From 091411baeac48acc269e28ef6ea8634afe8104ea Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Mon, 31 Mar 2025 17:49:18 +0200
Subject: [PATCH] fix : optimize imports
---
image_processing/build_dataset.py | 1 -
image_processing/build_image.py | 9 +++++----
image_ref/analyse_diann_digestion.py | 2 --
image_ref/dataset_ref.py | 5 ++---
image_ref/main.py | 5 -----
5 files changed, 7 insertions(+), 15 deletions(-)
diff --git a/image_processing/build_dataset.py b/image_processing/build_dataset.py
index d2820b28..e2e0e8ad 100644
--- a/image_processing/build_dataset.py
+++ b/image_processing/build_dataset.py
@@ -3,7 +3,6 @@ import os
import pandas as pd
import re
import numpy as np
-from PIL import Image
import matplotlib.image as mpimg
from build_image import build_image_ms1
diff --git a/image_processing/build_image.py b/image_processing/build_image.py
index a2d21431..f390b40e 100644
--- a/image_processing/build_image.py
+++ b/image_processing/build_image.py
@@ -32,12 +32,13 @@ def build_image_ms1(path, bin_mz):
e = oms.MSExperiment()
oms.MzMLFile().load(path, e)
e.updateRanges()
- id = e.getSpectra()[-1].getNativeID()
+ id_spectra = e.getSpectra()[-1].getNativeID()
- dico = dict(s.split('=', 1) for s in id.split())
+ dico = dict(s.split('=', 1) for s in id_spectra.split())
max_cycle = int(dico['cycle'])
list_cycle = [[] for _ in range(max_cycle)]
#get ms window size from first ms1 spectra (similar for all ms1 spectra)
+ ms1_start_mz,ms1_end_mz=None,None
for s in e:
if s.getMSLevel() == 1:
ms1_start_mz = s.getInstrumentSettings().getScanWindows()[0].begin
@@ -50,8 +51,8 @@ def build_image_ms1(path, bin_mz):
size_bin_ms1 = total_ms1_mz / n_bin_ms1
#organise sepctra by their MSlevel (only MS1 are kept)
for spec in e: # data structure
- id = spec.getNativeID()
- dico = dict(s.split('=', 1) for s in id.split())
+ id_spectra = spec.getNativeID()
+ dico = dict(s.split('=', 1) for s in id_spectra.split())
if spec.getMSLevel() == 1:
list_cycle[int(dico['cycle']) - 1].insert(0, spec)
diff --git a/image_ref/analyse_diann_digestion.py b/image_ref/analyse_diann_digestion.py
index 920a5861..ddaee148 100644
--- a/image_ref/analyse_diann_digestion.py
+++ b/image_ref/analyse_diann_digestion.py
@@ -1,7 +1,5 @@
-import pandas as pd
import pyarrow.parquet as pq
import matplotlib.pyplot as plt
-import numpy as np
from matplotlib_venn import venn2
diff --git a/image_ref/dataset_ref.py b/image_ref/dataset_ref.py
index 8d7f1fb0..be91a4cf 100644
--- a/image_ref/dataset_ref.py
+++ b/image_ref/dataset_ref.py
@@ -1,5 +1,4 @@
import random
-from cProfile import label
import numpy as np
import torch
@@ -9,10 +8,10 @@ import torch.utils.data as data
from PIL import Image
import os
import os.path
-from typing import Any, Callable, cast, Dict, List, Optional, Tuple, Union
+from typing import Callable, cast, Dict, List, Optional, Tuple, Union
from pathlib import Path
from collections import OrderedDict
-from sklearn.model_selection import train_test_split
+
IMG_EXTENSIONS = ".npy"
class Threshold_noise:
diff --git a/image_ref/main.py b/image_ref/main.py
index 8fadee97..d65d0c8e 100644
--- a/image_ref/main.py
+++ b/image_ref/main.py
@@ -1,8 +1,3 @@
-#TODO REFAIRE UN DATASET https://discuss.pytorch.org/t/upload-a-customize-data-set-for-multi-regression-task/43413?u=ptrblck
-"""1er methode load 1 image pour 1 ref
-2eme methode : load 1 image et toutes les refs : ok pour l'instant mais a voir comment est ce que cela scale avec l'augmentation du nb de classes
-3eme methods 2 datasets différents : plus efficace en stockage mais pas facil a maintenir"""
-
import matplotlib.pyplot as plt
import numpy as np
--
GitLab