Gfyuki

I am new to deep learning. I have imbalanced class data. I used one hot encoding and scaling to preprocess my data. I have used adamoptimizer as optimizer function and sparse categorical crossentropy as my lass function. The model always gives high accuracy on one class with very low accuracy on other classes. Here is my code:

`

#separating test data according to classes

data_test = data_final[data_final.YEAR.isin(2018)]

data_test_0 = data_test[data_test['DELAY_CLASS']==0]

test_labels_0 = data_test_0.pop('DELAY_CLASS')

data_test_1 = data_test[data_test['DELAY_CLASS']==1]

test_labels_1 = data_test_1.pop('DELAY_CLASS')

data_test_2 = data_test[data_test['DELAY_CLASS']==2]

test_labels_2 = data_test_2.pop('DELAY_CLASS')

data_test_3 = data_test[data_test['DELAY_CLASS']==3]

test_labels_3 = data_test_3.pop('DELAY_CLASS')





#Extracting continuous columns from training data 

data_train = data_train[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit',

'D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]



#Extracting continuous columns from testing data

data_test = data_test[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit',

'D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]







print("reached here")



#SMOTE

sm = SMOTE(random_state=2)

ad = ADASYN(random_state=2)

data_train, train_labels = sm.fit_sample(data_train, train_labels)



data_train = pd.DataFrame(data_train)

data_train = data_train.rename(columns = {0:'MONTH',1:'DAY_OF_MONTH',2:'DAY_OF_WEEK',3:'Dep_Hour',

4:'Arr_Hour', 5:'CRS_ELAPSED_TIME', 6:'DISTANCE',

7:'traffic',8:'O_SurfaceTemperatureFahrenheit',9:'O_CloudCoveragePercent',

10:'O_WindSpeedMph',11:'O_PrecipitationPreviousHourInches',12:'O_SnowfallInches',

13:'D_SurfaceTemperatureFahrenheit',14:'D_CloudCoveragePercent',15:'D_WindSpeedMph',

16:'D_PrecipitationPreviousHourInches',17:'D_SnowfallInches',18:'Bird_Strike'})



#taking only continuous columns

cols = ['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit','D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']



#scaling

train_mean = data_train[cols].mean(axis=0)

train_std = data_train[cols].std(axis=0)

data_train[cols] = (data_train[cols] - train_mean) / train_std

data_test[cols] = (data_test[cols] - train_mean) / train_std

rain_labels = pd.Series(train_labels)



#taking continuous columns from test separated data

data_test_0 = data_test_0[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit','D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]



data_test_1 = data_test_1[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK','Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit','D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]



data_test_2 = data_test_2[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit',

'D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]



data_test_3 = data_test_3[['MONTH','DAY_OF_MONTH','DAY_OF_WEEK',

'Dep_Hour','Arr_Hour','CRS_ELAPSED_TIME','DISTANCE','traffic','O_SurfaceTemperatureFahrenheit','O_CloudCoveragePercent','O_WindSpeedMph','O_PrecipitationPreviousHourInches','O_SnowfallInches','D_SurfaceTemperatureFahrenheit',

'D_CloudCoveragePercent','D_WindSpeedMph','D_PrecipitationPreviousHourInches','D_SnowfallInches','Bird_Strike']]



#my model

def build_model():

    model = keras.Sequential([

        layers.Dense(100, activation = 'sigmoid', input_shape=[len(data_train.keys())]),

        #layers.Dropout(0.5),

        layers.Dense(50, activation = 'softplus'),

        #layers.Dropout(0.3),

        layers.Dense(25, activation = 'sigmoid'),

        #layers.Dropout(0.2),

        layers.Dense(4, activation = 'softmax')

    ])



    model.compile(loss='sparse_categorical_crossentropy',#with binary crossentropy use sigmoid and 1 output neuron

                  optimizer= tf.train.AdamOptimizer(0.001),

                  metrics=['accuracy'])

    return model



model = build_model()

model.fit(data_train, train_labels, epochs=5, batch_size=128)







test_loss, test_acc = model.evaluate(data_test_0, test_labels_0)

print(test_acc)

test_loss, test_acc = model.evaluate(data_test_1, test_labels_1)

print(test_acc)

test_loss, test_acc = model.evaluate(data_test_2, test_labels_2)

print(test_acc)

test_loss, test_acc = model.evaluate(data_test_3, test_labels_3)

print(test_acc)

`

The training data is flights data of 2016 and 2017 and testing data is of 2018. I have separated classes from testing data to see the class wise accuracy of testing data.

The output is:

Class 0: 

44929/44929 [==============================] - 1s 12us/step

0.027710387500278218

Class 1:

10668/10668 [==============================] - 0s 11us/step

0.015935508061492312

Class 2:

33204/33204 [==============================] - 0s 9us/step

0.8956149861318866

Class 3:

274983/274983 [==============================] - 2s 9us/step

0.035293090845941046

The output remains somewhat same if I use adasyn instead of SMOTE or change layers and activation functions. Please help me out.
Thanks in advance.