Final reorganizing and adding some of our previous work

Co-authored By: Daniel [email protected] Co-authored By: Brandon [email protected] Co-authored By: Jinanshi [email protected] Co-authored By: Enrico [email protected]
BU-Spark · Dec 16, 2024 · 2a7ca6c · 2a7ca6c
1 parent 4664331
commit 2a7ca6c
Show file tree

Hide file tree

Showing 15 changed files with 6,338 additions and 0 deletions.
diff --git a/EDA/LibRAG_EDA.ipynb b/EDA/LibRAG_EDA.ipynb
diff --git a/EDA/README.md b/EDA/README.md
@@ -0,0 +1,16 @@
+# EDA Notebook Details
+
+The EDA notebook contains some preliminary analysis that we conducted on our data from Boston Public Library's database.
+
+We analyzed metadata retreived from the Digital CommonWealth API as well as full-text data.
+
+Some of our findings, such as how much of the image/video data has text annotations, will help in determing how we should conduct RAG in the coming phase.
+
+## Running the Code
+Please make sure your environment is the same as our to run the notebook using the following commands:
+
+pip install -r requirements.txt
+
+Also make sure to access the data, stored in the SCC in /projectnb/sparkgrp/ml-bpl-rag-data/
+
+Full text can be found in /projectnb/sparkgrp/ml-bpl-rag-data/text
diff --git a/EDA/requirements.txt b/EDA/requirements.txt
@@ -0,0 +1,5 @@
+numpy==1.26.4
+seaborn==0.13.2
+pandas==2.2.2
+textblob==0.18.0.post0
+matplotlib==3.9.2
diff --git a/PoC/.ipynb_checkpoints/POC-checkpoint.ipynb b/PoC/.ipynb_checkpoints/POC-checkpoint.ipynb