在散点图上添加颜色条标签作为文本

Question

I have a scatter plot generated using:

x = list(auto['umap1'])
y = list(auto['umap2'])


final_df2 = pd.DataFrame(list(zip(x,y,communities)), columns =['x', 'y', 'cluster'])
no_clusters = max(communities)
cluster_list = list(range (min(communities), no_clusters+1))
fig2, ax = plt.subplots(figsize = (20,15))
plt.scatter(x,y, c=final_df2['cluster'], cmap=plt.cm.get_cmap('hsv', max(cluster_list)), s = 0.5)
plt.title('Phenograph on UMAP - All Markers (auto)', fontsize=15)
plt.xlabel('umap_1', fontsize=15)
plt.ylabel('umap_2', fontsize=15)
plt.colorbar(extend='both',ticks = range(max(cluster_list)))
plt.show()

I wanted to know how can I add the colorbar labels (numbers from 1-31) to the actual clusters on the graph (as text) that each one corresponds to. This is because it is quite hard to tell this from the colours as they loop back to red.

I tried:

n = list(final_df2['cluster'])
for i, txt in enumerate(n):
    ax.annotate(txt, (y[i], x[i]))

But this is giving me no luck.

Answer 1

Your code for the annotations is writing an annotation for each and every dot. This just ends in a sea of numbers.

Somehow, you should find a kind of center for each cluster, for example by averaging all the points that belong to the same cluster.

Then, you use the coordinates of the center to position the text. You can give it a background to make it easier to read.

As I don't have your data, the code below simulates some points already around a center.

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np

# calculate some random points to serve as cluster centers; run a few steps of a relaxing algorithm to separate them a bit
def random_distibuted_centers():
    cx = np.random.uniform(-10, 10, MAX_CLUST + 1)
    cy = np.random.uniform(-10, 10, MAX_CLUST + 1)
    for _ in range(10):
        for i in range(1, MAX_CLUST + 1):
            for j in range(1, MAX_CLUST + 1):
                if i != j:
                    dist = np.linalg.norm([cx[i] - cx[j], cy[i] - cy[j]])
                    if dist < 4:
                        cx[i] += 0.4 * (cx[i] - cx[j]) / dist
                        cy[i] += 0.4 * (cy[i] - cy[j]) / dist
    return cx, cy

N = 1000
MAX_CLUST = 31
cx, cy = random_distibuted_centers()

# for demonstration purposes, just generate some random points around the centers
x =  np.concatenate( [np.random.normal(cx[i], 2, N) for i in range(1,MAX_CLUST+1)])
y =  np.concatenate( [np.random.normal(cy[i], 2, N) for i in range(1,MAX_CLUST+1)])
communities = np.repeat(range(1,MAX_CLUST+1), N)

final_df2 = pd.DataFrame({'x':x, 'y':y, 'cluster': communities})
no_clusters = max(communities)
cluster_list = list(range (min(communities), no_clusters+1))
fig2, ax = plt.subplots(figsize = (20,15))
plt.scatter(x,y, c=final_df2['cluster'], cmap=plt.cm.get_cmap('hsv', max(cluster_list)), s=0.5)
plt.title('Phenograph on UMAP - All Markers (auto)', fontsize=15)
plt.xlabel('umap_1', fontsize=15)
plt.ylabel('umap_2', fontsize=15)
plt.colorbar(extend='both',ticks = cluster_list)

bbox_props = dict(boxstyle="circle,pad=0.3", fc="white", ec="black", lw=2, alpha=0.9)
for i in range(1,MAX_CLUST+1):
    ax.annotate(i, xy=(cx[i], cy[i]), ha='center', va='center', bbox=bbox_props)
plt.show()