You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, could you please add support for categorical features in the utils.quantize method? It's crucial for handling large datasets that include categorical data. Here is the code to reproduce the issue:
`import pandas as pd
from catboost.utils import quantize
pool_quantize = quantize(
data_path=filename,
column_description=desc_filename,
delimiter='\t'
)
`
Returned error: CatBoostError: /Users/zomb-ml-platform-msk/go-agent-21.2.0/pipelines/BuildMaster/catboost.git/catboost/libs/data/load_and_quantize_data.cpp:52: Categorical features are not supported in block quantization
The text was updated successfully, but these errors were encountered:
Hello, could you please add support for categorical features in the utils.quantize method? It's crucial for handling large datasets that include categorical data. Here is the code to reproduce the issue:
`import pandas as pd
from catboost.utils import quantize
data = {
'precipitation': [0, 1, 0, 1],
'temperature': [20.5, 22.3, 18.0, 21.6],
'humidity': [85, 60, 78, 75],
'wind_direction': ['north', 'south', 'east', 'west']
}
df = pd.DataFrame(data)
filename = "weather_data.tsv"
df.to_csv(filename, sep='\t', index=False, header=False)
column_descriptions = {
'Index': ['0', '1', '2', '3'],
'Type': ['Label', 'Num', 'Num', 'Categ'],
'Feature': ['precipitation', 'temperature', 'humidity', 'wind_direction']
}
desc_df = pd.DataFrame(column_descriptions)
desc_filename = "columns_description.tsv"
desc_df.to_csv(desc_filename, sep='\t', index=False, header=False)
pool_quantize = quantize(
data_path=filename,
column_description=desc_filename,
delimiter='\t'
)
`
Returned error: CatBoostError: /Users/zomb-ml-platform-msk/go-agent-21.2.0/pipelines/BuildMaster/catboost.git/catboost/libs/data/load_and_quantize_data.cpp:52: Categorical features are not supported in block quantization
The text was updated successfully, but these errors were encountered: