This project aims to analyze and classify text data using various machine learning techniques. It includes several stages, from importing data to Google Cloud Storage (GCS) to performing sentiment analysis and multi-label tag classification. Each notebook focuses on a specific aspect of the project pipeline. Below is an overview of each notebook:
01 Import Data to GCS.ipynb This notebook demonstrates how to import and store datasets into Google Cloud Storage (GCS) for further processing.
02 EDA and Preprocessing.ipynb In this step, exploratory data analysis (EDA) is performed to understand the data better. Preprocessing techniques such as data cleaning and feature engineering are applied to prepare the dataset for machine learning.
03 Sentiment Analysis.ipynb This notebook focuses on building and evaluating a sentiment analysis model that can classify text into positive, negative, or neutral categories.
04A Multi-label Tag Classification.ipynb In this notebook, a multi-label classification model is created to predict multiple tags for each text entry.
04B Multi-label Tag Classification Inference.ipynb This notebook covers the process of running inference on new data using the multi-label classification model developed in the previous notebook.
04C Multi-label Tag Classification Inference Evaluation.ipynb This notebook evaluates the performance of the multi-label classification model's inference results.
04D Extract Inference Samples.ipynb This step involves extracting and saving inference samples for further analysis or model improvement.