Skip to main content

Natural Language Query Engine for Pandas

Project description




AskEdith logo: AskEdith is a Natural Language Query Engine

Natural Language Query Engine for Pandas

Badge Badge Badge

AskEdith is a data analytics question-answering system that can help you speed up your data analytics workflows. AskEdith converts your natural language questions into SQL queries that are used to return a computed DataFrame.

How It Works

  1. ETL / Ingress - AskEdith ingresses data and parses schema and metadata.
  2. Semantic Search to relate relevant sections of data to the question.
  3. NLP Language Model to convert natural language to SQL.
  4. Execute on input DataFrame and return results.

Installation

pip install askedith

Usage

import pandas as pd
import askedith

# Load Avocados Data (https://figshare.com/articles/dataset/avocado_csv/17696882)
df = pd.read_csv("https://figshare.com/ndownloader/files/35259799")

# Use AskEdith
df = df.askedith.ask("What's the average price for organic avocados?")

print(df)

Examples

Example Example

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

askedith-0.31.2-py3-none-any.whl (7.3 kB view details)

Uploaded Python 3

File details

Details for the file askedith-0.31.2-py3-none-any.whl.

File metadata

  • Download URL: askedith-0.31.2-py3-none-any.whl
  • Upload date:
  • Size: 7.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.8.19

File hashes

Hashes for askedith-0.31.2-py3-none-any.whl
Algorithm Hash digest
SHA256 34847e54072034536932eaafef499493050c99bcbb22f93863000b1ee1607df3
MD5 253a6c393693a70a4c46d06b0e5affa7
BLAKE2b-256 d5a2da8fc7b9230f326bbab5095d5c0a4b877fea2b4c1f7f6bcbbf3b3698b269

See more details on using hashes here.

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