mirror of
https://github.com/holodata/sensai-dataset.git
synced 2025-03-15 12:00:32 +09:00
3.9 KiB
3.9 KiB
In [2]:
import pandas as pd
from os.path import join
import os
from glob import glob
DATASET_DIR = os.environ.get("DATASET_DIR", "../input/sensai")
print("DATASET_DIR", DATASET_DIR)
In [3]:
df = pd.concat(
[pd.read_parquet(x) for x in glob(join(DATASET_DIR, '*.parquet'))],
ignore_index=True)
df.info()
In [11]:
df.sample(5)
Out[11]:
In [ ]: