# Cast score attribute as binary 'pass' (0) / 'fail' (1)
y_train = train['score'].apply(lambda x: 0 if x >= 40 else 1)
y_test = test['score'].apply(lambda x: 0 if x >= 40 else 1)
columns = list(X_train)
# Apply SMOTE to the training data
X_train, y_train = SMOTE(random_state=0).fit_resample(X_train, y_train)
X_train = pd.DataFrame(data=X_train, columns=columns)
y_train = pd.Series(y_train)
# Handle duplicate rows by reducing to majority class
if len(X_train) != len(X_train.drop_duplicates()):
# Group training data by matching all attributes (duplicates)
train_groups = X_train.groupby(by=list(X_train))
# Drop duplicate rows in the training data
X_train = X_train.drop_duplicates().copy(deep=True)
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()
