get rid of old data

.gitattributes

@@ -34,5 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 ALL_hum_isoforms_ESM1b_dels.zip filter=lfs diff=lfs merge=lfs -text
-del_sub_data.csv.gz filter=lfs diff=lfs merge=lfs -text
 ALL_hum_isoforms_ESM1b_del_sub.zip filter=lfs diff=lfs merge=lfs -text

app.py

@@ -141,7 +141,6 @@ if show_line_plots:
     st.plotly_chart(lt_apllr)
     st.plotly_chart(lt_llr)
 
-
 st.download_button(
     label=f"Download {selection_uid} data as CSV",
     data=ud.reset_index(drop=True).to_csv(),

del_sub_data.csv.gz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3b646c188438b5cb4508b95c59592cf094d670d60d24da1db9cda6b3eb11ddc2
-size 316120453

process_data.py

@@ -1,25 +0,0 @@
-import pandas as pd
-import zipfile
-import logging
-
-logging.basicConfig(level=logging.INFO,
-                    format='%(asctime)s - %(levelname)s - %(message)s',
-                   filename='processing.log')
-
-df = pd.read_csv("del_sub_data.csv.gz")
-
-prots = list(df.prot.unique())
-
-def write_chunk_to_zip(sub_df, zf, uid):
-    with zf.open(f"{uid}.csv", "w") as f:
-        sub_df.to_csv(f, index=False)
-        
-with zipfile.ZipFile("ALL_hum_isoforms_ESM1b_del_sub.zip", "w") as zip_file:
-    # Iterate over chunks of the DataFrame
-    for p in prots:
-        print(p)
-        prot_data = df[df.prot == p]
-        write_chunk_to_zip(prot_data, zip_file, p)
-        logging.info(f"Finished {p}")
-
-logging.info("Finished all")