{"id":28826487,"url":"https://github.com/obinnaokoye89/ecommerce-review-analysis","last_synced_at":"2026-05-10T03:03:16.734Z","repository":{"id":299417558,"uuid":"1002868942","full_name":"ObinnaOkoye89/ecommerce-review-analysis","owner":"ObinnaOkoye89","description":"NLP analysis of e-commerce reviews using OpenAI embeddings","archived":false,"fork":false,"pushed_at":"2025-06-16T12:20:07.000Z","size":271,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-16T13:29:44.626Z","etag":null,"topics":["chromadb","customer-reviews","data-science","llm","nlp","nlp-machine-learning","openai","python","text-embeddings","umap"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ObinnaOkoye89.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-16T09:13:02.000Z","updated_at":"2025-06-16T12:20:10.000Z","dependencies_parsed_at":"2025-06-16T13:41:32.570Z","dependency_job_id":null,"html_url":"https://github.com/ObinnaOkoye89/ecommerce-review-analysis","commit_stats":null,"previous_names":["obinnaokoye89/ecommerce-review-analysis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ObinnaOkoye89/ecommerce-review-analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ObinnaOkoye89%2Fecommerce-review-analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ObinnaOkoye89%2Fecommerce-review-analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ObinnaOkoye89%2Fecommerce-review-analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ObinnaOkoye89%2Fecommerce-review-analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ObinnaOkoye89","download_url":"https://codeload.github.com/ObinnaOkoye89/ecommerce-review-analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ObinnaOkoye89%2Fecommerce-review-analysis/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260676934,"owners_count":23045115,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chromadb","customer-reviews","data-science","llm","nlp","nlp-machine-learning","openai","python","text-embeddings","umap"],"created_at":"2025-06-19T03:04:38.988Z","updated_at":"2026-05-10T03:03:11.706Z","avatar_url":"https://github.com/ObinnaOkoye89.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# E-Commerce Reviews Analysis with Text Embeddings\r\n\r\nWelcome to this project, where we analyze customer reviews from a women's clothing e-commerce dataset using text embeddings. In this project, we:\r\n\r\n- **Create and store text embeddings** for the reviews.\r\n- **Perform dimensionality reduction** to visualize the embeddings in 2D.\r\n- **Categorize feedback** based on keywords (e.g. quality, fit, style, comfort).\r\n- **Implement a similarity search** function to retrieve the closest reviews to a given input.\r\n\r\n---\r\n\r\n## Table of Contents\r\n\r\n- [Overview](#overview)\r\n- [Prerequisites](#prerequisites)\r\n- [Installation](#installation)\r\n- [Dataset](#dataset)\r\n- [Solution Code](#solution-code)\r\n  - [1. Load and Clean the Dataset](#1-load-and-clean-the-dataset)\r\n  - [2. Create and Store the Embeddings](#2-create-and-store-the-embeddings)\r\n  - [3. Dimensionality Reduction \u0026 Visualization](#3-dimensionality-reduction--visualization)\r\n  - [4. Feedback Categorization](#4-feedback-categorization)\r\n  - [5. Similarity Search Function](#5-similarity-search-function)\r\n- [Usage](#usage)\r\n- [License](#license)\r\n\r\n---\r\n\r\n## Overview\r\n\r\nThe goal of this project is to leverage the power of text embeddings and Python libraries to extract insights from customer reviews. We use the **OpenAI API** to generate embeddings for each review in the dataset, then reduce the dimensionality for a 2D visualization using **UMAP**. Next, we identify reviews that mention key topics, and finally, we build a function that finds the most similar reviews to a given text input.\r\n\r\n---\r\n\r\n## Prerequisites\r\n\r\nBefore getting started, ensure you have Python installed (preferably Python 3.8 or later) along with the following Python libraries:\r\n\r\n- `openai==1.3.0`\r\n- `chromadb==0.4.17`\r\n- `pysqlite3-binary==0.5.2`\r\n- `pandas`\r\n- `numpy`\r\n- `umap-learn`\r\n- `matplotlib`\r\n- `scikit-learn`\r\n\r\nAlso, make sure you have set your OpenAI API key as an environment variable. For example, in your terminal or shell:\r\n\r\n```bash\r\nexport OPENAI_API_KEY=your_openai_api_key\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fobinnaokoye89%2Fecommerce-review-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fobinnaokoye89%2Fecommerce-review-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fobinnaokoye89%2Fecommerce-review-analysis/lists"}