Has ValueError "Must pass 2-d input" while Long Short Term Memory Classifier(Binary Classification) about network-intrusion-detection-using-machine-learning

[abhinav-bhardwaj]

Include the below code
X_test = X_test.to_numpy()
before executing this
x_test = np.reshape(X_test, (X_test.shape[0],X_test.shape[1],1))

This will fix the problem.

Closing the issue. Reopen if this issue arises again.

[klcheung99]

Abhinav, thank you so much!
Do you have LSTM Classifier (Multi-class Classification).
Moreover, I would want to use SHAP (SHapley Additive exPlanations), to explain the hidden layer and your model (KNN and LSTM), to see what features are the top important features while determining the result of model. however, there has some bugs.. I am so sorry to disturb you. but I spend a week to debug still got nothing. It will be great thankful if you have time to take a look! Thank you so much! Wish you have a nice weekend.

KNN SHAP explainer
`!pip install shap
import shap

knn_explainer = shap.KernelExplainer(knn.predict,X_test)
knn_shap_values = knn_explainer.shap_values(X_test)
shap.summary_plot(knn_shap_values, X_test)
shap.dependence_plot("intrusion", knn_shap_values, X_test)

shap.force_plot(knn_explainer.expected_value,knn_shap_values[10,:], X_test.iloc[10,:])
shap.force_plot(knn_explainer.expected_value, knn_shap_values, X_test)`

LSTM SHAP explainer
`import shap

explainer = shap.DeepExplainer(lstm, x_train)
shap_values = explainer.shap_values(x_test)
shap.initjs()`

[abhinav-bhardwaj]

@klcheung99 Thank you for mentioning this. At the moment I don't have LSTM for Multi-class but I will make sure to include that soon. Also, I will look into the SHAP issue.