Update app.py

app.py

@@ -5,8 +5,8 @@ import matplotlib.pyplot as plt
 from matplotlib import cm
 from PIL import Image
 import pandas as pd
-from dtaidistance import dtw
-
+#from dtaidistance import dtw
+'''
 def getDTWImage(IC_reference, sample, size):
 	d, paths = dtw.warping_paths(IC_reference, sample, window=int(size/2), psi=2)
 	x = np.array(paths)
@@ -19,9 +19,10 @@ def getDTWImage(IC_reference, sample, size):
 	# reshape the array
 	x = np.expand_dims(x, -1).astype("float32")
 	return x
-
-data = np.load('./data_LFP.npy')
-model = tf.keras.models.load_model('./models/model-bestLFP_V2.h5',compile = False)
+'''
+data = np.load('./data.npy')
+data_DTW = np.load('./data/data_DTW.npy')
+model = tf.keras.models.load_model('./models/model.h5',compile = False)
 
 def predict(Cell_number, Duty_Cycle, Cycle_number):
   # ------------------------ Prediction ------------------------
@@ -33,7 +34,7 @@ def predict(Cell_number, Duty_Cycle, Cycle_number):
 
   IC_reference = data[0][0]
   sample = data[Duty_Cycle-1][cycle]
-  sample_DTW = getDTWImage(IC_reference, sample, size)
+  sample_DTW = data_DTW[Duty_Cycle-1][cycle] #getDTWImage(IC_reference, sample, size)
   prediction = model.predict(np.expand_dims(sample_DTW, axis=0))
   pred = {"LLI ": str(prediction[0][0]), "LAMPE ": str(prediction[0][1]), "LAMNE ": str(prediction[0][2])}