def get_data_metadata(X: DataFrame, y: Series) -> dict:
X_raw = convert_to_raw(X)
feature_metadata_orig = FeatureMetadata.from_df(X)
feature_metadata_raw = FeatureMetadata.from_df(X_raw)
num_rows, num_cols = X.shape
num_null = X.isnull().sum().sum()
try:
problem_type = infer_problem_type(y, silent=True)
except:
# TODO: Remove, only here for legacy compatibility
problem_type = infer_problem_type(y)
if problem_type in ['binary', 'multiclass']:
num_classes = len(y.unique())
else:
num_classes = None
data_metadata = {
'num_rows': num_rows,
'num_cols': num_cols,
'num_null': num_null,
'num_classes': num_classes,
'problem_type': problem_type,
'feature_metadata': feature_metadata_orig,
'feature_metadata_raw': feature_metadata_raw,
}
# TODO: class imbalance
# TODO: has_text
# TODO: has_special
# TODO: memory size
return data_metadata
################ train_data = task.Dataset(file_path='https://autogluon.s3.amazonaws.com/datasets/Inc/train.csv') # can be local CSV file as well, returns Pandas DataFrame test_data = task.Dataset(file_path='https://autogluon.s3.amazonaws.com/datasets/Inc/test.csv') # another Pandas DataFrame label_column = 'class' # specifies which column do we want to predict train_data = train_data.head(1000) # subsample for faster demo ############################################# # Training custom model outside of task.fit # ############################################# # Separate features and labels X_train = train_data.drop(columns=[label_column]) y_train = train_data[label_column] problem_type = infer_problem_type(y=y_train) # 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_train) y_train_clean = label_cleaner.transform(y_train) naive_bayes_model.fit(X_train=X_train, y_train=y_train_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