10 种常用 Matplotlib 图的 Python 代码

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。

柱状图

柱状图有效地传达了项目的排名顺序。但是，在图表上方添加度量标准的值，用户可以从图表本身获取精确信息。

# 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
import matplotlib.patches as patches

fig, ax = plt.subplots(figsize=(16,10), facecolor='white', dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=20)

# Annotate Text
for i, cty in enumerate(df.cty):
    ax.text(i, cty+0.5, round(cty, 1), horizontalalignment='center')


# Title, Label, Ticks and Ylim
ax.set_title('Bar Chart for Highway Mileage', fontdict={'size':22})
ax.set(ylabel='Miles Per Gallon', ylim=(0, 30))
plt.xticks(df.index, df.manufacturer.str.upper(), rotation=60, horizontalalignment='right', fontsize=12)

# Add patches to color the X axis labels
p1 = patches.Rectangle((.57, -0.005), width=.33, height=.13, alpha=.1, facecolor='green', transform=fig.transFigure)
p2 = patches.Rectangle((.124, -0.005), width=.446, height=.13, alpha=.1, facecolor='red', transform=fig.transFigure)
fig.add_artist(p1)
fig.add_artist(p2)
plt.show()

 

棒棒糖图

棒棒糖图表以一种视觉上令人愉悦的方式提供与有序条形图类似的目的。

# 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=(16,10), dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=2)
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()

 

连续变量的直方图

直方图显示给定变量的频率分布。下面的表示基于分类变量对频率条进行分组，从而更好地了解连续变量和串联变量。

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

# Prepare data
x_var = 'displ'
groupby_var = 'class'
df_agg = df.loc[:, [x_var, groupby_var]].groupby(groupby_var)
vals = [df[x_var].values.tolist() for i, df in df_agg]

# Draw
plt.figure(figsize=(16,9), dpi= 80)
colors = [plt.cm.Spectral(i/float(len(vals)-1)) for i in range(len(vals))]
n, bins, patches = plt.hist(vals, 30, stacked=True, density=False, color=colors[:len(vals)])

# Decoration
plt.legend({group:col for group, col in zip(np.unique(df[groupby_var]).tolist(), colors[:len(vals)])})
plt.title(f"Stacked Histogram of ${x_var}$ colored by ${groupby_var}$", fontsize=22)
plt.xlabel(x_var)
plt.ylabel("Frequency")
plt.ylim(0, 25)
plt.xticks(ticks=bins[::3], labels=[round(b,1) for b in bins[::3]])
plt.show()

 

分类变量的直方图

分类变量的直方图显示该变量的频率分布。通过对条形图进行着色，您可以将分布与表示颜色的另一个分类变量相关联。

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

# Prepare data
x_var = 'manufacturer'
groupby_var = 'class'
df_agg = df.loc[:, [x_var, groupby_var]].groupby(groupby_var)
vals = [df[x_var].values.tolist() for i, df in df_agg]

# Draw
plt.figure(figsize=(16,9), dpi= 80)
colors = [plt.cm.Spectral(i/float(len(vals)-1)) for i in range(len(vals))]
n, bins, patches = plt.hist(vals, df[x_var].unique().__len__(), stacked=True, density=False, color=colors[:len(vals)])

# Decoration
plt.legend({group:col for group, col in zip(np.unique(df[groupby_var]).tolist(), colors[:len(vals)])})
plt.title(f"Stacked Histogram of ${x_var}$ colored by ${groupby_var}$", fontsize=22)
plt.xlabel(x_var)
plt.ylabel("Frequency")
plt.ylim(0, 40)
plt.xticks(ticks=bins, labels=np.unique(df[x_var]).tolist(), rotation=90, horizontalalignment='left')
plt.show()

 

散点图

Scatteplot是用于研究两个变量之间关系的经典和基本图。如果数据中有多个组，则可能需要以不同颜色可视化每个组。在Matplotlib，你可以方便地使用。

# Import dataset 
midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")

# Prepare Data 
# Create as many colors as there are unique midwest['category']
categories = np.unique(midwest['category'])
colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))]

# Draw Plot for Each Category
plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')

for i, category in enumerate(categories):
    plt.scatter('area', 'poptotal', 
                data=midwest.loc[midwest.category==category, :], 
                s=20, c=colors[i], label=str(category))

# 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("Scatterplot of Midwest Area vs Population", fontsize=22)
plt.legend(fontsize=12)    
plt.show() 

 

树状图

树状图根据给定的距离度量将相似的点组合在一起，并根据该点的相似性将它们组织成树状链接。

import scipy.cluster.hierarchy as shc

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

# Plot
plt.figure(figsize=(16, 10), dpi= 80)  
plt.title("USArrests Dendograms", fontsize=22)  
dend = shc.dendrogram(shc.linkage(df[['Murder', 'Assault', 'UrbanPop', 'Rape']], method='ward'), labels=df.State.values, color_threshold=100)  
plt.xticks(fontsize=12)
plt.show()

 

人口金字塔

人口金字塔可用于显示按体积排序的组的分布。或者，它也可以用来显示人口的逐步过滤，因为它在下面用于显示有多少人通过营销渠道的每个阶段。

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

# Draw Plot
plt.figure(figsize=(13,10), 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()))]

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()

 

饼图

饼图是显示组组成的经典方法。但是，如今一般不建议使用它，因为馅饼部分的面积有时可能会引起误解。因此，如果要使用饼图，强烈建议明确写下饼图各部分的百分比或数字。

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

# Prepare Data
df = df_raw.groupby('class').size()

# Make the plot with pandas
df.plot(kind='pie', subplots=True, figsize=(8, 8), dpi= 80)
plt.title("Pie Chart of Vehicle Class - Bad")
plt.ylabel("")
plt.show()

 

时间序列图

时间序列图用于可视化给定指标如何随时间变化。在这里，您可以了解1949年至1969年之间的航空客运流量如何变化。

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

# Draw Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.plot('date', 'traffic', data=df, color='tab:red')

# Decoration
plt.ylim(50, 750)
xtick_location = df.index.tolist()[::12]
xtick_labels = [x[-4:] for x in df.date.tolist()[::12]]
plt.xticks(ticks=xtick_location, labels=xtick_labels, rotation=0, fontsize=12, horizontalalignment='center', alpha=.7)
plt.yticks(fontsize=12, alpha=.7)
plt.title("Air Passengers Traffic (1949 - 1969)", fontsize=22)
plt.grid(axis='both', alpha=.3)

# Remove borders
plt.gca().spines["top"].set_alpha(0.0)    
plt.gca().spines["bottom"].set_alpha(0.3)
plt.gca().spines["right"].set_alpha(0.0)    
plt.gca().spines["left"].set_alpha(0.3)   
plt.show()

 

区域图未堆叠

未堆积的面积图用于可视化两个或多个系列相对于彼此的进度（涨跌）。在下面的图表中，您可以清楚地看到随着失业时间的中位数增加，个人储蓄率如何下降。未堆积面积图很好地显示了这种现象。

显示代码

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

# Prepare Data
x = df['date'].values.tolist()
y1 = df['psavert'].values.tolist()
y2 = df['uempmed'].values.tolist()
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange', 'tab:brown', 'tab:grey', 'tab:pink', 'tab:olive']      
columns = ['psavert', 'uempmed']

# Draw Plot 
fig, ax = plt.subplots(1, 1, figsize=(16,9), dpi= 80)
ax.fill_between(x, y1=y1, y2=0, label=columns[1], alpha=0.5, color=mycolors[1], linewidth=2)
ax.fill_between(x, y1=y2, y2=0, label=columns[0], alpha=0.5, color=mycolors[0], linewidth=2)

# Decorations
ax.set_title('Personal Savings Rate vs Median Duration of Unemployment', fontsize=18)
ax.set(ylim=[0, 30])
ax.legend(loc='best', fontsize=12)
plt.xticks(x[::50], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(2.5, 30.0, 2.5), fontsize=10)
plt.xlim(-10, x[-1])

# Draw Tick lines  
for y in np.arange(2.5, 30.0, 2.5):    
    plt.hlines(y, xmin=0, xmax=len(x), colors='black', alpha=0.3, linestyles="--", lw=0.5)

# 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()