remove unnecessary code

Qfunctions/loaData.py

@@ -5,7 +5,7 @@ STATIC_PATH = './Static'
 
 # 从文件夹中读取所有xlsx文件，每个文件对应一个label
 # labelNames为label的名字，如果不提供则默认为文件名
-def load_data(folder, labelNames, isDir):
+def load_data(folder, labelNames, isDir=True, fileClass='xlsx'):
   # 检查folder参数
   if folder is None:
     raise ValueError("The 'folder' parameter is required.")
@@ -20,34 +20,21 @@ def load_data(folder, labelNames, isDir):
   if not os.path.isdir(folder):
     raise ValueError(f"The folder '{folder}' does not exist.")
 
-#   fileNames = [f for f in os.listdir(folder) if f.endswith('.xlsx')]
-  
-#   # 获取数据的最大行数
-#   max_row_length = get_max_row_len(folder, fileNames)
-
-#   all_features = []
-
-#   for i, fileName in enumerate(fileNames):
-
-#       features = load_xlsx(folder + '/' + fileName, labelNames[i], max_row_length, 'zero')
-#       all_features.append(features)
-
-#   data = pd.concat(all_features, ignore_index = True)
-
   data = None
   if not isDir:
-    data = load_from_file(folder=folder, labelNames=labelNames)
+    data = load_from_file(folder=folder, labelNames=labelNames, fileClass=fileClass)
   else:
-    data = load_from_folder(folder=folder, labelNames=labelNames)
+    data = load_from_folder(folder=folder, labelNames=labelNames, fileClass=fileClass)
   print(data)
   return data
 
-def load_from_folder(folder, labelNames):
+def load_from_folder(folder, labelNames, fileClass):
     all_features = []
+    fileClass = '.' + fileClass
     for labelName in labelNames:
         subfolder = os.path.join(folder, labelName)
         if os.path.exists(subfolder) and os.path.isdir(subfolder):
-            fileNames = [f for f in os.listdir(subfolder) if f.endswith('.xlsx')]
+            fileNames = [f for f in os.listdir(subfolder) if f.endswith(fileClass)]
             max_row_length = get_max_row_len(subfolder, fileNames)
             features = []
             for fileName in fileNames:
@@ -58,8 +45,8 @@ def load_from_folder(folder, labelNames):
     # 将所有标签的数据合并
     return pd.concat(all_features, ignore_index=True)
 
-def load_from_file(folder, labelNames):
-  fileNames = [labelName + ".xlsx" for labelName in labelNames]
+def load_from_file(folder, labelNames, fileClass):
+  fileNames = [labelName + "." + fileClass for labelName in labelNames]
   # 获取数据的最大行数
   max_row_length = get_max_row_len(folder, fileNames)
   all_features = []

main.py

@@ -5,15 +5,13 @@ from Qfunctions.loaData import load_data as dLoader
 from sklearn.decomposition import PCA
 
 def main():
-  projet_name = '20241009MaterialDiv'
-  label_names =["Acrylic", "Ecoflex", "PDMS", "PLA", "Wood"]
-  data = dLoader(projet_name, label_names, isDir=True)
+  projet_name = '###########'                 # 输入元数据文件夹名称
+  label_names =[]                             # 请在[]内输入每一个分类的名称
+  data = dLoader(projet_name, label_names, isDir=False)
   X_train, X_test, y_train, y_test, encoder = divSet(
     data=data, labels=label_names, test_size= 0.3
   )
   
-  print(y_train)
-  
   import pandas as pd
   pca = PCA(n_components=2)  # 保留两个主成分
   principalComponents = pca.fit_transform(X_train)