15个Matplotlib常用Python绘图代码

大家好，今天分享给大家15个Matplotlib图的汇总，在数据分析和可视化中非常有用，文章较长，可以收藏下来练手。

# !pip install brewer2mpl
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
import warnings; warnings.filterwarnings(action='once')

large = 22; med = 16; small = 12
params = {'axes.titlesize': large,
          'legend.fontsize': med,
          'figure.figsize': (16, 10),
          'axes.labelsize': med,
          'axes.titlesize': med,
          'xtick.labelsize': med,
          'ytick.labelsize': med,
          'figure.titlesize': large}
plt.rcParams.update(params)
plt.style.use('seaborn-whitegrid')
sns.set_style("white")
%matplotlib inline

# Version
print(mpl.__version__)  #> 3.0.0
print(sns.__version__)  #> 0.9.0

1.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()    

2.带边界的气泡图

有时，你希望在边界内显示一组点以强调其重要性。在此示例中，你将从应该被环绕的数据帧中获取记录，并将其传递给下面的代码中描述的记录。

from matplotlib import patches
from scipy.spatial import ConvexHull
import warnings; warnings.simplefilter('ignore')
sns.set_style("white")

# 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.tab10(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=(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='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):
    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_data = midwest.loc[midwest.state=='IN', :]                         

# Draw polygon surrounding vertices    
encircle(midwest_encircle_data.area, midwest_encircle_data.poptotal, ec="k", fc="gold", alpha=0.1)
encircle(midwest_encircle_data.area, midwest_encircle_data.poptotal, ec="firebrick", fc="none", linewidth=1.5)

# 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()    

3.带线性回归最佳拟合线的散点图

如果你想了解两个变量如何相互改变，那么最合适的线就是要走的路。下图显示了数据中各组之间最佳拟合线的差异。要禁用分组并仅为整个数据集绘制一条最佳拟合线，请从下面的调用中删除该参数。

# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/mpg_ggplot2.csv")
df_select = df.loc[df.cyl.isin([4,8]), :]

# Plot
sns.set_style("white")
gridobj = sns.lmplot(x="displ", y="hwy", hue="cyl", data=df_select, 
                     height=7, aspect=1.6, robust=True, palette='tab10', 
                     scatter_kws=dict(s=60, linewidths=.7, edgecolors='black'))

# Decorations
gridobj.set(xlim=(0.5, 7.5), ylim=(0, 50))
plt.title("Scatterplot with line of best fit grouped by number of cylinders", fontsize=20)

4.抖动图

通常，多个数据点具有完全相同的X和Y值，多个点相互绘制并隐藏。为避免这种情况，请稍微抖动点，以便你可以直观地看到它们。

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

# Draw Stripplot
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)    
sns.stripplot(df.cty, df.hwy, jitter=0.25, size=8, ax=ax, linewidth=.5)

# Decorations
plt.title('Use jittered plots to avoid overlapping of points', fontsize=22)
plt.show()

5.计数图

避免点重叠问题的另一个选择是增加点的大小，这取决于该点中有多少点。因此，点的大小越大，周围的点的集中度就越大。

# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/mpg_ggplot2.csv")
df_counts = df.groupby(['hwy', 'cty']).size().reset_index(name='counts')

# Draw Stripplot
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)    
sns.stripplot(df_counts.cty, df_counts.hwy, size=df_counts.counts*2, ax=ax)

# Decorations
plt.title('Counts Plot - Size of circle is bigger as more points overlap', fontsize=22)
plt.show()

6.边缘直方图

边缘直方图具有沿X和Y轴变量的直方图。这用于可视化X和Y之间的关系以及单独的X和Y的单变量分布。该图如果经常用于探索性数据分析。

# 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)

# 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*4, c=df.manufacturer.astype('category').cat.codes, alpha=.9, data=df, cmap="tab10", edgecolors='gray', linewidths=.5)

# histogram on the right
ax_bottom.hist(df.displ, 40, histtype='stepfilled', orientation='vertical', color='deeppink')
ax_bottom.invert_yaxis()

# histogram in the bottom
ax_right.hist(df.hwy, 40, histtype='stepfilled', orientation='horizontal', color='deeppink')

# Decorations
ax_main.set(title='Scatterplot with Histograms 
 displ vs hwy', xlabel='displ', ylabel='hwy')
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)

xlabels = ax_main.get_xticks().tolist()
ax_main.set_xticklabels(xlabels)
plt.show()

7.边缘箱形图

边缘箱图与边缘直方图具有相似的用途。然而，箱线图有助于精确定位X和Y的中位数，第25和第75百分位数。

# 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)

# 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")
sns.boxplot(df.displ, ax=ax_bottom, orient="h")

# 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 
 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()

8.相关图

Correlogram用于直观地查看给定数据帧（或2D数组）中所有可能的数值变量对之间的相关度量。

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

# Plot
plt.figure(figsize=(12,10), dpi= 80)
sns.heatmap(df.corr(), xticklabels=df.corr().columns, yticklabels=df.corr().columns, cmap='RdYlGn', center=0, annot=True)

# Decorations
plt.title('Correlogram of mtcars', fontsize=22)
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
plt.show()

9.矩阵图

成对图是探索性分析中的最爱，以理解所有可能的数字变量对之间的关系。它是双变量分析的必备工具。

# Load Dataset
df = sns.load_dataset('iris')

# Plot
plt.figure(figsize=(10,8), dpi= 80)
sns.pairplot(df, kind="scatter", hue="species", plot_kws=dict(s=80, edgecolor="white", linewidth=2.5))
plt.show()

# Load Dataset
df = sns.load_dataset('iris')

# Plot
plt.figure(figsize=(10,8), dpi= 80)
sns.pairplot(df, kind="reg", hue="species")
plt.show()

10.发散型条形图

如果你想根据单个指标查看项目的变化情况，并可视化此差异的顺序和数量，那么发散条是一个很好的工具。它有助于快速区分数据中组的性能，并且非常直观，并且可以立即传达这一点。

# 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=(14,10), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z, color=df.colors, alpha=0.4, linewidth=5)

# Decorations
plt.gca().set(ylabel='$Model$', xlabel='$Mileage$')
plt.yticks(df.index, df.cars, fontsize=12)
plt.title('Diverging Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.show()

11.发散型文本

分散的文本类似于发散条，如果你想以一种漂亮和可呈现的方式显示图表中每个项目的价值，可以使用。

# 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=(14,14), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z)
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':'red' if x < 0 else 'green', '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()