Columns Info¶
Imports¶
[1]:
import pandas as pd
import numpy as np
from deepchecks.checks.overview import ColumnsInfo
from deepchecks.base import Dataset
Generating data:¶
[2]:
num_fe = np.random.rand(500)
cat_fe = np.random.randint(3, size=500)
num_col = np.random.rand(500)
date = range(1635693229, 1635693729)
index = range(500)
data = {'index': index, 'date': date, 'a': cat_fe, 'b': num_fe, 'c': num_col, 'label': cat_fe}
df = pd.DataFrame.from_dict(data)
dataset = Dataset(df, label='label', datetime_name='date', index_name='index', features=['a', 'b'], cat_features=['a'])
Running columns_info check:¶
[3]:
check = ColumnsInfo()
[4]:
check.run(dataset=dataset)
Columns Info
Return the role and logical type of each column. Read More...
Additional Outputs
* showing only the top 10 columns, you can change it using n_top_columns param
| index | date | a | b | c | label | |
|---|---|---|---|---|---|---|
| role | index | date | categorical feature | numerical feature | other | label |
[ ]: