else:
#le.fit(data[column_names[feature[node]]])
le_name_mapping = mapp[column_names[feature[node]]][0]
#print(le_name_mapping)
names=[k for k,v in le_name_mapping.items() if v >=threshold[node]]
mask += "({} is in {}) \t ".format(column_names[feature[node]], names)
# We insert the & at the right places
mask = mask.replace("\t", "&", mask.count("\t") - 1)
mask = mask.replace("\t", "")
return mask
# COMMAND ----------
import numpy as np
# Leaves
leave_id = clf.apply(df_encoded)
paths ={}
for leaf in np.unique(leave_id):
path_leaf = []
find_path(0, path_leaf, leaf)
paths[leaf] = np.unique(np.sort(path_leaf))
rules_columns = {}
for key in paths:
rules_columns[key] = get_rule2(paths[key], df_encoded.columns)
# COMMAND ----------
rules[7575]
