abnormal_values_impact_initial_scores.py

# We split the original DataFrame into train and test datasets
X_train, X_test, y_train, y_test = train_test_split(df.drop("Y",axis=1),df["Y"],random_state=22)

# We define the models to benchmark
models = [Lasso(), KNeighborsRegressor(), RandomForestRegressor(), GradientBoostingRegressor()]
# And create the corresponding model's names' list
model_names = []
for model in models: model_names.append(type(model).__name__)

# We record the original score achieved by each model on the "test" set after
# being trained on "train" sets
initial_scores = []

for model_choice in models:
  model_choice.fit(X_train, y_train)
  initial_scores.append(model_choice.score(X_test, y_test))

initial_scores = pd.DataFrame(initial_scores, columns=["Score"], index=model_names)
display(initial_scores)