Skip to main content

Lowerated is an opensource library that allows you to rate any item in a statistically accurate way

Project description

Lowerated's Rating Algorithm

Logo

The Best Way to Rate & Recommend Movies

USE IT HERE LM6 DeBERTa Lowerated Data YouTube Playlist


  • An algorithm that provides accurate ratings for any entity.
  • Uses diverse sources: reviews, links, documents, and other resources.
  • Completely unbiased.
  • Combines AI and human evaluation to determine the true rating of an entity.

What is an Entity?

  • Anything that can be rated.
  • Examples include films, cars, books, music, furniture, even your partner.
  • In the case of Lowerated, we're dealing with "Movies".

How Does It Work?

  • We have predefined research attributes that, when measured, give a comprehensive understanding of the item. Let's use a movie as an example.

Movie Rating Attributes

We evaluate a movie based on seven attributes:

  1. Cinematography - Visual appeal and camera work.
  2. Direction - How well the director conveys the story.
  3. Story - Plot coherence and engagement.
  4. Characters - Depth and development of characters.
  5. Production Design - Quality of the sets and overall look.
  6. Unique Concept - Originality of the idea.
  7. Emotions - Emotional impact on the audience.

We gather reviews from multiple critics and users. Our AI extracts information from the text inputs and assigns numerical values to each attribute. This process is repeated for all reviews, and we average the results.

Each attribute is given a percentage value from 0-100%, reflecting its presence in the movie.

We have identified key attributes for multiple entities, detailed in the listed Entities & Attributes.

How do I use it?

Check out the steps to use Lowerated here.

Prerequisites

Before using the Entity class, ensure you have the required libraries installed:

  • lowerated

You can install these libraries using pip:

pip install lowerated

Setup

  1. Import the necessary modules and classes:
from lowerated.rate import Entity
from lowerated.rate.utils import entities, find_attributes
  1. Define the Entity class with its methods.

Usage

See Available Entities & their Attributes

Get a list of available entities and their attributes:

entities = entities()
print(entities)

To see a specific entity's attributes, use the code below:

entity_name = "Movie"
attributes = find_attributes(entity_name)
print(attributes)

Initializing an Available Entity or Creating a Custom Entity

Create an instance of the Entity class by specifying the entity name and optionally its attributes:

entity_name = "Movie"
attributes = ['Cinematography', 'Direction', 'Story', 'Characters', 'Production Design', 'Unique Concept', 'Emotions']
movie_entity = Entity(entity_name, attributes)

Example 1: Using a List of Reviews

Rate the attributes of an entity using a list of textual reviews:

reviews_list = ["Great movie!", "Not worth the price.", "Excellent cinematography."]
rating = movie_entity.rate(reviews=reviews_list)
print(rating)

Example 2: Using a File Path

Rate the attributes of an entity using a file containing reviews. Supported file formats are CSV, Excel (XLSX), and TXT.

file_path = "reviews.csv"  # Can be .csv, .xlsx, or .txt
rating = movie_entity.rate(file_path=file_path)
print(rating)

Example 3: Using a Download Link

Rate the attributes of an entity using a URL to download the file containing reviews:

download_link = "https://example.com/reviews.xlsx"  # Can be .csv, .xlsx, or .txt
rating = movie_entity.rate(download_link=download_link)
print(rating)

License

Apache 2.0

Copyright (2024) FACT-RATED MEDIA (PVT-LTD)

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

lowerated-0.3.4.tar.gz (21.7 kB view details)

Uploaded Source

Built Distribution

lowerated-0.3.4-py3-none-any.whl (21.4 kB view details)

Uploaded Python 3

File details

Details for the file lowerated-0.3.4.tar.gz.

File metadata

  • Download URL: lowerated-0.3.4.tar.gz
  • Upload date:
  • Size: 21.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.5

File hashes

Hashes for lowerated-0.3.4.tar.gz
Algorithm Hash digest
SHA256 f183dcd09612958c0526e546ad6754033fd340fe8d32228160c09a3c07212f13
MD5 7df22d4ff08ab7cd80e5cbb1382a0201
BLAKE2b-256 183d93c58e4005b06d87bd95d902ab4ff8a84cc9b80e031b7723cbe092315eb4

See more details on using hashes here.

File details

Details for the file lowerated-0.3.4-py3-none-any.whl.

File metadata

  • Download URL: lowerated-0.3.4-py3-none-any.whl
  • Upload date:
  • Size: 21.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.5

File hashes

Hashes for lowerated-0.3.4-py3-none-any.whl
Algorithm Hash digest
SHA256 93ca4c9c5852119abaff2b372152b21a68641c317d687b8a89b8935ab7dfff7f
MD5 9c610fc2cad20a8cd430fdde291a9fcd
BLAKE2b-256 36800d3ddfa967ce3018edd07786053f56c327fad2e4f71d432b6e96c9bb8c2d

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