.

v2_unsupervised.py

 
 parser = OptionParser()
 parser.add_option("-t", "--train", dest="train", help="Trains the models (false)", default=False, action="store_true")
+parser.add_option("-p", "--plot", dest="plot", help="Plot Data (false)", default=False, action="store_true")
 parser.add_option("-n", "--timesteps", dest="timesteps", help="TIME STEPS ", default=12)
 
 (options, args) = parser.parse_args()
         datafiles[j].append([])
 
 # Freezer, SP=-26
-datafiles['5-26'][0]=['2025-01-25_5_','2025-01-26_5_','2025-01-29_5_','2025-01-30_5_','2025-01-31_5_','2025-02-01_5_','2025-02-02_5_']
+datafiles['5-26'][0]=['2025-01-25_5_','2025-01-26_5_','2025-01-29_5_','2025-01-30_5_','2025-01-31_5_','2025-02-01_5_','2025-02-02_5_','2025-02-03_5_','2025-02-04_5_']
 datafiles['5-26'][1]=['2024-12-11_5_', '2024-12-12_5_','2024-12-13_5_','2024-12-14_5_','2024-12-15_5_']
-datafiles['5-26'][2]=['2024-12-18_5_','2024-12-19_5_']
+datafiles['5-26'][2]=['2024-12-21_5_','2024-12-22_5_','2024-12-23_5_','2024-12-24_5_','2024-12-25_5_','2024-12-26_5_']
 datafiles['5-26'][3]=['2024-12-28_5_','2024-12-29_5_','2024-12-30_5_','2024-12-31_5_','2025-01-01_5_'] 
 datafiles['5-26'][4]=['2025-02-13_5_','2025-02-14_5_','2025-02-15_5_','2025-02-16_5_','2025-02-17_5_','2025-02-18_5_','2025-02-19_5_'] 
 
 # Freezer, SP=-18
-datafiles['5-18'][0]=['2025-01-21_5_','2025-01-22_5_','2025-01-23_5_',] # no hi son aquestx arxius
+datafiles['5-18'][0]=['2025-01-21_5_','2025-01-22_5_','2025-01-23_5_'] # 
+datafiles['5-18'][1]=['2025-02-17_5_','2025-02-18_5_','2025-02-19_5_'] # 
+datafiles['5-18'][2]=['2025-03-10_5_','2025-03-11_5_','2025-03-12_5_'] # 
+datafiles['5-18'][3]=['2025-01-04_5_','2025-01-05_5_','2025-01-06_5_','2025-01-07_5_'] # 
+datafiles['5-18'][4]=['2025-04-30_5_','2025-05-01_5_','2025-05-02_5_','2025-05-03_5_','2025-05-04_5_','2025-05-05_5_'] #  Faltens aquestes dades 
 
 # Freezer, SP=-22
 datafiles['5-22'][0]=['2025-03-13_5_','2025-03-14_5_','2025-03-15_5_','2025-03-16_5_']  
-datafiles['5-22'][1]=['2025-03-23_5_','2025-03-24_5_','2025-03-25_5_']  # es solapa amb el seguent test 
-datafiles['5-22'][2]=[]  
+datafiles['5-22'][1]=['2025-03-21_5_','2025-03-22_5_','2025-03-23_5_','2025-03-24_5_','2025-03-25_5_']  #  
+datafiles['5-22'][2]=['2025-03-26_5_','2025-03-27_5_','2025-03-28_5_']  
+datafiles['5-22'][3]=['2025-03-31_5_','2025-04-01_5_','2025-04-02_5_','2025-04-03_5_']  
+datafiles['5-22'][4]=['2025-03-17_5_']  
 
 # Refrigerator  0  
 datafiles['30'][0]=['2025-01-21_3_','2025-01-22_3_','2025-01-23_3_','2025-01-24_3_','2025-01-25_3_','2025-01-26_3_']
 datafiles['30'][1]=['2024-12-11_3_','2024-12-12_3_','2024-12-13_3_','2024-12-14_3_','2024-12-15_3_']
 datafiles['30'][2]=['2024-12-18_3_','2024-12-19_3_','2024-12-20_3_']
-datafiles['30'][3]=['2024-12-28_3_','2024-12-29_3_','2024-12-30_3_','2024-12-31_3_']
+datafiles['30'][3]=['2024-12-28_3_','2024-12-29_3_','2024-12-30_3_','2024-12-31_3_','2025-01-01_3_']
 datafiles['30'][4]=['2025-02-12_3_','2025-02-13_3_','2025-02-14_3_','2025-02-15_3_','2025-02-16_3_','2025-02-17_3_','2025-02-18_3_','2025-02-19_3_']   # es solapa amb ventilador no funcionant. i els dies 20 i 21 no hi son
 
 
 datafiles['32'][0]=['2025-03-13_3_','2025-03-14_3_','2025-03-15_3_','2025-03-16_3_']
 datafiles['32'][1]=['2025-03-10_3_']
 datafiles['32'][2]=['2025-03-17_3_']
-datafiles['32'][3]=['2025-03-22_3_','2025-03-23_3_']
+datafiles['32'][3]=['2025-03-24_3_','2025-03-25_3_','2025-03-26_3_']
 datafiles['32'][4]=['2025-03-27_3_','2025-03-28_3_']
 
 
 # Test data is: last 1/3 of data 
 dataTrain=[]
 dataTest=[]
-NumberOfSamplesForTest=300
+NumberOfSamplesForTest=0
 
 for i in range(NumberOfFailures+1):
     dataTrain.append(dataframe[i].values[0:int(dataframe[i].shape[0]*2/3),:])
 
 def plotData():    
     fig, axes = plt.subplots(
-        nrows=NumberOfFailures+1, ncols=2, figsize=(15, 20), dpi=80, facecolor="w", edgecolor="k",sharex=True
+        nrows=NumberOfFailures+1, ncols=NumFeatures, figsize=(15, 20), dpi=80, facecolor="w", edgecolor="k",sharex=True
     )
     for i in range(NumberOfFailures+1):
-        axes[i][0].plot(np.concatenate((dataTrainNorm[i][:,0],dataTestNorm[i][:,0])),label="Fail "+str(i)+",  feature 0")
-        axes[i][1].plot(np.concatenate((dataTrainNorm[i][:,1],dataTestNorm[i][:,1])),label="Fail "+str(i)+",  feature 1")
+        for  j in range(NumFeatures):
+            axes[i][j].plot(np.concatenate((dataTrainNorm[i][:,j],dataTestNorm[i][:,j])),label="Fail "+str(i)+",  feature 0")
     #axes[1].legend()
     #axes[0].set_ylabel(features[0])
     #axes[1].set_ylabel(features[1])
     plt.show()
 
-#plotData()
-#exit()
+if options.plot:
+    plotData()
+    exit()
 
 def create_sequences(values, time_steps):
     output = []
         b=Counter(km.labels_[ranges[i][0]:ranges[i][1]])
         labels.append(b.most_common(1)[0][0])
 
-    print("\n\n\n\LABELS: ",labels,"\n\n")
+    print("\n\n\n LABELS: ",labels,"\n\n")
 
     NumFeaturesToPlot=len(indexesToPlot)
     plt.rcParams.update({'font.size': 16})
     Ranges.append([r,r+dataTestNorm[i].shape[0]])
     r+=dataTestNorm[i].shape[0]
 
-X=np.vstack((X,dataTestNorm[0]))  # We add a last segment of no fail data
-Ranges.append([r,r+dataTestNorm[0].shape[0]])
+#X=np.vstack((X,dataTestNorm[0]))  # We add a last segment of no fail data
+#Ranges.append([r,r+dataTestNorm[0].shape[0]])
+
 Ranges[len(Ranges)-1][1]=Ranges[len(Ranges)-1][1]-timesteps-1
 
 xtest=create_sequences(X,timesteps)
 
 
 km.fit_predict(xtest)
-#anomalyMetric(km.labels_,Ranges)
+anomalyMetric(km.labels_,Ranges)
 plot(xtest,Ranges)