Removed reference to environmental variable

.gitignore

@@ -3,6 +3,7 @@
 *.npz
 *.csv
 *.pkl
+*.parquet
 .ipynb_checkpoints/*
 old_code/*
 model/*

Topic modeller to do.txt

@@ -0,0 +1,13 @@
+Need to add option to anonymise - done
+
+Need to add option to deduplicate
+
+Need option to sample for X number of rows with specific seed
+
+Add plotly visualisation - done
+
+Add zero shot topic list support
+
+Add topic renaming with LLMs - done
+
+Option to predict topics on a new dataset - done (kind of - just save model to file)

app.py

@@ -3,8 +3,7 @@ import os
 #os.environ["TOKENIZERS_PARALLELISM"] = "true"
 #os.environ["HF_HOME"] = "/mnt/c/..."
 #os.environ["CUDA_PATH"] = "/mnt/c/..."
-
-print(os.environ["HF_HOME"])
+#print(os.environ["HF_HOME"])
 
 import gradio as gr
 from datetime import datetime