Real-Time Tweets Sentiment Analysis Package
Overview
Retrieving real-time tweets using twitter API, Apache Kafka, and Apache Spark Streaming; then, using tensorflow deep learning model to classify the tweets wether they positive, negative, or neutral; all in a pypi package.
TweetsAnalysis
The streamer and model package, available on pypi TweetsAnalysis
Package Requirements
- gensim
- pandas
- pyspark
- kafka-python
- streamlit
- scikit-learn
- seaborn
- tensorflow
- tweepy==3.9.0
- pydantic
- strictyaml
- joblib
Model
The model architecture:
The model results in about 85.5% in the train set and 84.4% accuracy on the test set, which has 160000 tweets; therefore, there is no over-fitting here.
Run
First we need to install the requirements with:
pip install TweetsAnalysis
To train the model run, but first we need to specifiy the model and data directories in the config file:
python train_model.py
Straming
Start kafka with:
bin/zookeeper-server-start.sh config/zookeeper.properties
bin/kafka-server-start.sh config/server.properties
then create a kafka topic (tweets_stream) with:
bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic tweets_stream
Metadata
Release files for TweetsAnalysis 1.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| TweetsAnalysis-1.1.8.tar.gz | 17.5 kB | Without provenance | Details for TweetsAnalysis-1.1.8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| TweetsAnalysis-1.1.8-py3-none-any.whl | Python 3 | none | any | Details for TweetsAnalysis-1.1.8-py3-none-any.whl |
Total release size: 29.8 kB
Release files / TweetsAnalysis-1.1.8.tar.gz
| Download URL | TweetsAnalysis-1.1.8.tar.gz |
|---|---|
| Size | 17.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
20a1c7b990a13e665c06353f61847369f5409a07ebcbec681e2045961253248d
|
|
BLAKE2b-256 checksum How to use checksums |
9d0ff6a5368294edc7dec5c3db38a8c044367d1773cf90062f20fe67619179e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.10.4
|
Release files / TweetsAnalysis-1.1.8-py3-none-any.whl
| Download URL | TweetsAnalysis-1.1.8-py3-none-any.whl |
|---|---|
| Size | 12.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
62f1fbc34d64967055fad4d9cd11ed3ad4b68e3b86952f9720d42188752f736e
|
|
BLAKE2b-256 checksum How to use checksums |
bf3a916e9f6a58a574ab9f8d061518571ba259011037aead55fd69d20d5e6269
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.10.4
|
Security for TweetsAnalysis 1.1.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.