見たラベルを追跡できます。
import pylab as plt
xs = [1, 2, 1, 4, 3, 2]
ys = [1, 3, 2, 2, 3, 1]
labels = [1, 1, 0, 2, 1, 3]
label_dict = {0: 'r', 1: 'k', 2: 'b', 3: 'g'}
legend_dict = {0: 'foo', 1: 'bar', 2: 'baz', 3: 'biff'}
seen = set()
for x, y, label in zip(xs, ys, labels):
if label not in seen:
plt.scatter(x, y, c=label_dict.get(label), label=legend_dict.get(label))
else:
plt.scatter(x, y, c=label_dict.get(label))
seen.add(label)
plt.legend()
plt.show()
必要に応じて、if/else句を1行にまとめることができます。
seen = set()
for x, y, label in zip(xs, ys, labels):
plt.scatter(x, y, c=label_dict.get(label), label=legend_dict.get(label) if label not in seen else None)
seen.add(label)
個人的にはデータをグループ化しておくほうがいいと思います。plot
つまり、おそらく同じラベルのすべてのデータを一緒に保存するので、ラベルタイプごとに1つのコマンドを発行するだけで済みます。
import numpy as np
import pylab as plt
xs = [1, 2, 1, 4, 3, 2]
ys = [1, 3, 2, 2, 3, 1]
labels = [1, 1, 0, 2, 1, 3]
xs = np.array(xs)
ys = np.array(ys)
labels = np.array(labels)
labels_masks =( (x,(labels == x)) for x in set(labels))
data_dict = dict( (lbl,(xs[mask],ys[mask])) for lbl,mask in labels_masks )
label_dict = {0: 'r', 1: 'k', 2: 'b', 3: 'g'}
legend_dict = {0: 'foo', 1: 'bar', 2: 'baz', 3: 'biff'}
for label,data in data_dict.items():
x,y = data
plt.scatter(x,y,c=label_dict.get(label),label=legend_dict.get(label))
plt.legend()
plt.show()