.

v1_multifailure_importance_analysis.py

@@ -0,0 +1,307 @@
+# Csar Fdez, UdL, 2025
+import pandas as pd
+import matplotlib.pyplot as plt
+import datetime
+import numpy as np
+import keras
+import os.path
+import pickle
+from keras import layers
+import copy
+
+
+# data files arrays. Index:
+# 0.  No failure
+# 1.  Blocked evaporator
+# 2.   Full Blocked condenser
+# 3.   Partial Blocked condenser
+# 4   Fan condenser not working
+# 5.  Open door
+
+
+NumberOfFailures=5
+NumberOfFailures=4  # So far, we have only data for the first 4 types of failures
+datafiles=[]
+for i in range(NumberOfFailures+1):
+    datafiles.append([])
+
+# Next set of ddata corresponds to Freezer, SP=-26
+datafiles[0]=['2024-08-07_5_','2024-08-08_5_'] 
+datafiles[1]=['2024-12-11_5_', '2024-12-12_5_','2024-12-13_5_','2024-12-14_5_','2024-12-15_5_'] 
+datafiles[2]=['2024-12-18_5_','2024-12-19_5_'] 
+datafiles[3]=['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[4]=['2024-12-28_5_','2024-12-29_5_','2024-12-30_5_','2024-12-31_5_','2025-01-01_5_'] 
+#datafiles[4]=[] 
+
+# Features suggested by Xavier
+features=['r1 s1','r1 s4','r1 s5','pa1 apiii']
+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']
+NumFeatures=len(features)
+
+df_list=[]
+for i in range(NumberOfFailures+1):
+    df_list.append([])
+
+for i in range(NumberOfFailures+1):
+    dftemp=[]
+    for f in datafiles[i]:
+        print("                 ", f)
+        #df1 = pd.read_csv('./data/'+f+'.csv', parse_dates=['datetime'], dayfirst=True, index_col='datetime')
+        df1 = pd.read_csv('./data/'+f+'.csv')
+        dftemp.append(df1)
+    df_list[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
+
+dataframe=[]
+for i in range(NumberOfFailures+1):
+    dataframe.append([])
+
+for i in range(NumberOfFailures+1):
+    datalength=df_list[i].shape[0]
+    dataframe[i]=df_list[i].iloc[range(0,datalength,subsamplingrate)][features]
+    dataframe[i].reset_index(inplace=True,drop=True)
+    dataframe[i].dropna(inplace=True)
+
+
+# Train data is first 2/3 of data
+# Test data is: last 1/3 of data 
+dataTrain=[]
+dataTest=[]
+for i in range(NumberOfFailures+1):
+    dataTrain.append(dataframe[i].values[0:int(dataframe[i].shape[0]*2/3),:])
+    dataTest.append(dataframe[i].values[int(dataframe[i].shape[0]*2/3):,:])
+
+
+def normalize2(train,test):
+    # merges train and test
+    means=[]
+    stdevs=[]
+    for i in range(NumFeatures):
+        means.append(train[:,i].mean())
+        stdevs.append(train[:,i].std())
+    return( (train-means)/stdevs, (test-means)/stdevs )
+
+dataTrainNorm=[]
+dataTestNorm=[]
+for i in range(NumberOfFailures+1):
+    dataTrainNorm.append([])
+    dataTestNorm.append([])
+
+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()
+
+
+TIME_STEPS = 12
+def create_sequences(values, time_steps=TIME_STEPS):
+    output = []
+    for i in range(len(values) - time_steps + 1):
+        output.append(values[i : (i + time_steps)])
+    return np.stack(output)
+
+x_train=[]
+for i in range(NumberOfFailures+1):
+    x_train.append(create_sequences(dataTrainNorm[i]))
+
+
+model=[]
+modelckpt_callback =[]
+es_callback =[]
+path_checkpoint=[]
+for i in range(NumberOfFailures+1):
+    model.append([])
+    model[i] = keras.Sequential(
+        [
+            layers.Input(shape=(x_train[i].shape[1], x_train[i].shape[2])),
+            layers.Conv1D(
+                filters=64,
+                kernel_size=7,
+                padding="same",
+                strides=2,
+                activation="relu",
+            ),
+            layers.Dropout(rate=0.2),
+            layers.Conv1D(
+                filters=32,
+                kernel_size=7,
+                padding="same",
+                strides=2,
+                activation="relu",
+            ),
+            layers.Conv1DTranspose(
+                filters=32,
+                kernel_size=7,
+                padding="same",
+                strides=2,
+                activation="relu",
+            ),
+            layers.Dropout(rate=0.2),
+            layers.Conv1DTranspose(
+                filters=64,
+                kernel_size=7,
+                padding="same",
+                strides=2,
+                activation="relu",
+            ),
+            layers.Conv1DTranspose(filters=x_train[i].shape[2], kernel_size=7, padding="same"),
+        ]
+    )
+    model[i].compile(optimizer=keras.optimizers.Adam(learning_rate=0.001), loss="mse")
+    model[i].summary()
+    path_checkpoint.append("model_v1_"+str(i)+"._checkpoint.weights.h5")
+    es_callback.append(keras.callbacks.EarlyStopping(monitor="val_loss", min_delta=0, patience=15))
+    modelckpt_callback.append(keras.callbacks.ModelCheckpoint( monitor="val_loss", filepath=path_checkpoint[i], verbose=1, save_weights_only=True, save_best_only=True,))
+
+
+
+# Load models
+for i in range(NumberOfFailures+1):
+    model[i].load_weights(path_checkpoint[i])
+
+
+x_train_pred=[]
+train_mae_loss=[]
+threshold=[]
+for i in range(NumberOfFailures+1):
+    x_train_pred.append(model[i].predict(x_train[i]))
+    train_mae_loss.append(np.mean(np.abs(x_train_pred[i] - x_train[i]), axis=1))
+    threshold.append(np.max(train_mae_loss[i],axis=0))
+
+print("Threshold : ",threshold)
+for i in range(NumberOfFailures+1):
+    threshold[i]=threshold[i]*1.3
+# Threshold is enlarged because, otherwise, for subsamples at 5' have many false positives
+
+
+#  Anomaly metrics:  
+#   False positive: with datatTestNorm[0]
+#   True negative: with datatTestNorm[i]  i>0
+
+def AtLeastOneTrue(x):
+    for i in range(NumFeatures):
+        if x[i]:
+            return True
+    return False
+
+def anomalyMetric(testList):  # first of list is non failure data
+    # FP, TP: false/true positive
+    # TN, FN: true/false negative
+    # Sensitivity: probab of fail detection if data is fail
+    # Specificity: prob of no fail detection if data is well
+    x_test = create_sequences(testList[0])
+    x_test_pred = model[0].predict(x_test)
+    test_mae_loss = np.mean(np.abs(x_test_pred - x_test), axis=1)
+    anomalies = test_mae_loss > threshold[0]
+    count=0
+    for i in range(anomalies.shape[0]):
+        if AtLeastOneTrue(anomalies[i]):
+            count+=1
+    FP=count
+    TN=anomalies.shape[0]-1
+    count=0
+    TP=np.zeros((NumberOfFailures))
+    FN=np.zeros((NumberOfFailures))
+    for i in range(1,len(testList)):
+        x_test = create_sequences(testList[i])
+        x_test_pred = model[0].predict(x_test)
+        test_mae_loss = np.mean(np.abs(x_test_pred - x_test), axis=1)
+        anomalies = test_mae_loss > threshold[0]
+        count=0
+        for j in range(anomalies.shape[0]):
+            if AtLeastOneTrue(anomalies[j]):
+                count+=1
+        TP[i-1] = count
+        FN[i-1] = anomalies.shape[0]-count
+    Sensitivity=TP.sum()/(TP.sum()+FN.sum())
+    Specifity=TN/(TN+FP)
+    print("Sensitivity: ",Sensitivity)
+    print("Specifity: ",Specifity)
+    return Sensitivity+Specifity
+
+
+
+MaxMetric=anomalyMetric([dataTestNorm[0],dataTestNorm[1],dataTestNorm[2],dataTestNorm[3],dataTestNorm[4]])
+
+# Now iterate  by permuting features and order them depending on Metric reduction
+
+
+metric=np.zeros(NumFeatures)
+for i in range(NumFeatures):
+    dataTestNormCopy=[]
+    # A deep copy is required because shuffle is an inline operation
+    for j in range(NumberOfFailures+1):
+        dataTestNormCopy.append([])
+        dataTestNormCopy[j]=copy.deepcopy(dataTestNorm[j])
+    for j in range(NumberOfFailures+1):
+        np.random.shuffle(dataTestNormCopy[j][:,i])
+    metric[i]=anomalyMetric([dataTestNormCopy[0],dataTestNormCopy[1],dataTestNormCopy[2],dataTestNormCopy[3],dataTestNormCopy[4]])
+
+
+# features ordered from least to most important
+indexes_ordered=np.argsort(metric)
+
+
+# Now, lets eliminate features accumulatively from least to most
+metric=np.zeros(NumFeatures)
+dataTestNormCopy=[]
+for j in range(NumberOfFailures+1):
+    dataTestNormCopy.append([])
+    dataTestNormCopy[j]=copy.deepcopy(dataTestNorm[j])
+# A deep copy is required because shuffle is an inline operation
+for i in range(NumFeatures):
+    for j in range(NumberOfFailures+1):
+        np.random.shuffle(dataTestNormCopy[j][:,i])
+    metric[i]=anomalyMetric([dataTestNormCopy[0],dataTestNormCopy[1],dataTestNormCopy[2],dataTestNormCopy[3],dataTestNormCopy[4]])
+
+# print features to be used in v1_multifailure.py
+
+#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','tc s3']
+F=np.array(features)
+
+l=indexes_ordered.shape[0]
+for i in range(3,NumFeatures-5):
+    print(F[indexes_ordered[l-i:]])
+
+'''
+
+['r1 s10' 'r1 s6' 'r2 s8']
+['tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r1 s5' 'pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6'
+ 'r2 s8']
+['r2 s3' 'r1 s5' 'pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10'
+ 'r1 s6' 'r2 s8']
+['tc s2' 'r2 s3' 'r1 s5' 'pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1'
+ 'r1 s10' 'r1 s6' 'r2 s8']
+['r1 s7' 'tc s2' 'r2 s3' 'r1 s5' 'pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2'
+ 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r2 s5' 'r1 s7' 'tc s2' 'r2 s3' 'r1 s5' 'pa1 apiii' 'r1 s8' 'r2 s1'
+ 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r2 s7' 'r2 s5' 'r1 s7' 'tc s2' 'r2 s3' 'r1 s5' 'pa1 apiii' 'r1 s8'
+ 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r2 s4' 'r2 s7' 'r2 s5' 'r1 s7' 'tc s2' 'r2 s3' 'r1 s5' 'pa1 apiii'
+ 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+['r1 s9' 'r2 s4' 'r2 s7' 'r2 s5' 'r1 s7' 'tc s2' 'r2 s3' 'r1 s5'
+ 'pa1 apiii' 'r1 s8' 'r2 s1' 'r2 s2' 'tc s1' 'r1 s10' 'r1 s6' 'r2 s8']
+'''
+