Machine Learning Tutorial Python - 5: Save Model Using Joblib And Pickle

Training machine learning model can be quite time consuming if training dataset is very big. In this case it makes sense to train a model and save it to a file so that later on while making predictions you can just load that model from a file and you don't need to train it every time. Pickle and sklearn joblib modules can be used for this purpose. Joblib seems to be more efficient with big numpy arrays hence it is preferred when you have many numpy objects involved in your training step.

#MachineLearning #PythonMachineLearning #MachineLearningTutorial #Python #PythonTutorial #PythonTraining #MachineLearningCource #TrainingDataset #sklearntutorials #scikitlearntutorials

Topics that are covered in this Video:
0:00 - Saving trained model to the file
0:14 - How to solve a problem using machine learning?
1:33 - Coding
2:06 - Save model using pickle module
5:10 - Save model using joblib module
5:13 - Difference between pickle and joblib?

Next Video:

Populor Playlist:

Tools and Libraries:
Scikit learn tutorials
Sklearn tutorials
Machine learning with scikit learn tutorials
Machine learning with sklearn tutorials

#️⃣ Social Media #️⃣

[adnanax]

i was kinnda sad when at the end u said "i don't have any exercise today" but the student inside me felt really happy....lol

[pavan]

The best machine learning playlist in YouTube. Thank you very much sir🙏

[GlobalDee_]

Thanks so much, is so sad that I am just coming across your YouTube channel, but it is never too late.Your explanation are so explicit.God bless you.Thanks for all you do

[arvindkushwaha]

recently i started to watch your videos and i found these ML videos are awesome...thanks

[rudrakshya]

Great! Awesome, This is what I looking for a while.

[Lonczakt]

Great channel! Thank you for making these tutorials

[alivelumangaushadevi]

quick step to deploy model to file. Thanks for the great information..

[OrcaChess]

Thanks! Your tutorial helped me a lot. Keep up the good work :).

[faisalsaddique]

if in case of doing it with joblib you get an error with using 'model' in the brackets, use the name of your own model, which in this case was 'reg'

[_cestd]

thanks for this video, really helped!

[anchalmore]

Thanks a lot sir ..very useful ...everyone tells about training but you have explained very well how to save that model

[AnimeshSinghIITM]

It was really awesome tutorial, I'm enjoying it.

[debasishchakraborty]

Thank you for the nice and clear explanation. Now, if I want to take that trained and saved model to use for a different data-file (with same labels of course), how to do that?

[SaravananShanmughamportal]

I just wanted to add the correction to the video. The joblib is moved out of sklearn. Please find the deprecation warning.

DeprecationWarning: sklearn.externals.joblib is deprecated in 0.21 and will be removed in 0.23. Please import this functionality directly from joblib, which can be installed with: pip install joblib. If this warning is raised when loading pickled models, you may need to re-serialize those models with scikit-learn 0.21+.


you can import joblib directly as "import joblib"

[jinks]

Dhanyavaad I learnt a new thing because of you :)

[Steve-vlvr]

hi, I am into digital marketing, basically started learning machine learning hence, I have built the text summarization model and saved the model using pickle, now, I want to give the code to the company's developer to deploy the code on the website. so, should I give the pickle notepad file to him because that file is, as you said in the video binary format? please help

[priyankamahato]

Hi Sir, I had gone a lot of preprocessing, scaling etc before modeling will all these be saved in the model too when I pass raw data?