PyUpsetTest2.py

import pandas as pd
from sklearn.datasets import load_boston
from matplotlib import pyplot as plt
from upsetplot import UpSet

# Load the dataset into a DataFrame
boston = load_boston()
boston_df = pd.DataFrame(boston.data, columns=boston.feature_names)
print(boston_df.head(10))

# Get five features most correlated with median house value
correls = boston_df.corrwith(pd.Series(boston.target),
                             method='spearman').sort_values()
top_features = correls.index[-5:]

# Get a binary indicator of whether each top feature is above average
boston_above_avg = boston_df > boston_df.median(axis=0)
print(boston_df.median(axis=0))
boston_above_avg = boston_above_avg[top_features]
boston_above_avg = boston_above_avg.rename(columns=lambda x: x + '>')
print(boston_above_avg)

# Make this indicator mask an index of boston_df
boston_df = pd.concat([boston_df, boston_above_avg],
                      axis=1)
print(boston_df)
boston_df = boston_df.set_index(list(boston_above_avg.columns))
print(boston_df)
# Also give us access to the target (median house value)
boston_df = boston_df.assign(median_value=boston.target)
print(boston_df)

upset = UpSet(boston_df, subset_size='count', intersection_plot_elements=3,
              orientation='vertical')
upset.add_catplot(value='median_value', kind='strip', color='blue')
upset.add_catplot(value='AGE', kind='strip', color='black')
upset.plot()
plt.title("UpSet with catplots, for orientation='vertical'")
plt.show()