]
if args.dataset == 'kkbox_v2':
df_test = df_train.sample(frac=0.25)
df_train = df_train.drop(df_test.index)
df_val = df_train.sample(frac=0.1)
df_train = df_train.drop(df_val.index)
elif not (args.dataset == 'kkobx'):
df_test = df_train.sample(frac=0.2)
df_train = df_train.drop(df_test.index)
df_val = df_train.sample(frac=0.2)
df_train = df_train.drop(df_val.index)
standardize = [([col], StandardScaler()) for col in cols_standardize]
leave = [(col, None) for col in cols_leave]
categorical = [(col, OrderedCategoricalLong()) for col in cols_categorical]
x_mapper_float = DataFrameMapper(standardize + leave)
x_mapper_long = DataFrameMapper(categorical)
x_fit_transform = lambda df: tt.tuplefy(
x_mapper_float.fit_transform(df).astype(np.float32),
x_mapper_long.fit_transform(df))
x_transform = lambda df: tt.tuplefy(
x_mapper_float.transform(df).astype(np.float32),
x_mapper_long.transform(df))
x_train = x_fit_transform(df_train)
x_val = x_transform(df_val)
x_test = x_transform(df_test)
num_embeddings = x_train[1].max(0) + 1
df_train.columns = [
"x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7", "duration", "event"
]
cols_standardize = ["x0", "x3", "x4", "x6"]
cols_leave = ["x1", "x7"]
cols_categorical = ["x2", "x5"]
if len(cols_categorical) > 0:
num_embeddings = [
len(df_train[cat].unique()) + 1 for cat in cols_categorical
]
embedding_dims = [math.ceil(n_emb / 2) for n_emb in num_embeddings]
standardize = [([col], StandardScaler()) for col in cols_standardize]
leave = [(col, None) for col in cols_leave]
categorical = [(col, OrderedCategoricalLong())
for col in cols_categorical]
x_mapper_float = DataFrameMapper(standardize + leave)
x_mapper_long = DataFrameMapper(categorical)
x_fit_transform = lambda df: tt.tuplefy(
x_mapper_float.fit_transform(df).astype(np.float32),
x_mapper_long.fit_transform(df))
x_transform = lambda df: tt.tuplefy(
x_mapper_float.transform(df).astype(np.float32),
x_mapper_long.transform(df))
else:
standardize = [([col], StandardScaler()) for col in cols_standardize]
leave = [(col, None) for col in cols_leave]
x_mapper = DataFrameMapper(standardize + leave)
