The jupyter notebook gives a w2v representation analysis of the Game of Thrones episodes on Ice and fire
The data consists of 5 episodes of the series, which are in the text format, These are read and the stopwords are removed further building the corpus on the available data. This corpus used to build the GLOVE(Global Vectors for Word Representation) using the Gensim package.
Further to visualize the data we can reduce the dimensionality of the data using the t-SNE algoritham which is implemented using the scikitlearn API.
The attached W2V.ipynb file attched to the repository can be used to understand the anlysis of the language processing of the text files.
The required packages are to be installed which are mentioned at the start of the notebook, Where all the packages can be installed with the help of the pip
Hoping this helps in uderstanding more of about the usage and the theory behind the notebook.
Continue to watch my repository for furhter updates.
Until then enjoy the machine learning life!!