Skip to main content

Supercharge your data science workflows with Ollama models

Project description

SMART_PANDAS 🤖 Open In Colab

Supercharge your data science workflows with 🐐 Ollama models.


smart-pandas is a Python library highly inspired by the pandas-gpt, to perform the diverse operations on a pandas DataFrame using llama 2 model.

Installation

First install the ollama from 🐐ollama. Ollama is required and need to be installed must.

pip install smart-pandas

Examples

import pandas as pd
import smart_pandas

df = pd.DataFrame('https://raw.githubusercontent.com/owid/covid-19-data/master/scripts/input/un/handwashing_facilities.csv')

# Data transformation
df = df.ask('Remove iso_code')

# Queries
top_10 = df.ask('what are the top 10 most locations having handwashing_facilities, as a table')

# Plotting
top_10=top_10.ask("Reset index")
top_10.ask('horizontal bar plot, seaborn colors with width 700')

Aurthor

Muntakimur Rahaman

Senior Data Scientist,

Innova-analytics.ai

Contact: muntakim.cse@gmail.com

Alternatives

  • pandas-gpt: OpenAI based pandas auto-completion (Paid api key)
  • GitHub Copilot: General-purpose code completion (paid subscription)
  • Sketch: AI-powered data summarization and code suggestions (works without an API key)

Disclaimer

Please note that the limitations of llama 2 also apply to this library. I would recommend using smart-pandas in a sandboxed environment such as Google Colab, Kaggle, or GitPod.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

smart_pandas-0.0.15.tar.gz (3.2 kB view hashes)

Uploaded Source

Built Distribution

smart_pandas-0.0.15-py3-none-any.whl (3.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page