run_test = False
if run_test:
data_path = "/Users/magnus/Documents/02_PhD/03_Newsvendor_foundation_model/experiments/datasets/raw/kaggle_m5"
if data_path is not None:
loader = KaggleM5DatasetLoader(data_path, overwrite=False, product_as_feature=False)
demand, SKU_features, time_features, time_SKU_features, mask = loader.load_dataset()INFO:root:Using existing data from disk
INFO:root:Importing data
INFO:root:Preprocessing data
INFO:root:--Creating catogory mapping and features
INFO:root:--Preparing sales time series data
INFO:root:--Preparing calendric information
INFO:root:--Preparing snap features
INFO:root:--Preparing price information
INFO:root:--Creating indicator table if products are available for purchase
INFO:root:--Preparing final outputs and ensure consistency of time and feature dimensions HOBBIES_1_001_CA_1 HOBBIES_1_002_CA_1 HOBBIES_1_003_CA_1 \
0 0 0 0
1 0 0 0
2 0 0 0
3 0 0 0
4 0 0 0
... ... ... ...
1936 0 0 0
1937 3 0 2
1938 3 0 3
1939 0 0 0
1940 1 0 1
HOBBIES_1_004_CA_1 HOBBIES_1_005_CA_1 HOBBIES_1_006_CA_1 \
0 0 0 0
1 0 0 0
2 0 0 0
3 0 0 0
4 0 0 0
... ... ... ...
1936 1 0 0
1937 3 0 0
1938 0 2 5
1939 2 1 2
1940 6 0 0
HOBBIES_1_007_CA_1 HOBBIES_1_008_CA_1 HOBBIES_1_009_CA_1 \
0 0 12 2
1 0 15 0
2 0 0 7
3 0 0 3
4 0 0 0
... ... ... ...
1936 1 5 0
1937 0 4 0
1938 1 1 0
1939 1 40 1
1940 0 32 0
HOBBIES_1_010_CA_1 ... FOODS_3_818_WI_3 FOODS_3_819_WI_3 \
0 0 ... 0 14
1 0 ... 0 11
2 1 ... 0 5
3 0 ... 0 6
4 0 ... 0 5
... ... ... ... ...
1936 1 ... 3 6
1937 1 ... 1 4
1938 0 ... 3 4
1939 0 ... 0 1
1940 1 ... 0 1
FOODS_3_820_WI_3 FOODS_3_821_WI_3 FOODS_3_822_WI_3 FOODS_3_823_WI_3 \
0 1 0 4 0
1 1 0 4 0
2 1 0 2 2
3 1 0 5 2
4 1 0 2 0
... ... ... ... ...
1936 3 0 0 1
1937 3 1 2 0
1938 3 1 1 0
1939 0 0 3 1
1940 1 4 4 1
FOODS_3_824_WI_3 FOODS_3_825_WI_3 FOODS_3_826_WI_3 FOODS_3_827_WI_3
0 0 0 0 0
1 0 6 0 0
2 0 0 0 0
3 0 2 0 0
4 0 2 0 0
... ... ... ... ...
1936 0 1 0 0
1937 1 0 1 2
1938 0 1 1 2
1939 1 0 1 5
1940 0 2 0 1
[1941 rows x 30490 columns]