mode_labels = {}
# Loop through each unique (non-duplicate) row
for unique_row in train_groups.groups.keys():
# Retrieve all labels for a given row and its duplicates
group_labels = y_train.loc[train_groups.groups[unique_row]]
# Record the majority class for each unique row
mode_labels[unique_row] = group_labels.value_counts().idxmax()
# Reduce training labels to match training data indices
y_train = y_train.loc[X_train.index]
# Set the appropriate training labels to the majority class
for index, row in X_train.iterrows():
y_train[index] = mode_labels[tuple(row.tolist())]
km = None
# Initialize K-Means object and set number of clusters for edge cases
num_rows = len(X_train)
if num_rows <= 8:
km = KMeans(n_clusters=(int(num_rows**0.5)),
random_state=0,
n_jobs=-1)
else:
km = KMeans(random_state=0, n_jobs=-1)
# Fit the K-Means object to the training data
