Python数据可视化（三）：条形图绘制

作者: Davey1220 | 来源:发表于2021-04-25 21:18 被阅读0次

Python数据可视化（三）：条形图绘制
python学统计第二课复现与作业
R语言可视化手册学习笔记
初识Plotly—Python图形化MySQL中数据
Python爬虫：绘图matplotlib与词云
Python可视化应用——如何自动控制条形图每根柱子颜色不同
Python编程&数据科学入门——第5课作业
Matplotlib基础用法
matplotlib可视化之如何给图形添加数据标签？
手把手教你 Tableau 绘制条形图（一）

使用matplotlib包绘制条形图

# 导入所需的python包
# Libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# 构建示例数据
# Create dataset
height = [3, 12, 5, 18, 45]
bars = ('A', 'B', 'C', 'D', 'E')
x_pos = np.arange(len(bars))

x_pos
array([0, 1, 2, 3, 4])

绘制基础条形图

# Create bars
plt.bar(x_pos, height)

# Create names on the x-axis
plt.xticks(x_pos, bars)

# Show graphic
plt.show()

image.png

# Create a data frame
df = pd.DataFrame ({
        'Group':  ['A', 'B', 'C', 'D', 'E'],
        'Value': [1,5,4,3,9]
})

df.head()

	Group	Value
0	A	1
1	B	5
2	C	4
3	D	3
4	E	9

# 绘制水平条形图
# Create horizontal bars
plt.barh(y=df.Group, width=df.Value)

image.png

# 排序绘制水平条形图
# Sort the table
df = df.sort_values(by=['Value'])

# Create horizontal bars
plt.barh(y=df.Group, width=df.Value);

# Add title
plt.title('A simple barplot');

image.png

自定义条形图的颜色

# Create bars with different colors
plt.bar(x=df.Group, height=df.Value, color=['black', 'red', 'green', 'blue', 'cyan'])

# Show graph
plt.show()

image.png

# Create bars with blue edge color
plt.bar(x=df.Group, height=df.Value, color=(0.1, 0.1, 0.1, 0.1), edgecolor='blue')

# Add title and axis names
plt.title('My title')
plt.xlabel('categories')
plt.ylabel('values')

# Show graph
plt.show()

image.png

添加误差棒

# width of the bars
barWidth = 0.3

# Choose the height of the blue bars
bars1 = [10, 9, 2]

# Choose the height of the cyan bars
bars2 = [10.8, 9.5, 4.5]

# Choose the height of the error bars (bars1)
yer1 = [0.5, 0.4, 0.5]

# Choose the height of the error bars (bars2)
yer2 = [1, 0.7, 1]

# The x position of bars
r1 = np.arange(len(bars1))
r2 = [x + barWidth for x in r1]

# Create blue bars
plt.bar(x=r1, height=bars1, width = barWidth, color = 'blue', edgecolor = 'black', yerr=yer1, capsize=7, label='poacee')

# Create cyan bars
plt.bar(x=r2, height=bars2, width = barWidth, color = 'cyan', edgecolor = 'black', yerr=yer2, capsize=7, label='sorgho')

# general layout
plt.xticks([r + barWidth for r in range(len(bars1))], ['cond_A', 'cond_B', 'cond_C'])

plt.ylabel('height')
plt.legend()

# Show graphic
plt.show()

image.png

绘制堆叠条形图

# 构建示例数据

# set width of bars
barWidth = 0.25

# set heights of bars
bars1 = [12, 30, 1, 8, 22]
bars2 = [28, 6, 16, 5, 10]
bars3 = [29, 3, 24, 25, 17]

# Set position of bar on X axis
r1 = np.arange(len(bars1))
r2 = [x + barWidth for x in r1]
r3 = [x + barWidth for x in r2]

# 绘制分组条形图

# Make the plot
plt.bar(r1, bars1, color='#7f6d5f', width=barWidth, edgecolor='white', label='var1')
plt.bar(r2, bars2, color='#557f2d', width=barWidth, edgecolor='white', label='var2')
plt.bar(r3, bars3, color='#2d7f5e', width=barWidth, edgecolor='white', label='var3')

# Add xticks on the middle of the group bars
plt.xlabel('group', fontweight='bold')
plt.xticks([r + barWidth for r in range(len(bars1))], ['A', 'B', 'C', 'D', 'E'])

# Create legend & Show graphic
plt.legend()
plt.show()

image.png

# 绘制堆叠条形图

# Heights of bars1 + bars2
bars = np.add(bars1, bars2).tolist()

# The position of the bars on the x-axis
r = [0,1,2,3,4]

# Names of group and bar width
names = ['A','B','C','D','E']
barWidth = 1

# Create brown bars
plt.bar(r, bars1, color='#7f6d5f', edgecolor='white', width=barWidth)
# Create green bars (middle), on top of the first ones
plt.bar(r, bars2, bottom=bars1, color='#557f2d', edgecolor='white', width=barWidth)
# Create green bars (top)
plt.bar(r, bars3, bottom=bars, color='#2d7f5e', edgecolor='white', width=barWidth)

# Custom X axis
plt.xticks(r, names, fontweight='bold')
plt.xlabel("group")

# Show graphic
plt.show()

image.png

# 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)]

# 绘制填充堆叠条形图

# plot
barWidth = 0.85
names = ('A','B','C','D','E')

# Create green Bars
plt.bar(r, greenBars, color='#b5ffb9', edgecolor='white', width=barWidth, label="group A")
# Create orange Bars
plt.bar(r, orangeBars, bottom=greenBars, color='#f9bc86', edgecolor='white', width=barWidth, label="group B")
# Create blue Bars
plt.bar(r, blueBars, bottom=[i+j for i,j in zip(greenBars, orangeBars)], color='#a3acff', edgecolor='white', width=barWidth, label="group C")

# Custom x axis
plt.xticks(r, names)
plt.xlabel("group")

# Add a legend
plt.legend(loc='upper left', bbox_to_anchor=(1,1), ncol=1)

# Show graphic
plt.show()

image.png

使用seaborn包绘制条形图

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

# set plot style: grey grid in the background:
sns.set(style="darkgrid")

# load dataset
tips = sns.load_dataset("tips")
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

# Set the figure size
plt.figure(figsize=(10, 7))

# plot a bar chart
# 绘制水平条形图
sns.barplot(
    x="total_bill", 
    y="day", 
    data=tips, 
    estimator=sum, # estimator : function to estimate within each category
    ci=None, # ci : size of confidence intervals (if None, error bars will not be drawn)
    color='#69b3a2');

image.png

# Set the figure size
plt.figure(figsize=(14, 10))

# plot a bar chart
sns.barplot(
    y="total_bill", 
    x="day", 
    data=tips, 
    estimator=sum, 
    ci=None, 
    color='skyblue');

image.png

# order参数设置条形图的顺序

# Set the figure size
plt.figure(figsize=(14, 10))

# plot a bar chart with given order of bars ["Fri","Thur","Sun","Sat"]
sns.barplot(
    x="total_bill", 
    y="day", 
    data=tips, 
    estimator=sum, 
    ci=None, 
    order=["Fri","Thur","Sun","Sat"], 
    color='#69b3a2'
);

image.png

# 添加误差棒

# Set the figure size
plt.figure(figsize=(14, 8))

# plot a bar chart
ax = sns.barplot(x="day", y="total_bill", data=tips, estimator=np.mean, ci=85, capsize=.2, color='lightblue')

image.png

# 绘制分组条形图

# set plot style: grey grid in the background:
sns.set(style="darkgrid")

# load dataset
tips = sns.load_dataset("tips")

# Set the figure size
plt.figure(figsize=(8, 8))

# grouped barplot
sns.barplot(x="day", y="total_bill", hue="smoker", data=tips, ci=None);

image.png

# 自定义条形图颜色

# Create an array with the colors you want to use
colors = ["#69b3a2", "#4374B3"]
sns.set_palette(sns.color_palette(colors))

# Set the figure size
plt.figure(figsize=(10, 10))

# grouped barplot
ax = sns.barplot(
    x="day", 
    y="total_bill", 
    hue="smoker", 
    data=tips, 
    ci=None
    )

# Customize the axes and title
ax.set_title("Smokers have bigger bills")
ax.set_ylabel("Bill value")

# Remove top and right borders
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

image.png

# 绘制堆叠条形图

import matplotlib.patches as mpatches

# load dataset
tips = sns.load_dataset("tips")

# set plot style: grey grid in the background:
sns.set(style="darkgrid")

# set the figure size
plt.figure(figsize=(14, 14))

# top bar -> sum all values(smoker=No and smoker=Yes) to find y position of the bars
total = tips.groupby('day')['total_bill'].sum().reset_index()

# bar chart 1 -> top bars (group of 'smoker=No')
bar1 = sns.barplot(x="day",  y="total_bill", data=total, color='darkblue')

# bottom bar ->  take only smoker=Yes values from the data
smoker = tips[tips.smoker=='Yes']

# bar chart 2 -> bottom bars (group of 'smoker=Yes')
bar2 = sns.barplot(x="day", y="total_bill", data=smoker, estimator=sum, ci=None,  color='lightblue')

# add legend
top_bar = mpatches.Patch(color='darkblue', label='smoker = No')
bottom_bar = mpatches.Patch(color='lightblue', label='smoker = Yes')
plt.legend(handles=[top_bar, bottom_bar])

# show the graph
plt.show()

image.png

# 绘制填充堆叠条形图

import matplotlib.patches as mpatches

# load dataset
tips = sns.load_dataset("tips")

# set the figure size
plt.figure(figsize=(14, 14))

# from raw value to percentage
total = tips.groupby('day')['total_bill'].sum().reset_index()
smoker = tips[tips.smoker=='Yes'].groupby('day')['total_bill'].sum().reset_index()
smoker['total_bill'] = [i / j * 100 for i,j in zip(smoker['total_bill'], total['total_bill'])]
total['total_bill'] = [i / j * 100 for i,j in zip(total['total_bill'], total['total_bill'])]

# bar chart 1 -> top bars (group of 'smoker=No')
bar1 = sns.barplot(x="day",  y="total_bill", data=total, color='darkblue')

# bar chart 2 -> bottom bars (group of 'smoker=Yes')
bar2 = sns.barplot(x="day", y="total_bill", data=smoker, color='lightblue')

# add legend
top_bar = mpatches.Patch(color='darkblue', label='smoker = No')
bottom_bar = mpatches.Patch(color='lightblue', label='smoker = Yes')
plt.legend(handles=[top_bar, bottom_bar])

# show the graph
plt.show()