Sinaptik-AI / pandas-ai

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
https://pandas-ai.com
Other
13.01k stars 1.25k forks source link

Feature generation #1363

Open abrichr opened 1 month ago

abrichr commented 1 month ago

🚀 The feature

Hello, it says at https://docs.pandas-ai.com/intro:

Feature generation: Enhance data quality through feature generation.

Where can I find out more about this feature?

Thank you 🙏

Motivation, pitch

I'm interested in understanding the extent to which Pandas AI can work with unstructured data.

Alternatives

No response

Additional context

No response

dosubot[bot] commented 1 month ago

Hey @abrichr! I'm here to help you with any bugs, questions, or contributions you have. If you need any assistance, feel free to ask.

You can find out more about feature generation in PandasAI and its ability to work with unstructured data in the "Introduction to PandasAI" documentation. Specifically, the documentation mentions:

Additionally, the pandasai/helpers/shortcuts.py file provides a method for feature generation:

def generate_features(self) -> DataFrameType:
    """
    Do feature generation and return the dataframe.

    Returns:
        DataFrameType: The DataFrame with generated features.
    """

    return self.chat(
        """
1. Copy the dataframe to a new variable named df_features.
2. Do feature generation.
3. Return df_features.
"""
    )

For more detailed information, you can refer to the library documentation and the platform documentation [1][2].

To continue talking to Dosu, mention @dosu.