2025-AKO/v1_multifailure_importance_...

# 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
from optparse import OptionParser


parser = OptionParser()
parser.add_option("-t", "--train", dest="train", help="Trains the models (false)", default=False, action="store_true")

(options, args) = parser.parse_args()


# 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','tc s3']
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,))


if options.train:
    history=[]
    for i in range(NumberOfFailures+1):
        history.append(model[i].fit( x_train[i], x_train[i], epochs=400, batch_size=128, validation_split=0.3, callbacks=[  es_callback[i], modelckpt_callback[i]      ],))

    fig, axes = plt.subplots(
        nrows=int(np.ceil((NumberOfFailures+1)/2)), ncols=2, figsize=(15, 20), dpi=80, facecolor="w", edgecolor="k",sharex=True
    )
    for i in range(int(np.ceil((NumberOfFailures+1)/2))):
        for j in range(2):
            r=2*i+j
            if r < NumberOfFailures+1:
                axes[i][j].plot(history[r].history["loss"], label="Training Loss")
                axes[i][j].plot(history[r].history["val_loss"], label="Val Loss")
                axes[i][j].legend()
    plt.show()
else:
    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]*1.7
# Threshold is enlarged because, otherwise, for subsamples at 5' have many false positives


#  1st scenario. Detect only anomaly.  Later, we will classiffy it
# Test data=  testnormal + testfail1 + testtail2 + testfail3 + testfail4 + testnormal
d=np.vstack((dataTestNorm[0],dataTestNorm[1],dataTestNorm[2],dataTestNorm[3],dataTestNorm[4],dataTestNorm[0]))

x_test = create_sequences(d)
x_test_pred = model[0].predict(x_test)
test_mae_loss = np.mean(np.abs(x_test_pred - x_test), axis=1)


# Define ranges for plotting in different colors
testRanges=[]
r=dataTestNorm[0].shape[0]
testRanges.append([0,r])
for i in range(1,NumberOfFailures+1):
    rnext=r+dataTestNorm[i].shape[0]
    testRanges.append([r,rnext] )
    r=rnext
testRanges.append([r, x_test.shape[0]  ])


def AtLeastOneTrue(x):
    for i in range(NumFeatures):
        if x[i]:
            return True
    return False

anomalies = test_mae_loss > threshold[0]
anomalous_data_indices = []
for i in range(anomalies.shape[0]):
    if AtLeastOneTrue(anomalies[i]):
    #if anomalies[i][0] or anomalies[i][1] or anomalies[i][2] or anomalies[i][3]:
        anomalous_data_indices.append(i)

#print(anomalous_data_indices)


# Let's plot only a couple of features
def plotData2():    
    fig, axes = plt.subplots(
        nrows=2, ncols=1, figsize=(15, 20), dpi=80, facecolor="w", edgecolor="k",sharex=True
    )
    axes[0].plot(range(len(x_train[0])),x_train[0][:,0,0],label="normal")
    axes[0].plot(range(len(x_train[0]),len(x_train[0])+len(x_test)),x_test[:,0,0],label="abnormal")
    axes[0].plot(len(x_train[0])+np.array(anomalous_data_indices),x_test[anomalous_data_indices,0,0],color='red',marker='.',linewidth=0,label="abnormal detection")
    axes[0].legend()
    axes[1].plot(range(len(x_train[0])),x_train[0][:,0,1],label="normal")
    axes[1].plot(range(len(x_train[0]),len(x_train[0])+len(x_test)),x_test[:,0,1],label="abnormal")
    axes[1].plot(len(x_train[0])+np.array(anomalous_data_indices),x_test[anomalous_data_indices,0,1],color='red',marker='.',linewidth=0,label="abnormal detection")
    axes[1].legend()
    axes[0].set_ylabel(features[0])
    axes[1].set_ylabel(features[1])
    plt.show()

#plotData2()


#   2nd scenario. Go over anomalies and classify it by less error
'''   
#This code works, but too slow
anomalous_data_type=[]
for i in anomalous_data_indices:
    error=[]
    for m in range(1,NumberOfFailures+1):
        error.append(np.mean(np.mean(np.abs(model[m].predict(x_test[i:i+1,:,:])-x_test[i:i+1,:,:]),axis=1)))
    anomalous_data_type.append(np.argmin(error)+1)
'''

anomalous_data_type=[]
x_test_predict=[]
for m in range(NumberOfFailures+1):
    x_test_predict.append(model[m].predict(x_test))


for i in anomalous_data_indices:
    error=[]
    for m in range(1,NumberOfFailures+1):
        error.append(np.mean(np.mean(np.abs(x_test_predict[m][i:i+1,:,:]-x_test[i:i+1,:,:]),axis=1)))
    anomalous_data_type.append(np.argmin(error)+1)


# For plotting purposes


anomalous_data_indices_by_failure=[]
for i in range(NumberOfFailures+1):
    anomalous_data_indices_by_failure.append([])

for i in range(len(anomalous_data_indices)):
    print(i," ",anomalous_data_type[i])
    anomalous_data_indices_by_failure[anomalous_data_type[i]].append(anomalous_data_indices[i])  


colorline=['violet','lightcoral','cyan','lime','grey']
colordot=['darkviolet','red','blue','green','black']

featuresToPlot=['r1 s1','r1 s3','r1 s5','r2 s3','r2 s4','pa1 apiii','tc s1','tc s2','tc s3']
indexesToPlot=[]
for i in featuresToPlot:
    indexesToPlot.append(features.index(i))

def plotData3():
    NumFeaturesToPlot=len(indexesToPlot)
    fig, axes = plt.subplots(
        nrows=NumFeaturesToPlot, ncols=1, figsize=(25, 20), dpi=80, facecolor="w", edgecolor="k",sharex=True
    )
    for i in range(NumFeaturesToPlot):
        init=0
        end=len(x_train[0])
        axes[i].plot(range(init,end),x_train[0][:,0,indexesToPlot[i]],label="normal train")
        #axes.plot(range(len(x_train[0]),len(x_train[0])+len(x_test)),x_test[:,0,0],label="abnormal")
        init=end
        end+=testRanges[0][1]
        axes[i].plot(range(init,end),x_test[testRanges[0][0]:testRanges[0][1],0,indexesToPlot[i]],label="normal test")
        init=end
        end+=(testRanges[1][1]-testRanges[1][0])
        for j in range(1,NumberOfFailures+1):
            axes[i].plot(range(init,end),x_test[testRanges[j][0]:testRanges[j][1],0,indexesToPlot[i]],label="fail type "+str(j), color=colorline[j-1])
            init=end
            end+=(testRanges[j+1][1]-testRanges[j+1][0])

            axes[i].plot(len(x_train[0])+np.array(anomalous_data_indices_by_failure[j]),x_test[anomalous_data_indices_by_failure[j],0,indexesToPlot[i]],color=colordot[j-1],marker='.',linewidth=0,label="abnormal detection type "+str(j))

        init=end-(testRanges[NumberOfFailures+1][1]-testRanges[NumberOfFailures+1][0])
        end=init+(testRanges[0][1]-testRanges[0][0])
        axes[i].plot(range(init,end),x_test[testRanges[0][0]:testRanges[0][1],0,indexesToPlot[i]],color='orange')

        if i==0:
            axes[i].legend(bbox_to_anchor=(1, 0.5))
        axes[i].set_ylabel(features[indexesToPlot[i]])
        axes[i].grid()
    plt.show()


plotData3()