Building a Machine Learning Pipeline with Python and Scikit-Learn | Step-by-Step Tutorial
Вставка
- Опубліковано 6 жов 2024
- Welcome to our comprehensive tutorial on building powerful machine learning pipelines using Python and Scikit-Learn! In this video, we will guide you through the entire process of creating a robust machine learning pipeline, from data preprocessing to model evaluation
Interested in discussing a Data or AI project? Feel free to reach out via email or simply complete the contact form on my website.
📧 Email: ryannolandata@gmail.com
🌐 Website & Blog: ryannolandata....
🍿 WATCH NEXT
Scikit-Learn and Machine Learning Playlist: • Scikit-Learn Tutorials...
Simple Imputer: • Handling Missing Data ...
Column Transformer: • Simplify Data Preproce...
Voting Classifier: • Mastering Voting Class...
MY OTHER SOCIALS:
👨💻 LinkedIn: / ryan-p-nolan
🐦 Twitter: / ryannolan_
⚙️ GitHub: github.com/Rya...
🖥️ Discord: / discord
📚 *Data and AI Courses: datacamp.pxf.i...
📚 *Practice SQL & Python Interview Questions: stratascratch....
WHO AM I?
As a full-time data analyst/scientist at a fintech company specializing in combating fraud within underwriting and risk, I've transitioned from my background in Electrical Engineering to pursue my true passion: data. In this dynamic field, I've discovered a profound interest in leveraging data analytics to address complex challenges in the financial sector.
This UA-cam channel serves as both a platform for sharing knowledge and a personal journey of continuous learning. With a commitment to growth, I aim to expand my skill set by publishing 2 to 3 new videos each week, delving into various aspects of data analytics/science and Artificial Intelligence. Join me on this exciting journey as we explore the endless possibilities of data together.
*This is an affiliate program. I may receive a small portion of the final sale at no extra cost to you.
Hey guys I hope you enjoyed the video! If you did please subscribe to the channel!
Join our Data Science Discord Here: discord.com/invite/F7dxbvHUhg
If you want to watch a full course on Machine Learning check out Datacamp: datacamp.pxf.io/XYD7Qg
Want to solve Python data interview questions: stratascratch.com/?via=ryan
I'm also open to freelance data projects. Hit me up at ryannolandata@gmail.com
*Both Datacamp and Stratascratch are affiliate links.
This is by far the best tutorial I’ve come across on YT on pipelines and column transformers. Thank you Ryan
Means a lot. Thanks for checking it out
very good explanation keep continue
Thanks again. This is one great video. Very informative and demonstrate how to get it done w pipeline. I just summarize your content, and have a few questions. Let me know if I misunderstand some of your content. Using the cat/num pipeline example for the summary.
# 1 train_test_split raw data with NaN value
# 2 define num_cols and cat_cols for the num_pipeline, and cat_pipeline
# 3 make num_pipeline w Pipeline
# 4 make cat_pipeline w Pipeline
#5 use column transformer to combine num_pipeline and cat_pipeline
# 6 using make_pipeline to combine column_transformer (preprocessing) and DTC (classifier)
This is the Best tutorial based on pipeline. Well explained.
Thank you
Excellent demo! Nice job
here are my few question:
1) Do we test_train_split first before we do anything?
2) We use fit_transfrom for imputer in previous videos? Do you just need to fit the data in pipeline, and imputer will transform it in the pipeline?
3) what is n_jobs = -1 in the column_transformer?
4) pipeline going to save us time to retype all the code, so say if i want to use a different classifier (like random forest)? Do i just need to modify step 6 like this
RF = RandomForestClassifier()
pipefinal = make_pipeline (col_transformer, RF)
5) also -wonder if i run a different classifier, does that mean i also redo all the preprocessing step and then use a different classifier
6) can you explain how i can use the saved pipeline?
Thanks again, sorry for so many question, but you really provide a lot of good info on this topic for beginners. Thank you very much.
Good video, thanks. One of the best on this topic.
It would help if you explained the main idea more though. It always seemed mysterious how the output of one procedure/ function/pipeline component flowed into the next one. Also what conditions are required to be confident this process turns out right?
Looks nice. Can you use k-fold cross validation on the pipeline and tune the hyperparameters of the model inside the pipeline using GrindSearchCV?
best tutorial come across ...love from india
Appreciate it
First of all I want to thank you for making such a beautiful informative video on this topic and very neat and clean explanation.
I also want to know how to implement multiple Ml algorithms in the pipelines and choose the best algo according to the problem statement and dataset. Is there any way to do different tasks like 'nulifying multicollinearity(VIF)' and 'dimentionality reduction' within the pipeline?
Thanks you teacher!!
No problem
d2 = {'Genre':['Rock', 'Metal', 'Bluegrass', 'Rock', np.nan, 'Rock', 'Rock', np.nan, 'Bluegrass', 'Rock'],
'Social_media_followers':[1000000, np.nan, 2000000, 1310000, 1700000, np.nan, 4100000, 1600000, 2200000, 1000000],
'Sold_out':[1,0,0,1,0,0,0,1,0,1]}
What is the difference between makepipeline and pipeline while importing
Do we need to scale for a decision tree?
How to we clean the data here? Suppose some of my categorical columns have typos and outliers , how is our model going to handle them in after deployment ? During model building we clean the data manually but how does it happen in production?
In pipelines and transformers we can remove nulls and scale them with packages but how do we clean them?
Why not build a custom transformer to perform whatever operations you want to clean the data?
where can I find this notebook with all the python scripts in the video?
Awesome 👏
I learnt new tricks
Great! Thanks for checking it out