.

v5_class.py

@@ -25,6 +25,7 @@ import pickle
 parser = OptionParser()
 parser.add_option("-t", "--train", dest="train", help="Trains the models (false)", default=False, action="store_true")
 parser.add_option("-n", "--timesteps", dest="timesteps", help="TIME STEPS ", default=12)
+parser.add_option("-r", "--transition", dest="transition", help="Includes transition data (false)", default=False, action="store_true")
 #parser.add_option("-f", "--thresholdfactor", dest="TF", help="Threshold Factor ", default=1.4)
 # threshold makes no sense when classifying, becaues we apply many models and decide class for the less MSE
 
@@ -48,17 +49,25 @@ for i in range(NumberOfFailures+1):
 
 # Next set of ddata corresponds to Freezer, SP=-26
 datafiles[0][0]=['2024-08-07_5_','2024-08-08_5_','2025-01-25_5_','2025-01-26_5_'] 
-datafiles[1][0]=['2025-01-27_5_','2025-01-28_5_'] 
-
 datafiles[0][1]=['2024-12-11_5_', '2024-12-12_5_','2024-12-13_5_'] 
-datafiles[1][1]=['2024-12-14_5_','2024-12-15_5_'] 
-
 datafiles[0][2]=['2024-12-18_5_','2024-12-21_5_','2024-12-22_5_','2024-12-23_5_','2024-12-24_5_'] 
-datafiles[1][2]=['2024-12-19_5_','2024-12-25_5_','2024-12-26_5_'] 
+datafiles[0][3]=['2024-12-28_5_','2024-12-29_5_','2024-12-30_5_'] 
 
+if options.transition:
+    datafiles[1][0]=['2025-01-27_5_','2025-01-28_5_'] 
+    datafiles[1][1]=['2024-12-14_5_','2024-12-15_5_','2024-12-16_5_']  # with TRANSITION
+    datafiles[1][2]=['2024-12-17_5_','2024-12-19_5_','2024-12-25_5_','2024-12-26_5_'] # with TRANSITION
+    datafiles[1][3]=['2024-12-27_5_','2024-12-31_5_','2025-01-01_5_'] # with TRANSITION
+else:
+    datafiles[1][0]=['2025-01-27_5_','2025-01-28_5_'] 
+    datafiles[1][1]=['2024-12-14_5_','2024-12-15_5_'] 
+    datafiles[1][2]=['2024-12-19_5_','2024-12-25_5_','2024-12-26_5_'] 
+    datafiles[1][3]=['2024-12-31_5_','2025-01-01_5_'] 
+ 
+
+#datafiles[0][4]=['2025-02-05_5_'] 
+#datafiles[1][4]=['2025-02-05_5_'] 
 
-datafiles[0][3]=['2024-12-28_5_','2024-12-29_5_','2024-12-30_5_'] 
-datafiles[1][3]=['2024-12-31_5_','2025-01-01_5_'] 
 
 #r1s5 supply air flow temperature
 #r1s1 inlet evaporator temperature
@@ -72,10 +81,10 @@ features=['r1 s1','r1 s4','r1 s5']
 features=['r1 s5']
 # Feature combination suggested by AKO
 #features=['r1 s1','r1 s4','r1 s5','pa1 apiii']
-#features=['r1 s1','r1 s4','r1 s5']
+features=['r1 s1','r1 s4','r1 s5']
 #features=['r1 s1','r1 s5','pa1 apiii']
 #features=['r1 s5','pa1 apiii']
-features=['r1 s1','r1 s5']
+#features=['r1 s1','r1 s5']
 #features=['r1 s5']
 
 
@@ -92,11 +101,6 @@ unitNames['r1 s4']='$(^{o}C)$'
 unitNames['r1 s5']='$(^{o}C)$'
 unitNames['pa1 apiii']='$(W)$'
 
-
-#features=['r1 s1','r1 s2','r1 s3','r1 s4','r1 s5','r1 s6','r1 s7','r1 s8','r1 s9','r1 s10','r2 s1','r2 s2','r2 s3','r2 s4','r2 s5','r2 s6','r2 s7','r2 s8','r2 s9','pa1 apiii','tc s1','tc s2']
-
-#features=['r2 s2', 'tc s1','r1 s10','r1 s6','r2 s8']
-
 NumFeatures=len(features)
 
 df_list=[[],[]]
@@ -121,8 +125,6 @@ for i in range(NumberOfFailures+1):
         dftemp.append(df1)
     df_list[1][i]=pd.concat(dftemp)
 
-
-
 # subsampled to 5'  =  30 * 10"
 # We consider smaples every 5' because in production, we will only have data at this frequency
 subsamplingrate=30
@@ -137,6 +139,7 @@ for i in range(NumberOfFailures+1):
     dataframe[0][i]=df_list[0][i].iloc[range(0,datalength,subsamplingrate)][features]
     dataframe[0][i].reset_index(inplace=True,drop=True)
     dataframe[0][i].dropna(inplace=True)
+
 for i in range(NumberOfFailures+1):
     datalength=df_list[1][i].shape[0]
     dataframe[1][i]=df_list[1][i].iloc[range(0,datalength,subsamplingrate)][features]
@@ -144,13 +147,13 @@ for i in range(NumberOfFailures+1):
     dataframe[1][i].dropna(inplace=True)
 
 
-# Train data is first 2/3 of data
+# Train data is first 2/3 of data. Not exactly. L
 # Test data is: last 1/3 of data 
 dataTrain=[]
 dataTest=[]
 for i in range(NumberOfFailures+1):
-    dataTrain.append(dataframe[0][i].values)
-    dataTest.append(dataframe[0][i])
+    dataTrain.append(dataframe[0][i])
+    dataTest.append(dataframe[1][i])
 
 # Calculate means and stdev
 a=dataTrain[0]
@@ -171,34 +174,16 @@ for i in range(NumberOfFailures+1):
 for i in range(NumberOfFailures+1):
     (dataTrainNorm[i],dataTestNorm[i])=normalize2(dataTrain[i],dataTest[i])
 
-def plotData():    
-    fig, axes = plt.subplots(
-        nrows=NumberOfFailures+1, ncols=2, 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")
-    #axes[1].legend()
-    #axes[0].set_ylabel(features[0])
-    #axes[1].set_ylabel(features[1])
-    plt.show()
-
-#plotData()
-#exit(0)
-
 
 NumFilters=64
 KernelSize=7
 DropOut=0.2
-ThresholdFactor=1.4
 def create_sequences(values, time_steps):
     output = []
     for i in range(len(values) - time_steps + 1):
         output.append(values[i : (i + time_steps)])
     return np.stack(output)
 
-
-
 def listToString(l):
     r=''
     for i in l:
@@ -295,8 +280,8 @@ for i in range(1,len(datalist)):
 testRanges=[]
 r=0
 for i in range(len(datalist)):
-    testRanges.append([r,r+datalist[i].shape[0]-int(options.timesteps)])
-    r+=datalist[i].shape[0]-int(options.timesteps)
+    testRanges.append([r,r+datalist[i].shape[0]-int(options.timesteps)+1])
+    r+=datalist[i].shape[0]-int(options.timesteps)+1
 
 testClasses=[0,1,2,3]
 
@@ -348,7 +333,7 @@ def plotData4():
                 end+=(testRanges[j+1][1]-testRanges[j+1][0])
 
             #if i==0:
-            #    axes[0].plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  type "+str(j) )
+            #    axes[0].plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  class "+str(j) )
 
 
 
@@ -364,9 +349,9 @@ def plotData4():
 
     for j in range(NumberOfFailures+1):
         if NumFeaturesToPlot==1:
-            axes.plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  type "+str(j) )
+            axes.plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  class "+str(j) )
         else:
-            axes[0].plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  type "+str(j) )
+            axes[0].plot(x[j],y[j] ,color=colordot[j],marker='.',markersize=10,linewidth=0,label="Fail detect  class "+str(j) )
             
     if NumFeaturesToPlot==1:
         axes.legend(ncol=4,loc=(0.1,0.98))
@@ -384,7 +369,7 @@ def whichClass(k,ranges):
     print("Error:  Class not exists")
     exit(0)        
 
-##   It remains to implemenent anomaly metrics for each failure type
+##   implemenent anomaly metrics for each failure class
 def anomalyMetric(classes,testranges,testclasses):  
     # FP, TP: false/true positive
     # TN, FN: true/false negative
@@ -423,6 +408,5 @@ def anomalyMetric(classes,testranges,testclasses):
 
 anomalyMetric(classes,testRanges,testClasses)
 plotData4()
-exit(0)