how should i do when i use my data using dataframe not loaded csv file?

[heemokyim]

for example,

from entity_embeddings import Config, Embedder, TargetType
from entity_embeddings.util import visualization_utils

df=pd.read_csv('test_file.csv')

config = Config.make_default_config(df,
target_name='churn',
target_type=TargetType.BINARY_CLASSIFICATION,
train_ratio=0.8,
epochs=10,
verbose=True,
artifacts_path='artifacts')

embedder = Embedder(config)
embedder.perform_embedding()

[rodrigobressan]

Hello @heemokyim, thanks for the question. At this moment we're only accepting the path of the csv file.

If you need the DataFrame to be used as parameter, I can look into implementing it in the following weeks, or if you need it sooner, feel free to submit a pull request with the implementation. Certainly it would be welcome to the project.

In short, you just need to add a new initializer into the Config class (config.py file) with the pandas DataFrame instead of the csv file path.

If you have any further questions, please do not hesitate to ask.