()+"-"+str(y) for y,m in zip(df.date.dt.year, df.date.dt.month_name())]
plt.gca().set_xticks(x[::6])
plt.gca().set_xticklabels(xtickvals[::6], rotation=90, fontdict={'horizontalalignment': 'center', 'verticalalignment': 'center_baseline'})
plt.ylim(-35,35)
plt.xlim(1,100)
plt.title("Month Economics Return %", fontsize=22)
plt.ylabel('Monthly returns %')
plt.grid(alpha=0.5)
plt.show()

6、棒棒糖图(Lollipop Chart)

# Prepare Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.sort_values('cty', inplace=True)
df.reset_index(inplace=True)

# Draw plot
fig, ax = plt.subplots(figsize=(10,8), dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=4)
ax.scatter(x=df.index, y=df.cty, s=75, color='firebrick', alpha=0.7)

# Title, Label, Ticks and Ylim
ax.set_title('Lollipop Chart for Highway Mileage', fontdict={'size':22})
ax.set_ylabel('Miles Per Gallon')
ax.set_xticks(df.index)
ax.set_xticklabels(df.manufacturer.str.upper(), rotation=60, fontdict={'horizontalalignment': 'right', 'size':12})
ax.set_ylim(0, 30)

# Annotate
for row in df.itertuples():
    ax.text(row.Index, row.cty+.5, s=round(row.cty, 2), horizontalalignment= 'center', verticalalignment='bottom', fontsize=14)

plt.show()

7、坡图(Slope Chart)

#comparing the ‘Before’ and ‘After’ positions of a given person/item
import matplotlib.lines as mlines
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/gdppercap.csv")

left_label = [str(c) + ', '+ str(round(y)) for c, y in zip(df.continent, df['1952'])]
right_label = [str(c) + ', '+ str(round(y)) for c, y in zip(df.continent, df['1957'])]
klass = ['red' if (y1-y2) < 0 else 'green' for y1, y2 in zip(df['1952'], df['1957'])]

# draw line
# https://stackoverflow.com/questions/36470343/how-to-draw-a-line-with-matplotlib/36479941
def newline(p1, p2, color='black'):
    ax = plt.gca()
    l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='red' if p1[1]-p2[1] > 0 else 'green', marker='o', markersize=6)
    ax.add_line(l)
    return l

fig, ax = plt.subplots(1,1,figsize=(12,10), dpi= 80)

# Vertical Lines
ax.vlines(x=1, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted')
ax.vlines(x=3, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted')

# Points
ax.scatter(y=df['1952'], x=np.repeat(1, df.shape[0]), s=10, color='black', alpha=0.7)
ax.scatter(y=df['1957'], x=np.repeat(3, df.shape[0]), s=10, color='black', alpha=0.7)

# Line Segmentsand Annotation
for p1, p2, c in zip(df['1952'], df['1957'], df['continent']):
    newline([1,p1], [3,p2])
    ax.text(1-0.05, p1, c + ', ' + str(round(p1)), horizontalalignment='right', verticalalignment='center', fontdict={'size':14})
    ax.text(3+0.05, p2, c + ', ' + str(round(p2)), horizontalalignment='left', verticalalignment='center', fontdict={'size':14})

# 'Before' and 'After' Annotations
ax.text(1-0.05, 13000, 'BEFORE', horizontalalignment='right', verticalalignment='center', fontdict={'size':18, 'weight':700})
ax.text(3+0.05, 13000, 'AFTER', horizontalalignment='left', verticalalignment='center', fontdict={'size':18, 'weight':700})

# Decoration
ax.set_title("Slopechart: Comparing GDP Per Capita between 1952 vs 1957", fontdict={'size':22})
ax.set(xlim=(0,4), ylim=(0,14000), ylabel='Mean GDP Per Capita')
ax.set_xticks([1,3])
ax.set_xticklabels(["1952", "1957"])
plt.yticks(np.arange(500, 13000, 2000), fontsize=12)

# Lighten borders
plt.gca().spines["top"].set_alpha(.0)
plt.gca().spines["bottom"].set_alpha(.0)
plt.gca().spines["right"].set_alpha(.0)
plt.gca().spines["left"].set_alpha(.0)
plt.show()

8、哑铃图(Dumbbell Plot)

#显示排序和处理前后值范围
import matplotlib.lines as mlines

# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/health.csv")
df.sort_values('pct_2014', inplace=True)
df.reset_index(inplace=True)

# Func to draw line segment
def newline(p1, p2, color='black'):
    ax = plt.gca()
    l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='skyblue')
    ax.add_line(l)
    return l

# Figure and Axes
fig, ax = plt.subplots(1,1,figsize=(12,10), facecolor='#f7f7f7', dpi= 80)

# Vertical Lines
ax.vlines(x=.05, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.10, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.15, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.20, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')

# Points
ax.scatter(y=df['index'], x=df['pct_2013'], s=50, color='#0e668b', alpha=0.7)
ax.scatter(y=df['index'], x=df['pct_2014'], s=50, color='#a3c4dc', alpha=0.7)

# Line Segments
for i, p1, p2 in zip(df['index'], df['pct_2013'], df['pct_2014']):
    newline([p1, i], [p2, i])

# Decoration
ax.set_facecolor('#f7f7f7')
ax.set_title("Dumbell Chart: Pct Change - 2013 vs 2014", fontdict={'size':22})
ax.set(xlim=(0,.25), ylim=(-1, 27), ylabel='Mean GDP Per Capita')
ax.set_xticks([.05, .1, .15, .20])
ax.set_xticklabels(['5%', '15%', '20%', '25%'])
ax.set_xticklabels(['5%', '15%', '20%', '25%'])    
plt.show()

9、山峰图(joypy)

#每组数据绘制核密度图，R中有ggjoy
import joypy
# Import Data
mpg = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(12,8), dpi= 80)
fig, axes = joypy.joyplot(mpg, column=['hwy', 'cty'], by="class", ylim='own', figsize=(12,8))

# Decoration
plt.title('Joy Plot of City and Highway Mileage by Class', fontsize=22)
plt.show()

10、金字塔图(Population Pyramid)

# Read data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/email_campaign_funnel.csv")

# Draw Plot
plt.figure(figsize=(12,8), dpi= 80)
group_col = 'Gender'
order_of_bars = df.Stage.unique()[::-1]
colors = [plt.cm.Spectral(i/float(len(df[group_col].unique())-1)) for i in range(len(df[group_col].unique()))]


#一种排过序的分组水平柱状图barplot
for c, group in zip(colors, df[group_col].unique()):
    sns.barplot(x='Users', y='Stage', data=df.loc[df[group_col]==group, :], order=order_of_bars, color=c, label=group)

# Decorations    
plt.xlabel("$Users$")
plt.ylabel("Stage of Purchase")
plt.yticks(fontsize=12)
plt.title("Population Pyramid of the Marketing Funnel", fontsize=22)
plt.legend()
plt.show()

11、树状图(Treemap)

# 类似饼图，面积大小反应变量大小
# pip install squarify
import squarify 

# Import Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size().reset_index(name='counts')
labels = df.apply(lambda x: str(x[0]) + "\n (" + str(x[1]) + ")", axis=1)
sizes = df['counts'].values.tolist()
colors = [plt.cm.Spectral(i/float(len(labels))) for i in range(len(labels))]

# Draw Plot
plt.figure(figsize=(10,8), dpi= 80)
squarify.plot(sizes=sizes, label=labels, color=colors, alpha=.8)

# Decorate
plt.title('Treemap of Vechile Class')
plt.axis('off')
plt.show()

12、同一个图使用双坐标轴

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv")

x = df['date']
y1 = df['psavert']
y2 = df['unemploy']

# Plot Line1 (Left Y Axis)
fig, ax1 = plt.subplots(1,1,figsize=(12,8), dpi= 80)
ax1.plot(x, y1, color='tab:red')

# Plot Line2 (Right Y Axis)
ax2 = ax1.twinx()  # instantiate a second axes that shares the same x-axis
ax2.plot(x, y2, color='tab:blue')

# Decorations
# ax1 (left Y axis)
ax1.set_xlabel('Year', fontsize=20)
ax1.tick_params(axis='x', rotation=90, labelsize=12)
ax1.set_ylabel('Personal Savings Rate', color='tab:red', fontsize=20)
ax1.tick_params(axis='y', rotation=0, labelcolor='tab:red' )
ax1.grid(alpha=.4)

# ax2 (right Y axis)
ax2.set_ylabel("# Unemployed (1000's)", color='tab:blue', fontsize=20)
ax2.tick_params(axis='y', labelcolor='tab:blue')
ax2.set_xticks(np.arange(0, len(x), 60))
ax2.set_xticklabels(x[::60], rotation=90, fontdict={'fontsize':10})
ax2.set_title("Personal Savings Rate vs Unemployed: Plotting in Secondary Y Axis", fontsize=22)
fig.tight_layout()
plt.show()

13、堆积面积图(Stacked Area Chart)

# Import Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/nightvisitors.csv')

# Decide Colors 
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange', 'tab:brown', 'tab:grey', 'tab:pink', 'tab:olive']      

# Draw Plot and Annotate
fig, ax = plt.subplots(1,1,figsize=(12, 8), dpi= 80)
columns = df.columns[1:]
labs = columns.values.tolist()

# Prepare data
x  = df['yearmon'].values.tolist()
y0 = df[columns[0]].values.tolist()
y1 = df[columns[1]].values.tolist()
y2 = df[columns[2]].values.tolist()
y3 = df[columns[3]].values.tolist()
y4 = df[columns[4]].values.tolist()
y5 = df[columns[5]].values.tolist()
y6 = df[columns[6]].values.tolist()
y7 = df[columns[7]].values.tolist()
y = np.vstack([y0, y2, y4, y6, y7, y5, y1, y3])

# Plot for each column
labs = columns.values.tolist()
ax = plt.gca()
ax.stackplot(x, y, labels=labs, colors=mycolors, alpha=0.8)
ax.tick_params(axis='x', rotation=90, labelsize=12)
# Decorations
ax.set_title('Night Visitors in Australian Regions', fontsize=18)
ax.set(ylim=[0, 100000])
ax.legend(fontsize=10, ncol=4)
plt.xticks(x[::5], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(10000, 100000, 20000), fontsize=10)
plt.xlim(x[0], x[-1])

# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)

plt.show()

---

参考资料