def fit_dataset(train_data, model, label, fit_args, sample_size=None):
if sample_size is not None and sample_size < len(train_data):
train_data = train_data.sample(n=sample_size, random_state=0)
X = train_data.drop(columns=[label])
y = train_data[label]
problem_type = infer_problem_type(y)
label_cleaner = LabelCleaner.construct(problem_type=problem_type, y=y)
y = label_cleaner.transform(y)
feature_generator = AutoMLPipelineFeatureGenerator()
X = feature_generator.fit_transform(X, y)
X, X_val, y, y_val = generate_train_test_split(
X, y, problem_type=problem_type, test_size=0.2, random_state=0)
model.fit(X=X, y=y, X_val=X_val, y_val=y_val, **fit_args)
return model, label_cleaner, feature_generator
def _infer_problem_type(y: Series, silent=False):
return infer_problem_type(y=y, silent=silent)
def infer_problem_type(y: Series):
return infer_problem_type(y=y)
################
train_data = TabularDataset('https://autogluon.s3.amazonaws.com/datasets/Inc/train.csv') # can be local CSV file as well, returns Pandas DataFrame
test_data = TabularDataset('https://autogluon.s3.amazonaws.com/datasets/Inc/test.csv') # another Pandas DataFrame
label = 'class' # specifies which column do we want to predict
train_data = train_data.head(1000) # subsample for faster demo
#####################################################
# Training custom model outside of TabularPredictor #
#####################################################
# Separate features and labels
X = train_data.drop(columns=[label])
y = train_data[label]
problem_type = infer_problem_type(y=y) # Infer problem type (or else specify directly)
naive_bayes_model = NaiveBayesModel(path='AutogluonModels/', name='CustomNaiveBayes', problem_type=problem_type)
# Construct a LabelCleaner to neatly convert labels to float/integers during model training/inference, can also use to inverse_transform back to original.
label_cleaner = LabelCleaner.construct(problem_type=problem_type, y=y)
y_clean = label_cleaner.transform(y)
naive_bayes_model.fit(X=X, y=y_clean) # Fit custom model
# To save to disk and load the model, do the following:
# load_path = naive_bayes_model.path
# naive_bayes_model.save()
# del naive_bayes_model
# naive_bayes_model = NaiveBayesModel.load(path=load_path)
# Prepare test data
