import pandas as pd
import numpy as np

#read the dataset
data = np.load('x20data.npz')

df = pd.DataFrame(data['data'])
df['target'] = data['label']
df['target'] = df['target'].replace(-1,0)

#lets plot class distribution
df['target']
.value_counts(normalize=True)
.plot
.bar(figsize=(10,6),alpha=0.6)

plt.xlabel("Label")
plt.ylabel("Distribution %")
plt.yticks(list(np.linspace(0,1,11)))
plt.grid(True)
plt.show()