Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/mehrab-kalantari/sms-spam-classifier

Building spam classifier using different algorithms and choosing the best one to build a streamlit application
https://github.com/mehrab-kalantari/sms-spam-classifier

classification english-nlp imbalanced-learning machine-learning nlp streamlit supervised-learning voting-classifier

Last synced: 4 days ago
JSON representation

Building spam classifier using different algorithms and choosing the best one to build a streamlit application

Host: GitHub
URL: https://github.com/mehrab-kalantari/sms-spam-classifier
Owner: Mehrab-Kalantari
Created: 2023-08-01T15:52:26.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2023-09-01T09:46:32.000Z (over 1 year ago)
Last Synced: 2024-11-15T21:14:16.473Z (2 months ago)
Topics: classification, english-nlp, imbalanced-learning, machine-learning, nlp, streamlit, supervised-learning, voting-classifier
Language: Jupyter Notebook
Homepage:
Size: 1.45 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

# SMS Spam Classifier
[Dataset on kaggle](https://www.kaggle.com/datasets/uciml/sms-spam-collection-dataset?resource=download)

## Contents
### Data cleaning
* Drop null columns
* Drop duplicates
* Label encoding
* Drop NaN values

### Data understanding and EDA
* Pie chart
* Bar chart
* Histogram
* Pair plot
* Correlation matrix

### Data preprocessing
* To lower case
* Tokenization
* Removing special characters
* Removing stopwords and punctuation
* Stemming

### Modeling
* Single classifiers
* Voting classifier

### Evaluation
Here we choose the best model from the following measures
* Accuracy
* Precision
* F1 score

![models](/sample/models.png)

### Deployment
Deploy our model on streamlit

---
### Sample
![s](sample/sample.jpg)