From 13c96bfd15dadbb726b84d335bb28f4fea894d8c Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Thu, 3 Oct 2024 13:33:57 +0200
Subject: [PATCH] filter cysteine
---
alignement.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/alignement.py b/alignement.py
index 2b88a0c..39892fc 100644
--- a/alignement.py
+++ b/alignement.py
@@ -146,7 +146,7 @@ def filter_cysteine(df, col):
# dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl')
# dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')
-data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_train.pkl').reset_index(drop=True)
+data_train_1 = pd.read_csv('database/data_holdout.csv').reset_index(drop=True)
# data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_test.pkl').reset_index(drop=True)
# data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True)
# data_ori['Sequence']=data_ori['sequence']
@@ -154,4 +154,4 @@ data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_train.pkl').reset_index(
# data_train = pd.concat([data_train_2,data_train_1]).reset_index(drop=True)
# data_align = align(data_train, data_ori)
-df = filter_cysteine(data_train_1,'Sequence')
+df = filter_cysteine(data_train_1,'sequence')
--
GitLab