test

alignement.py

+import numpy as np
+import pandas as pd
+from loess.loess_1d import loess_1d
+
+from dataloader import RT_Dataset
+from common_dataset import Common_Dataset
+import matplotlib.pyplot as plt
+
+ALPHABET_UNMOD = {
+    "_": 0,
+    "A": 1,
+    "C": 2,
+    "D": 3,
+    "E": 4,
+    "F": 5,
+    "G": 6,
+    "H": 7,
+    "I": 8,
+    "K": 9,
+    "L": 10,
+    "M": 11,
+    "N": 12,
+    "P": 13,
+    "Q": 14,
+    "R": 15,
+    "S": 16,
+    "T": 17,
+    "V": 18,
+    "W": 19,
+    "Y": 20,
+    "CaC": 21,
+    "OxM": 22
+}
+
+ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()}
+
+def numerical_to_alphabetical(arr):
+    seq = ''
+    for i in range(len(arr)):
+        seq+=ALPHABET_UNMOD_REV[arr[i]]
+    return seq
+
+def align(dataset, reference):
+    seq_ref = reference['sequence']
+    seq_common = dataset['Sequence']
+    seq_ref = seq_ref.tolist()
+    seq_common = seq_common.tolist()
+
+    seq_ref = [tuple(l) for l in seq_ref]
+    seq_common = [tuple(l) for l in seq_common]
+
+    ind_dict_ref = dict((k, i) for i, k in enumerate(seq_ref))
+    inter = set(ind_dict_ref).intersection(seq_common)
+    ind_dict_ref = [ind_dict_ref[x] for x in inter]
+
+    indices_common = dict((k, i) for i, k in enumerate(seq_common))
+    indices_common = [indices_common[x] for x in inter]
+
+    rt_ref = reference['irt'][ind_dict_ref].reset_index()
+    rt_data = dataset['Retention time'][indices_common].reset_index()
+
+    xout, yout, wout = loess_1d(np.array(rt_data['Retention time'].tolist()), np.array(rt_ref['irt'].tolist()),
+                                xnew=dataset['Retention time'],
+                                degree=1, frac=0.5,
+                                npoints=None, rotate=False, sigy=None)
+    dataset['Retention time'] = yout
+    return dataset
+
+
+data_ori = RT_Dataset(None, 'database/data.csv', 'train', 25).data
+data_ori ['sequence'] = data_ori['sequence'].map(numerical_to_alphabetical)
+# data_ori = pd.read_pickle('database/data_01_16_DIA_ISA_55.pkl')
+# data_ori = Common_Dataset(data_ori, 30).data
+data_train = pd.read_pickle('database/data_DIA_ISA_55_train.pkl')
+# data_train = Common_Dataset(data_train, 30).data
+#
+data_align = align(data_train, data_ori)
+#
+plt.scatter(data_train['Retention time'], data_align['Retention time'], s=1)
+plt.savefig('test_align_2.png')
+#
+#
+# dataset_ref = pd.read_pickle('database/data_01_16_DIA_ISA_55.pkl')
+# data_ref = Common_Dataset(dataset_ref, 25).data
+# dataset_2 = pd.read_pickle('database/data_01_20_DIA_ISA_55.pkl')
+# data_2 = Common_Dataset(dataset_2, 25).data
+# dataset_3 = pd.read_pickle('database/data_01_17_DIA_ISA_55.pkl')
+# data_3 = Common_Dataset(dataset_3, 25).data
+# dataset_4 = pd.read_pickle('database/data_01_23_DIA_ISA_55.pkl')
+# data_4 = Common_Dataset(dataset_4, 25).data
+# data_align_3 = align(data_3, data_ref)
+# data_align_4 = align(data_4, data_ref)
+#
+# data = pd.concat([data_ref, data_2, data_align_3, data_align_4], ignore_index=True)
+# data = data.drop(columns='index')
+# data['Sequence'] = data['Sequence'].map(numerical_to_alphabetical)
+# num_data = data.shape[0]
+# train_num = np.floor(num_data*0.8)
+# train_size=0
+# list_train=[]
+# list_test=[]
+# groups = data.groupby('Sequence')
+# for seq, gr in groups:
+#
+#     train_size+= gr.shape[0]
+#
+#     if train_size>train_num:
+#         list_test.append(gr)
+#     else:
+#         list_train.append(gr)
+#
+#
+# dataset_train = pd.concat(list_train, ignore_index=True)
+# dataset_test = pd.concat(list_test, ignore_index=True)
+# dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl')
+# dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')