Skip to content

Tag: machine-learning

name ‘Bidirectional’ is not defined

Im following this tutorial and right when I want to initialize a sequential keras, like the code below: I get an error saying : What is the problem ? it is the exact same code as in the tutorial. Answer You’re most likely missing the import statement from the tensorflow package. It appears that’s there is a link to the

Remove outlier using quantile python

I need to remove outlier for a regression dataset. Lets say the dataset is consist in the following way With closer inspection, the column humidity has three outliers which are 50.0,18.0,0.01 but for windspeed column the outliers are 20 and 0.05 and both columns outliers are not in the same row. In this case if I remove my outlier with

Add features to the “numeric” dataset whose categorical value must be mapped using a conversion formula

I have this dataset: This is the request: “Add the Mjob and Fjob attributes to the “numeric” dataset whose categorical value must be mapped using a conversion formula of your choice.” Does anyone knows how to do it? For example: if ‘at_home’ value become ‘1’ in Mjob, I want the same result in the Fjob column. Same categorical values must

trying to callibrate keras model

I’m trying to calibrate my CNN model by Sklearn implementation CalibratedClassifierCV, tried to wrap it as KerasClassifier and to override the predict function but without success. someone could say me what I did wrong? this is the model code: this is me trying to calibrate it : the output : valX_cnn and val_y_cnn are of type np.array. tried even to

TensorFlow TextVectorization producing Ragged Tensor with no padding after loading it from pickle

I have a TensorFlow TextVectorization layer named “eng_vectorization”: and I saved it in a pickle file, using this code: Then I load that pickle file properly as new_eng_vectorization: Now I am expecting, both previous vectorization eng_vectorization and newly loaded vectorization new_eng_vectorization to work the same, but they are not. The output of original vectorization, eng_vectorization([‘Hello people’]) is a Tensor: And