I have built a model which will predict the sentiment of movie reviews. I used Naive-Bayes, SVM, and RNN+LSTM based model to obtain really good result.
- Python 2.7
- pandas
- numpy
- scipy
- scikit-learn
- matplotlib
- jupyter notebook
- TensorFlow
- Keras
I'm working on Linux OS (Ubuntu 16.04 LTS) so command for installation all dependencies are given below.
Pandas: $ sudo pip install pandas
numpy: $ sudo pip install numpy
scipy: $ sudo pip install scipy
scikit-learn: $ sudo pip install -U scikit-learn
matplotlib:
$ sudo apt-get install libfreetype6-dev libpng-dev
$ sudo pip install matplotlib
jupyter notebook: $ sudo apt-get -y install ipython ipython-notebook
$ sudo -H pip install jupyter
TensorFlow: For installation you can refer this link: [https://www.tensorflow.org/install/install_linux]
Keras: For installation you can refer this link: [https://keras.io/#installation]
You can untar the data.tar.gz and model.tar.gz by using following command.
$ sudo tar -xvzf Path and Name of tar.gz file [./community_images.tar.gz]