datasets

prosit_data_merge.py

@@ -107,42 +107,48 @@ def alphabetical_to_numerical(seq):
 # np.save('data/intensity/irt_train.npy',data_int.irt)
 
 
-sources = ('data/intensity/sequence_holdout.npy',
-             'data/intensity/intensity_holdout.npy',
-             'data/intensity/precursor_charge_holdout.npy',
-             'data/intensity/precursor_charge_holdout.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]
-
+# sources = ('data/intensity/sequence_holdout.npy',
+#              'data/intensity/intensity_holdout.npy',
+#              'data/intensity/precursor_charge_holdout.npy',
+#              'data/intensity/precursor_charge_holdout.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_holdout.npy',data_int.irt)
 
-data_int.irt = np.zeros(data_int.energy.shape)
+df = pd.read_pickle('database/data_prosit_merged_holdout.pkl')
 
-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]
+df = df.head(100)
 
-np.save('data/intensity/irt_holdout.npy',data_int.irt)
+df.to_csv('database/data_head.csv')