Remove xlsx files from tracking, replace with Parquet

- Convert remaining xlsx files to parquet: db-polymer-properties,
db-D-interp-37-clean, db-D-interp-50-clean
- Update quantity_module/functions.py to read new parquet files
- Untrack all xlsx files from git and add *.xlsx to .gitignore
- Update convert_to_parquet.py to include newly converted files

Co-Authored-By: Claude Code <noreply@anthropic.com>

.gitignore

@@ -11,4 +11,5 @@ color_module/static/.DS_Store
 *.bkup
 tools/
 chris.tar.gz
+*.xlsx
 

convert_to_parquet.py

@@ -13,6 +13,9 @@ files = [
     ('quantity_module/data/vrentas-duda-params.xlsx',                 'quantity_module/data/vrentas-duda-params-solutes.parquet',         {'sheet_name': 'Solutes'}),
     ('quantity_module/data/vrentas-duda-params.xlsx',                 'quantity_module/data/vrentas-duda-params-polymers.parquet',        {'sheet_name': 'Polymers'}),
     ('qrf/qrf_parameters_allT.xlsx',                                 'qrf/qrf_parameters_allT.parquet',                                  {}),
+    ('data/db-polymer-properties-and-categories.xlsx',               'data/db-polymer-properties-and-categories.parquet',                {}),
+    ('quantity_module/data/db-D-interp-37-clean.xlsx',               'quantity_module/data/db-D-interp-37-clean.parquet',                {}),
+    ('quantity_module/data/db-D-interp-50-clean.xlsx',               'quantity_module/data/db-D-interp-50-clean.parquet',                {}),
 ]
 
 for src, dst, kwargs in files:

data/{db-polymer-properties-and-categories.xlsx → db-polymer-properties-and-categories.parquet}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694283f4bd9d9815738f0aaf451d28cfa4f239a03b908116af84b84a76795735
-size 26083
+oid sha256:36247c7305dad04c700ab49ff2f19ab1295b695062e8c98738e6f7e595b4e690
+size 27591

mp/model-opera-knn-alldata.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52547e54fc469bb5899c71c8ac12167a9661dfccb6a769799e4b0e89da30015e
-size 6551311

qrf/db-D-interp-allT-semiclean.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c5c4399929d0bb5f72e3fee3896058e7accfbf68d63df155e409a4c2b6b87a2
-size 13087796

qrf/mordred-descriptors.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:121f72b88fa46a0f16af6a1244af761ee6b9d679af7ab2e32d545538f8b5c5b5
-size 10251595

qrf/qrf_x.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98ea75f2a01564c9b1d998b699bbd11ee22954e5971c95addf8bb8a87e43fbd1
-size 195153

quantity_module/data/data-descriptors-mordred-numconfs51.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:121f72b88fa46a0f16af6a1244af761ee6b9d679af7ab2e32d545538f8b5c5b5
-size 10251595

qrf/qrf_y.xlsx → quantity_module/data/db-D-interp-37-clean.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8728d1f5c88d133dc396c8b8cb85313b716252d2f9dc7ed1a67b86780814157
-size 35100
+oid sha256:62039c3f5ad8001aa162770345788fa5055f6a20af8c458cad62c6b90847f7e8
+size 210568

quantity_module/data/db-D-interp-37-clean.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5c046f45ede6419629615b2e7397d74dc22c19db8556853638dd0c54ef9fad3f
-size 546002

qrf/qrf_parameters_allT.xlsx → quantity_module/data/db-D-interp-50-clean.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8d83fd6f4f5efd9352cb33e9a4c48d05d94c4aee1b64b2a3134d847856ae52
-size 5755
+oid sha256:1393f14023049e5e0cd5abac4827cfcbc4aa2501b1361725ba5aefe50bf4501c
+size 140776

quantity_module/data/db-D-interp-50-clean.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2086bf5769a47fb6ff95f4f1dc4368788f03d6365300e5c40f6631798929116d
-size 314780

quantity_module/data/db-D-interp-allT-clean.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b34934f1be324e95766d57b156ee29822b1ed282b3f0b4402e5405a8752c8acd
-size 10436853

quantity_module/data/solvent-viscosity.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1981623bba77ebda97107ece1e0b4d6b638a633cb5a91ed6a88a1a1bf26f513b
-size 13815

quantity_module/data/vrentas-duda-params.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:56a52df0ca74da211a93de2ca5e7c735a1265026bf954f967ea21a01831bd8bb
-size 23473

quantity_module/functions.py

@@ -46,8 +46,8 @@ df_visc = pd.read_parquet('quantity_module/data/solvent-viscosity.parquet')
 df_desc = pd.read_parquet('quantity_module/data/data-descriptors-mordred-numconfs51.parquet', columns=['Solute_InChIKey', 'Vabc','VMcGowan'])
 if not use_new:
     ## clean data
-    df_final_37 = pd.read_excel('quantity_module/data/db-D-interp-37-clean.xlsx')
-    df_final_50 = pd.read_excel('quantity_module/data/db-D-interp-50-clean.xlsx')
+    df_final_37 = pd.read_parquet('quantity_module/data/db-D-interp-37-clean.parquet')
+    df_final_50 = pd.read_parquet('quantity_module/data/db-D-interp-50-clean.parquet')
     # convert all T to K
     df_final_37['T'] = df_final_37['T'] + 273.15
     df_final_37['Polymer_Tg'] = df_final_37['Polymer_Tg'] + 273.15
@@ -183,7 +183,7 @@ df_vd_solv = pd.read_parquet('quantity_module/data/vrentas-duda-params-solutes.p
 df_vd_solv.drop_duplicates(keep='first', inplace=True, ignore_index=True) # drop exact duplicates
 df_vd_poly = pd.read_parquet('quantity_module/data/vrentas-duda-params-polymers.parquet')
 df_vd_poly.drop_duplicates(keep='first', inplace=True, ignore_index=True) # drop exact duplicates
-df_props = pd.read_excel('data/db-polymer-properties-and-categories.xlsx')
+df_props = pd.read_parquet('data/db-polymer-properties-and-categories.parquet')
 df_vd_poly = pd.merge(df_vd_poly, df_props[['Polymer_Name','Polymer_Tg','Polymer_Tm', 'CHRIS Class', 'New Class']], how='left', on='Polymer_Name')
 df_vd_poly['New Class'] = df_vd_poly['New Class'].fillna('none')
 df_vd_poly['CHRIS Class'] = df_vd_poly['CHRIS Class'].fillna('none')