https://github.com/abdoufermat5/text-mining-reviews
Sentiment Analysis on amazon reviews
https://github.com/abdoufermat5/text-mining-reviews
classification data-mining data-science machine-learning python sentiment-analysis
Last synced: about 1 month ago
JSON representation
Sentiment Analysis on amazon reviews
- Host: GitHub
- URL: https://github.com/abdoufermat5/text-mining-reviews
- Owner: abdoufermat5
- Created: 2023-01-02T00:57:53.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-10T05:00:36.000Z (over 3 years ago)
- Last Synced: 2025-02-27T07:25:45.981Z (over 1 year ago)
- Topics: classification, data-mining, data-science, machine-learning, python, sentiment-analysis
- Language: HTML
- Homepage:
- Size: 52.1 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Unlocked Phone Reviews amazon
## clone this repo
```git clone https://github.com/abdoufermat5/text-mining-reviews ```
## Simple way to run the app
If you have docker and docker compose installed,
you can run the app with the following command:
```docker compose up --build -d```
Then go to [http://localhost:8501](http://localhost:8501)
#### if not started rerun the command again
If you don't have docker, you can run the app with the following steps:
## install dependencies
```bash pip install -r requirements.txt ```
## download the dataset from kaggle
PS: You don't really need to do this step, because the dataset is already stored in a mongoDB cluster
> [https://www.kaggle.com/datasets/PromptCloudHQ/amazon-reviews-unlocked-mobile-phones](https://www.kaggle.com/datasets/PromptCloudHQ/amazon-reviews-unlocked-mobile-phones)
Then move the csv file to the **data/** folder
## notebooks
>- notebooks/stats_on_other_features.ipynb
> > here we explore the other features of the dataset
>
>- notebooks/preprocessing.ipynb
> >here we preprocess the data
>
>- notebooks/model.ipynb
> > here we build different models and compare them
## streamlit app
We've built a streamlit app to make it easier to understand the data and the models
To run the streamlit app
> go to the deploy folder
> ```cd deploy ```
>
> install local package fermat-helpers
> ```pip install . ```
>
> run the app
> ```bash streamlit run Accueil.py ```
>
> go to the url displayed in the terminal
> [http://localhost:8501](http://localhost:8501)
## Some screenshots of the app
- Visualisation of the data and Stats
- Preprocessing page
- Exploring the models
- Predictions
