Personal projects using NLP techniques.

Prerequisites

Project: Pitchfork Rating Prediction

The following project requires python 3.10 and R 4.3 to be installed.

To run the python code in this project, you will first need to install the relevant dependencies. This can be done by executing the following command from the project root:

pip install -r requirements.txt

Also, since this project contains a custom utilities library myutilpy, this must be installed to your environment. To do this, run the following command from the project root:

pip install -e myutilpy

This project contains a few R language jupyter notebooks. To execute these, your R environment must have the dependencies specified in requirements_R.txt installed. This can be done manually for each listed dependency.

Directory: notebooks_pitchfork_ratings

This sequence of notebooks utilizes a Pitchfork reviews dataset of approximately 20K album reviews (mattismegevand/pitchfork). The notebooks cover the following steps:

1. Data preprocessing (01_initial_data_prep). Loading, cleaning, and preprocessing of data.
2. Exploratory data analysis (02_data_explore). Visualization and summary statistics of processed dataset.
3. Model fitting and prediction (03_rating_pred). Model fitting and saving of model parameters. Also, collection and save-out of performance metrics and test set predictions.
4. Results analysis (04_fit_analysis). Post-fit investigation of model performance on test data.