From 283c24211c57abffb3d57173aef2f620f2a2ea1b Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Fri, 18 Oct 2024 10:42:07 +0200
Subject: [PATCH] datasets
---
prosit_data_merge.py | 76 ++++++++++++++++++++++----------------------
1 file changed, 38 insertions(+), 38 deletions(-)
diff --git a/prosit_data_merge.py b/prosit_data_merge.py
index 02c2431..a0d6b56 100644
--- a/prosit_data_merge.py
+++ b/prosit_data_merge.py
@@ -67,44 +67,44 @@ def alphabetical_to_numerical(seq):
return np.array(num)
-sources = ('data/intensity/sequence_train.npy',
- 'data/intensity/intensity_train.npy',
- 'data/intensity/precursor_charge_train.npy',
- 'data/intensity/precursor_charge_train.npy')
-
-
-data_rt = pd.read_csv('database/data_unique_ptms.csv')
-data_rt['Sequence']=data_rt['mod_sequence']
-
-padding(data_rt, 'Sequence', 30)
-data_rt['Sequence'] = data_rt['Sequence'].map(alphabetical_to_numerical)
-
-data_rt =data_rt.drop(columns='mod_sequence')
-
-data_int = load_intensity_df_from_files(sources[0], sources[1], sources[2], sources[3])
-
-seq_rt = data_rt.Sequence
-seq_int = data_int.seq
-seq_rt = seq_rt.tolist()
-seq_int = seq_int.tolist()
-seq_rt = [tuple(l) for l in seq_rt]
-seq_int = [tuple(l) for l in seq_int]
-
-ind_dict_rt = dict((k, i) for i, k in enumerate(seq_rt))
-inter = set(ind_dict_rt).intersection(seq_int)
-ind_dict_rt = [ind_dict_rt[x] for x in inter]
-
-
-data_int.irt = np.zeros(data_int.energy.shape)
-
-i=0
-for ind in ind_dict_rt :
- print(i,'/',len(ind_dict_rt))
- i+=1
- ind_int = [k for k, x in enumerate(seq_int) if x == seq_rt[ind]]
- data_int.irt[ind_int] = data_rt.irt[ind]
-
-np.save('data/intensity/irt_train.npy',data_int.irt)
+# sources = ('data/intensity/sequence_train.npy',
+# 'data/intensity/intensity_train.npy',
+# 'data/intensity/precursor_charge_train.npy',
+# 'data/intensity/precursor_charge_train.npy')
+#
+#
+# data_rt = pd.read_csv('database/data_unique_ptms.csv')
+# data_rt['Sequence']=data_rt['mod_sequence']
+#
+# padding(data_rt, 'Sequence', 30)
+# data_rt['Sequence'] = data_rt['Sequence'].map(alphabetical_to_numerical)
+#
+# data_rt =data_rt.drop(columns='mod_sequence')
+#
+# data_int = load_intensity_df_from_files(sources[0], sources[1], sources[2], sources[3])
+#
+# seq_rt = data_rt.Sequence
+# seq_int = data_int.seq
+# seq_rt = seq_rt.tolist()
+# seq_int = seq_int.tolist()
+# seq_rt = [tuple(l) for l in seq_rt]
+# seq_int = [tuple(l) for l in seq_int]
+#
+# ind_dict_rt = dict((k, i) for i, k in enumerate(seq_rt))
+# inter = set(ind_dict_rt).intersection(seq_int)
+# ind_dict_rt = [ind_dict_rt[x] for x in inter]
+#
+#
+# data_int.irt = np.zeros(data_int.energy.shape)
+#
+# i=0
+# for ind in ind_dict_rt :
+# print(i,'/',len(ind_dict_rt))
+# i+=1
+# ind_int = [k for k, x in enumerate(seq_int) if x == seq_rt[ind]]
+# data_int.irt[ind_int] = data_rt.irt[ind]
+#
+# np.save('data/intensity/irt_train.npy',data_int.irt)
sources = ('data/intensity/sequence_holdout.npy',
--
GitLab