# !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，您希望在边界内显示一组点以强调其重要性。在此示例中，您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。encircle()
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
defencircle(x,y, ax=None, **kw):
ifnot 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)
每个回归线都在自己的列中
或者，您可以在其自己的列中显示每个组的最佳拟合线。你可以通过在里面设置参数来实现这一点。
# 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]), :]
# Each line in its own column
sns.set_style("white")
gridobj = sns.lmplot(x="displ", y="hwy",
data=df_select,
height=7,
robust=True,
palette='Set1',
col="cyl",
scatter_kws=dict(s=60, linewidths=.7, edgecolors='black'))
# Decorations
gridobj.set(xlim=(0.5, 7.5), ylim=(0, 50))
plt.show()
