https://github.com/swat1563/recommendation-system
This repository features a recommendation system and analytics engine using datasets on users, organizations, contents, contacts, events, and recommendations. It includes data preprocessing, building a recommendation system, and creating visual reports with Power BI.
https://github.com/swat1563/recommendation-system
analytics data-analysis data-visualization engine kaggle numpy pandas powerbi powerbi-dashboards powerbi-desktop powerbi-reports python recommendation-engine recommendation-system recommender-systems scikit-learn scipy
Last synced: about 1 month ago
JSON representation
This repository features a recommendation system and analytics engine using datasets on users, organizations, contents, contacts, events, and recommendations. It includes data preprocessing, building a recommendation system, and creating visual reports with Power BI.
- Host: GitHub
- URL: https://github.com/swat1563/recommendation-system
- Owner: SwAt1563
- Created: 2024-05-18T11:10:02.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-05-27T10:50:23.000Z (11 months ago)
- Last Synced: 2025-02-01T17:44:27.981Z (3 months ago)
- Topics: analytics, data-analysis, data-visualization, engine, kaggle, numpy, pandas, powerbi, powerbi-dashboards, powerbi-desktop, powerbi-reports, python, recommendation-engine, recommendation-system, recommender-systems, scikit-learn, scipy
- Language: Jupyter Notebook
- Homepage:
- Size: 3.36 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Recommendation System and Analytics Engine
## Overview
This repository contains the solution for the skill set assessment task. The task involves creating an analytics engine to produce various reports, insights, and analyses using the provided datasets. The primary goal was to develop a recommendation system based on system scores for multiple users across different categories such as content, contacts, and events.
## Datasets
The datasets provided include:
1. Users
2. Organizations
3. Contents
4. Contacts
5. Events
6. Recommendations
## Task Breakdown
### 1. Data Preprocessing
#### Tools and Libraries
- **Kaggle Platform**
- **Python**
- NumPy
- Pandas
#### Steps and Cleaning
1. **Users Dataset**
- Removed empty columns: `city`, `country`, `state`, `phone_number`, `linkedin_url`, `description`.
2. **Organizations Dataset**
- Removed empty columns: `email`, `year_founded`, `phone_number`, `linkedin_url`.
3. **Contents Dataset**
- Removed empty columns: `organisation_id`, `creator_id`.
- Removed unhelpful column: `content_type` (all records had the same value).
- Cast `id` column from float to integer.
- Removed leading spaces from column names.
- Dropped records without `id` values.
4. **Events Dataset**
- Removed empty column: `organisation_id`.
- Corrected `location` value for `id` 854 from ',' to 'online'.
- Processed the row with `id` 438, which had 68 concatenated records in the `title` field, by identifying the erroneous row, extracting and parsing the concatenated string into individual records, splitting them into 68 distinct rows, reinserting these rows back into the dataset, and verifying the consistency and accuracy of all other fields. As seen in the figure below, all 68 records were originally placed in one row in the `title` field.
- Reformatted `Price` column: converted 'Free' to 0 and string values to float.
- Reformatted `location` into three columns: `meeting`, `state`, `city`.
6. **Contacts Dataset**
- Removed empty columns: `organisation_id`, `picture_name`, `position`, `gender`, `phone_number`.
- Removed unhelpful column: `role_id` (all records had the same value).
7. **Recommendations Dataset**
- Removed empty column: `user_score`.
### 2. Categorizing Recommendations
The recommendations table was divided into three categories based on `asset_type`:
1. **Content Recommendations**
- Renamed `asset_id` to `content_id`.
2. **Event Recommendations**
- Renamed `asset_id` to `event_id`.
3. **Contact Recommendations**
- Renamed `asset_id` to `contact_id`.
### 3. Data Export Post-Cleanup
The cleaned datasets were exported for further use in building the recommendation system and analytics engine.
### 4. Recommendation System
#### Tools and Libraries
- **Kaggle Platform**
- **Python**
- NumPy
- Pandas
- Scikit-learn
- SciPy
#### Methodology
A collaborative filtering recommendation system was developed for content recommendations based on `user_id`, `content_id`, and `system_score`. The `system_score` is assumed to reflect user interactions like clicks or time spent on content. The same algorithm can be applied to events and contacts.
##### Services Provided
1. **User-based Recommendations**
- Input: `user_id`
- Output: Top 5 recommended contents for the user.
2. **Content-based Recommendations**
- Input: `content_id`
- Output: Top 5 contents similar to the provided content.
### 5. Analytics Engine and Visualization
#### Tool
- **Power BI Desktop**
Certainly! Here’s the enhanced format for the reports section:
---
#### Reports
Various reports covering all datasets were created and visualized in Power BI:
1. **Users**
2. **Organizations**
3. **Contents**
4. **Contacts**
5. **Events**
6. **Content Recommendations System**
7. **Contact Recommendations System**
8. **Event Recommendations System**
## Repository Structure
- **Data Wrangling Code:** [Kaggle Notebook](https://www.kaggle.com/code/swat1563/data-wrangling)
- **Content Recommendations System Code:** [Kaggle Notebook](https://www.kaggle.com/code/swat1563/content-recommendations-system)
- **Power BI Reports PDF:** Available in the `reports` directory.
- **Analytics Engine Files:** Power BI files (.pbit, .pbix) for interaction and visualization, available in the repository.
## Links
- **GitHub Repository:** [Recommendation System](https://github.com/SwAt1563/recommendation-system)