使用seaborn包绘制热图
# library
import seaborn as sns
import pandas as pd
import numpy as np
# Create a dataset
df = pd.DataFrame(np.random.random((5,5)), columns=["a","b","c","d","e"])
df.head()
|
a |
b |
c |
d |
e |
| 0 |
0.285442 |
0.951543 |
0.685812 |
0.924632 |
0.309812 |
| 1 |
0.358051 |
0.686573 |
0.286615 |
0.571409 |
0.224154 |
| 2 |
0.404226 |
0.489562 |
0.848711 |
0.490436 |
0.777601 |
| 3 |
0.244537 |
0.015112 |
0.253332 |
0.405353 |
0.482515 |
| 4 |
0.648074 |
0.593299 |
0.788003 |
0.731065 |
0.197049 |
# Default heatmap: just a visualization of this square matrix
sns.heatmap(df)
image.png
# Create a dataset
df = pd.DataFrame(np.random.random((100,5)), columns=["a","b","c","d","e"])
# Calculate correlation between each pair of variable
# 计算相关性矩阵
corr_matrix=df.corr()
corr_matrix.head()
|
a |
b |
c |
d |
e |
| a |
1.000000 |
0.159442 |
0.124977 |
0.006820 |
-0.164380 |
| b |
0.159442 |
1.000000 |
0.204697 |
0.128948 |
-0.152218 |
| c |
0.124977 |
0.204697 |
1.000000 |
0.013078 |
-0.210332 |
| d |
0.006820 |
0.128948 |
0.013078 |
1.000000 |
-0.066149 |
| e |
-0.164380 |
-0.152218 |
-0.210332 |
-0.066149 |
1.000000 |
# plot it
# 设置cmap参数更改热图颜色
sns.heatmap(corr_matrix, cmap='PuOr')
image.png
# Create a dataset
df = pd.DataFrame(np.random.random((10,10)), columns=["a","b","c","d","e","f","g","h","i","j"])
# plot a heatmap with annotation
# 设置annot=True参数添加文本注释
sns.heatmap(df, annot=True, annot_kws={"size": 7})
image.png
# plot a heatmap with custom grid lines
# 设置linewidths和linecolor参数更改热图边框线的宽度和颜色
sns.heatmap(df, linewidths=2, linecolor='yellow')
image.png
# plot a heatmap
# 设置yticklabels=False参数去掉y轴标签
sns.heatmap(df, yticklabels=False)
image.png
# plot a heatmap
# 设置cbar=False参数去掉图例
sns.heatmap(df, cbar=False)
image.png
# color bar range between 0 and 0.5
# 设置vmin和vmax参数更改图例范围
sns.heatmap(df, cmap="YlGnBu", vmin=0, vmax=0.5)
image.png
# Normalize it by row:
# 对数据按行进行归一化
df_norm_row = df.apply(lambda x: (x-x.mean())/x.std(), axis = 1)
df_norm_row.head()
|
a |
b |
c |
d |
e |
f |
g |
h |
i |
j |
| 0 |
-0.269670 |
0.382143 |
-1.460830 |
1.402933 |
-0.833766 |
-0.245428 |
-1.278216 |
1.171598 |
0.937957 |
0.193277 |
| 1 |
0.474720 |
0.890045 |
-0.607959 |
0.143930 |
-1.703700 |
-0.907119 |
0.459649 |
1.476858 |
0.737861 |
-0.964285 |
| 2 |
-0.848842 |
1.051811 |
-0.548000 |
0.835517 |
1.096437 |
-0.535326 |
-0.951875 |
-0.831628 |
1.553493 |
-0.821587 |
| 3 |
0.095071 |
-1.127515 |
-0.090492 |
0.081681 |
-0.071626 |
-1.829757 |
-0.412118 |
1.650594 |
0.903475 |
0.800687 |
| 4 |
1.600482 |
-0.628712 |
-0.322168 |
-0.625308 |
0.041427 |
1.357510 |
-0.904758 |
-1.389798 |
0.971431 |
-0.100107 |
# And see the result
sns.heatmap(df_norm_row, cmap='viridis')
image.png
# Now if we normalize it by column:
# 对数据按列进行归一化
df_norm_col=(df-df.mean())/df.std()
sns.heatmap(df_norm_col, cmap='viridis')
image.png
对热图添加聚类树
# Libraries
import seaborn as sns
import pandas as pd
from matplotlib import pyplot as plt
# Data set
url = 'c:/Users/Dell/Downloads/mtcars.csv'
df = pd.read_csv(url,index_col=0)
df.head()
|
mpg |
cyl |
disp |
hp |
drat |
wt |
qsec |
vs |
am |
gear |
carb |
| Mazda RX4 |
21.0 |
6 |
160.0 |
110 |
3.90 |
2.620 |
16.46 |
0 |
1 |
4 |
4 |
| Mazda RX4 Wag |
21.0 |
6 |
160.0 |
110 |
3.90 |
2.875 |
17.02 |
0 |
1 |
4 |
4 |
| Datsun 710 |
22.8 |
4 |
108.0 |
93 |
3.85 |
2.320 |
18.61 |
1 |
1 |
4 |
1 |
| Hornet 4 Drive |
21.4 |
6 |
258.0 |
110 |
3.08 |
3.215 |
19.44 |
1 |
0 |
3 |
1 |
| Hornet Sportabout |
18.7 |
8 |
360.0 |
175 |
3.15 |
3.440 |
17.02 |
0 |
0 |
3 |
2 |
# Default plot
sns.clustermap(df)
# Show the graph
plt.show()
image.png
# 进行数据归一化
# Standardize or Normalize every column in the figure
# Standardize:
sns.clustermap(df, standard_scale=1)
plt.show()
image.png
# Normalize
sns.clustermap(df, z_score=1)
plt.show()
image.png
# 设置不同的距离计算方法
# plot with correlation distance
sns.clustermap(df, metric="correlation", standard_scale=1, cmap="PiYG")
plt.show()
image.png
# plot with euclidean distance
sns.clustermap(df, metric="euclidean", standard_scale=1, cmap="PiYG")
plt.show()
image.png
# 设置不同的聚类方法
# linkage method to use for calculating clusters: single
sns.clustermap(df, metric="euclidean", standard_scale=1, method="single", cmap = "Blues")
plt.show()
image.png
In [38]:
# linkage method to use for calculating clusters: ward
sns.clustermap(df, metric="euclidean", standard_scale=1, method="ward", cmap = "Blues")
plt.show()
image.png
# 更改不同的热图颜色
# Change color palette
sns.clustermap(df, metric="euclidean", standard_scale=1, method="ward", cmap="mako")
plt.show()
image.png
sns.clustermap(df, metric="euclidean", standard_scale=1, method="ward", cmap="viridis")
plt.show()
image.png
# 添加行注释信息
# Prepare a vector of color mapped to the 'cyl' column
my_palette = dict(zip(df.cyl.unique(), ["orange","yellow","brown"]))
row_colors = df.cyl.map(my_palette)
row_colors
Mazda RX4 orange
Mazda RX4 Wag orange
Datsun 710 yellow
Hornet 4 Drive orange
Hornet Sportabout brown
Valiant orange
Duster 360 brown
Merc 240D yellow
Merc 230 yellow
Merc 280 orange
Merc 280C orange
Merc 450SE brown
Merc 450SL brown
Merc 450SLC brown
Cadillac Fleetwood brown
Lincoln Continental brown
Chrysler Imperial brown
Fiat 128 yellow
Honda Civic yellow
Toyota Corolla yellow
Toyota Corona yellow
Dodge Challenger brown
AMC Javelin brown
Camaro Z28 brown
Pontiac Firebird brown
Fiat X1-9 yellow
Porsche 914-2 yellow
Lotus Europa yellow
Ford Pantera L brown
Ferrari Dino orange
Maserati Bora brown
Volvo 142E yellow
Name: cyl, dtype: object</pre>
# plot
sns.clustermap(df, metric="correlation", method="single", cmap="Blues", standard_scale=1, row_colors=row_colors)
plt.show()
image.png
网友评论