update utils

utils.py

@@ -1,10 +1,12 @@
 import numpy as np
 import csv
-from model import cumbersome_model2
-from model import UNet_family
-from model import UNet_attention
+#from model import cumbersome_model2
+#from model import UNet_family
+#from model import UNet_attention
 from model import tf_model
 from model import tf_data
+#from opts import get_opts
+#from tools import pick_models
 
 import time
 import torch
@@ -13,6 +15,8 @@ import random
 import shutil
 from scipy.signal import decimate, resample_poly, firwin, lfilter
 
+from pathlib import Path
+
 
 os.environ["CUDA_VISIBLE_DEVICES"]="0"
 
@@ -65,12 +69,12 @@ def read_train_data(file_name):
     return data
 
 
-def cut_data(raw_data):
+def cut_data(filepath, raw_data):
     raw_data = np.array(raw_data).astype(np.float64)
     total = int(len(raw_data[0]) / 1024)
     for i in range(total):
         table = raw_data[:, i * 1024:(i + 1) * 1024]
-        filename = './temp2/' + str(i) + '.csv'
+        filename = filepath + '/temp2/' + str(i) + '.csv'
         with open(filename, 'w', newline='') as csvfile:
             writer = csv.writer(csvfile)
             writer.writerows(table)
@@ -114,8 +118,8 @@ def dataDelete(path):
     except OSError as e:
         print(e)
     else:
-        pass
-        #print("The directory is deleted successfully")
+        #pass
+        print("The directory is deleted successfully")
 
 
 def decode_data(data, std_num, mode=5):
@@ -181,11 +185,12 @@ def decode_data(data, std_num, mode=5):
 
 def preprocessing(filename, samplerate):
     # establish temp folder
+    tmp_filepath = str(Path(str(filename)).parent)
     try:
-        os.mkdir("./temp2/")
+        os.mkdir(tmp_filepath+"/temp2/")
     except OSError as e:
-        dataDelete("./temp2/")
-        os.mkdir("./temp2/")
+        dataDelete(tmp_filepath+"/temp2/")
+        os.mkdir(tmp_filepath+"/temp2/")
         print(e)
     
     # read data
@@ -198,17 +203,17 @@ def preprocessing(filename, samplerate):
     signal = FIR_filter(signal, 1, 50)
     #print(signal.shape)
     # cutting data
-    total_file_num = cut_data(signal)
+    total_file_num = cut_data(tmp_filepath, signal)
 
     return total_file_num
 
 
 # model = tf.keras.models.load_model('./denoise_model/')
-def reconstruct(model_name, total, outputfile):
+def reconstruct(model_name, total, filepath, outputfile):
     # -------------------decode_data---------------------------
     second1 = time.time()
     for i in range(total):
-        file_name = './temp2/{}.csv'.format(str(i))
+        file_name = filepath + '/temp2/{}.csv'.format(str(i))
         data_noise = read_train_data(file_name)
         
         std = np.std(data_noise)
@@ -220,13 +225,13 @@ def reconstruct(model_name, total, outputfile):
         d_data = decode_data(data_noise, std, model_name)
         d_data = d_data[0]
 
-        outputname = "./temp2/output{}.csv".format(str(i))
+        outputname = filepath + '/temp2/output{}.csv'.format(str(i))
         save_data(d_data, outputname)
 
     # --------------------glue_data----------------------------
-    glue_data("./temp2/", total, outputfile)
+    glue_data(filepath+"/temp2/", total, filepath+'/'+outputfile)
     # -------------------delete_data---------------------------
-    dataDelete("./temp2/")
+    dataDelete(filepath+"/temp2/")
     second2 = time.time()
 
     print("Using", model_name,"model to reconstruct", outputfile, " has been success in", second2 - second1, "sec(s)")