AttributeError: 'bytes' object has no attribute 'predict': Using pickle to load a Machine Learning model

Question

I have a trained Machine Learning model saved in GitHub repository with the name "trained_model.sav". I want to download it using Requests module of Python and use it in my Python file (with .py extension). When I run the following code:

url = "https://github.com/MUmairAB/Stroke-Prediction-using-Machine-Learning/blob/main/trained_model.sav?raw=true"
r = requests.get(url)
pickle.dump(r.content,open(os.path.join(getcwd(),'trained_model12.pkl'),'wb'))
model = pickle.load(open(os.path.join(getcwd(),'trained_model12.pkl'),'rb'))

# Using the model to make predictions
input_array = np.array([[0,67,0,1,0,228.69,36.6],
              [0,58,1,0,0,87.96,39.2]])

input_df = pd.DataFrame(x)
prediction = modell.predict(input_df)

I get the following error

runfile('C:/Users/User1/Desktop/folder1/file1.py', wdir='C:/Users/User1/Desktop/folder1')
Traceback (most recent call last):

  File ~\anaconda3\lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
    exec(code, globals, locals)

  File c:\users\user1\desktop\folder1\file1.py:35
    prediction = model.predict(df)

AttributeError: 'bytes' object has no attribute 'predict'

About the trained_model.sav:

It is a Machine Learning Pipeline object. After downloading it, I want to use it to make predictions.

What I want to achieve with the code?

I want to use the "trained_model.sav** file present in a GitHub repository, in a Python file with .py extension.

I can easily do this easily in IPython Notebook with .ipyn extension with:

!git clone REPOSITORY_LINK

But I cannot do that in .py file.

So, any suggestion how to do it or point out mistake in this code will be highly appreciated. If there is some other approach to get the job done, please comment that as well.

I was expecting that "trained_model.sav" file will be downloaded in my Python (with extension .py) file. And use this file as a Machine Learning model.

The variable modell is not defined in this code, what is it exactly? — Dr. Snoopy, Mar 06 '23 at 13:27
What your code does is download a .sav file, then the file contents (bytes) are saved inside a pickle file, and then you load that pickle file. The pickle file has bytes, not a model, so it triggers the error. — Dr. Snoopy, Mar 06 '23 at 15:10
You saved bytes into the pickle file, this is exactly what your code does. — Dr. Snoopy, Mar 06 '23 at 15:26
This is the problem with the code. I don't want pickle to save bytes. I want it to save the model. This is the solution I am looking for. — Umair Akram, Mar 06 '23 at 15:30

AttributeError: 'bytes' object has no attribute 'predict': Using pickle to load a Machine Learning model

0 Answers0