Major Compilation : Best Notebooks on Kaggle — Part 1
Notebooks from which you will learn the most…
I have been participating in the Kaggle competitions for past 4 years during my free time and it’s been an incredible learning curve. As much as I loved writing my own solution to the problems on the platform, I thoroughly went through some of the top notebooks only to find the gems hidden beneath.
Advanced SQL Series
Day 2 : SQL Basics, Query Structure, Built In functions Conditions
Day 4 : Set Theory Operations, Stored Procedures and CASE statements in SQL
Day 6 : Subqueries, Group by, order by and Having clauses in SQL and Analytical Functions
Day 7 : Window Functions, Grouping Sets and Constraints in SQL
Day 8 : BigQuery Basics, SELECT, FROM, WHERE and Date and Extract in BigQuery
Day 9 : Common Expression Table, UNNEST Clause, SQL vs NoSQL Databases
Day 10 : Triggers, Pivot and Cursors in SQL
Day 14 : MySQL in Depth
Day 15 : PostgreSQL inDepth
Some of the other best Series —
How to solve any System Design Question ( approach that you can take)?
100 days : Your Data Science and Machine Learning Degree Series with projects
Complete Data Visualization and Pre-processing Series with projects
Projects Videos —
All the projects, data structures, SQL, algorithms, system design, Data Science and ML , Data Analytics, Data Engineering, , Implemented Data Science and ML projects, Implemented Data Engineering Projects, Implemented Deep Learning Projects, Implemented Machine Learning Ops Projects, Implemented Time Series Analysis and Forecasting Projects, Implemented Applied Machine Learning Projects, Implemented Tensorflow and Keras Projects, Implemented PyTorch Projects, Implemented Scikit Learn Projects, Implemented Big Data Projects, Implemented Cloud Machine Learning Projects, Implemented Neural Networks Projects, Implemented OpenCV Projects,Complete ML Research Papers Summarized, Implemented Data Analytics projects, Implemented Data Visualization Projects, Implemented Data Mining Projects, Implemented Natural Leaning Processing Projects, MLOps and Deep Learning, Applied Machine Learning with Projects Series, PyTorch with Projects Series, Tensorflow and Keras with Projects Series, Scikit Learn Series with Projects, Time Series Analysis and Forecasting with Projects Series, ML System Design Case Studies Series videos will be published on our youtube channel ( just launched).
Subscribe today!
Tech Newsletter —
If you are interested, you can join my newsletter through which I send tech interview tips, techniques, patterns, hacks — Software Development, ML, Data Science, Startups and Technology projects to more than 30K readers. You can subscribe to Tech Brew :
In this post, I’ll share with you the best notebooks on Kaggle( according to me) from which you can learn the most and exponentially speed up your learning curve in data science and ML field.
1. Jigsaw Rate Severity of Toxic Comments
Task —
In this your task is to score a set of about fourteen thousand comments. Pairs of comments were presented to expert raters, who marked one of two comments more harmful; each according to their own notion of toxicity.
Prize: $50,000, Kind: Featured, Metric: Jigsaw Agreement with Annotators
Best Notebooks —
https://www.kaggle.com/code/julian3833/jigsaw-incredibly-simple-naive-bayes-0-768
https://www.kaggle.com/code/kishalmandal/most-detailed-eda-tf-idf-and-logistic-reg
https://www.kaggle.com/code/its7171/jigsaw-cv-strategy
https://www.kaggle.com/code/subinium/how-to-visualize-text-dataset
https://www.kaggle.com/code/steubk/jrsotc-fe-rud-2-linear-rank-sub/notebook
https://www.kaggle.com/code/coreacasa/jigsaw4-luke-base-training-tito-cv-strategy/notebook
https://www.kaggle.com/code/alexander1980/best-cv-ens/notebook?scriptVersionId=87213915
2. Tabular Playground Series
Task —
In this your task is to classify 10 different bacteria species using data from a genomic analysis technique that has some data compression and data loss.
Prize : Swag, Team: 1,255, Kind: Playground, Metric: Categorization Accuracy
Best Notebooks —
https://www.kaggle.com/code/odins0n/tps-feb-22-eda-modelling
https://www.kaggle.com/code/usharengaraju/tensorflow-tabtransformer
https://www.kaggle.com/code/ambrosm/tpsfeb22-exploiting-the-flawed-random-generation/notebook
https://www.kaggle.com/code/remekkinas/super-learner-ensemble-extree-tuned-lda-umap
https://www.kaggle.com/code/remekkinas/bacteria-image-conv2d-cv-grad-cam
3. Indoor Location & Navigation
Task —
In this your task is to predict the indoor position of smartphones based on real-time sensor data, provided by indoor positioning technology company XYZ10.
Prize: $10,000, Kind: Research, Metric: Indoor Localization Mean Position Error
Best Notebooks —
https://www.kaggle.com/code/andradaolteanu/indoor-navigation-complete-data-understanding
https://www.kaggle.com/code/kokitanisaka/lstm-by-keras-with-unified-wi-fi-feats
https://www.kaggle.com/code/nigelhenry/simple-99-accurate-floor-model
https://www.kaggle.com/code/kokitanisaka/create-unified-wifi-features-example
https://www.kaggle.com/code/iamleonie/intro-to-indoor-location-navigation
https://www.kaggle.com/code/saitodevel01/indoor-post-processing-by-cost-minimization
https://github.com/ttvand/Indoor-Location-Navigation-Public
https://www.kaggle.com/code/mamasinkgs/discrete-optimization-in-2nd-place-solution/notebook
4. Shopee — Price Match Guarantee
Task —
In this you’re task is to apply your machine learning skills to build a model that predicts which items are the same products.
Prize: $30,000, Kind: Featured, Metric: Mean F-Score
Best Notebooks —
https://www.kaggle.com/code/lyakaap/2nd-place-solution/notebook
https://www.kaggle.com/code/ruchi798/shopee-eda-rapids-preprocessing-w-b
https://www.kaggle.com/code/tanulsingh077/pytorch-metric-learning-pipeline-only-images
https://www.kaggle.com/code/underwearfitting/pytorch-densenet-arcface-validation-training
https://www.kaggle.com/code/ragnar123/shopee-inference-efficientnetb1-tfidfvectorizer
https://www.kaggle.com/code/tanulsingh077/metric-learning-pipeline-only-text-sbert
https://www.kaggle.com/code/harangdev/shopee-embedding-visualizations-before-after-inb/notebook
https://www.kaggle.com/code/btbpanda/parts-of-3rd-solution-with-lightautoml/notebook
https://www.kaggle.com/code/isaienkov/shopee-data-understanding-and-analysis
5. Tweet Sentiment Extraction
Task —
In this task you’ll look at the labeled sentiment for a given tweet and figure out what word or phrase best supports it.
Prize: $15,000, Kind: Featured, Metric: Jaccard
Best Notebooks —
https://www.kaggle.com/code/faressayah/natural-language-processing-nlp-for-beginners
https://www.kaggle.com/code/parulpandey/eda-and-preprocessing-for-bert
https://www.kaggle.com/code/rftexas/nlp-cheatsheet-master-nlp
https://www.kaggle.com/code/theoviel/character-level-model-magic/notebook
https://www.kaggle.com/code/shahules/complete-eda-baseline-model-0-708-lb
https://www.kaggle.com/code/cdeotte/unsupervised-text-selection
https://www.kaggle.com/code/cpmpml/ensemble
https://www.kaggle.com/code/faressayah/nlp-with-spacy-nltk-gensim
https://www.kaggle.com/code/faressayah/nlp-sentiment-analysis-with-keras
6. TensorFlow 2.0 Question Answering
Task —
In this task you need to predict short and long answer responses to real questions about Wikipedia articles.
Prize: $50,000, Kind: Featured, Metric: NQMicroF1
Best Notebooks —
https://www.kaggle.com/code/mmmarchetti/tensorflow-2-0-bert-yes-no-answers
https://www.kaggle.com/code/ragnar123/exploratory-data-analysis-and-baseline
https://www.kaggle.com/code/opanichev/tf2-0-qa-binary-classification-baseline
https://www.kaggle.com/code/xhlulu/tf2-qa-lstm-for-long-answers-predictions
https://www.kaggle.com/code/axel81/hugging-face-transformers-pytorch-setup
https://www.kaggle.com/code/philculliton/using-tensorflow-2-0-w-bert-on-nq
https://www.kaggle.com/code/abhinand05/bert-for-humans-tutorial-baseline
7. 2019 Data Science Bowl
Task —
In this you are tasked to uncover new insights in early childhood education and how media can support learning outcomes.
Prize: $160,000, Kind: Featured, Metric: QuadraticWeightedKappa
Best Notebooks —
https://www.kaggle.com/code/robikscube/2019-data-science-bowl-an-introduction
https://www.kaggle.com/code/artgor/quick-and-dirty-regression
https://www.kaggle.com/code/erikbruin/data-science-bowl-2019-eda-and-baseline
https://www.kaggle.com/code/gpreda/2019-data-science-bowl-eda
https://www.kaggle.com/code/shahules/xgboost-feature-selection-dsbowl
https://www.kaggle.com/code/caesarlupum/ds-bowl-start-here-a-gentle-introduction
https://www.kaggle.com/code/ragnar123/feature-engineering-v-1-0
https://www.kaggle.com/code/gpreda/data-science-bowl-fast-compact-solution
https://www.kaggle.com/code/xhlulu/dsb-2019-simple-lgbm-using-aggregated-data
8. Two Sigma; Using News to Predict Stock Movements
Task —
In this competition you are tasked to analyze the news data to predict stock prices
Prize: $100,000, Kind: Featured, Metric: Two Sigma News
Best Notebooks —
https://www.kaggle.com/code/artgor/eda-feature-engineering-and-everything
https://www.kaggle.com/code/bguberfain/a-simple-model-using-the-market-and-news-data
https://www.kaggle.com/code/dster/two-sigma-news-official-getting-started-kernel
https://www.kaggle.com/code/youhanlee/simple-quant-features-using-python
https://www.kaggle.com/code/ashishpatel26/bird-eye-view-of-two-sigma-nn-approach
https://www.kaggle.com/code/zikazika/predicting-stock-movement
https://www.kaggle.com/code/wrosinski/shap-feature-importance-with-feature-engineering
https://www.kaggle.com/code/smasar/eda-preprocessing-processing-evaluation
https://www.kaggle.com/code/aditya1702/create-data-pipeline-and-lgbclassifiercv
9. Airbus Ship Detection Challenge
Task —
In this competition you are tasked to build a model that detects all ships in satellite images as quickly as possible. Can you find them even in imagery with clouds or haze?
Prize: $60,000, Kind: Featured, Metric: Intersection Over Union Object Segmentation
Best Notebooks —
https://www.kaggle.com/code/kmader/baseline-u-net-model-part-1
https://www.kaggle.com/code/inversion/run-length-decoding-quick-start
https://www.kaggle.com/code/meaninglesslives/airbus-ship-detection-data-visualization
https://www.kaggle.com/code/kmader/transfer-learning-for-boat-or-no-boat
https://www.kaggle.com/code/hmendonca/airbus-mask-rcnn-and-coco-transfer-learning
https://www.kaggle.com/code/leighplt/pytorch-tutorial-dataset-data-preparetion-stage
https://www.kaggle.com/code/iafoss/rotating-bounding-boxes-ship-localization
https://www.kaggle.com/code/voglinio/from-masks-to-bounding-boxes
https://www.kaggle.com/code/rackovic1994/convolutional-neural-network
10. New York City Taxi Fare Prediction
Task —
In this competition, you are tasked with predicting the fare amount (inclusive of tolls) for a taxi ride in New York City given the pickup and drop off locations.
Prize: Knowledge, Kind: Playground, Metric: Root Mean Squared Error
Best Notebooks —
https://www.kaggle.com/code/dster/nyc-taxi-fare-starter-kernel-simple-linear-model
https://www.kaggle.com/code/madhurisivalenka/cleansing-eda-modelling-lgbm-xgboost-starters
https://www.kaggle.com/code/shaz13/simple-exploration-notebook-map-plots-v2
https://www.kaggle.com/code/dimitreoliveira/taxi-fare-prediction-with-keras-deep-learning
https://www.kaggle.com/code/dimitreoliveira/tensorflow-dnn-coursera-ml-course-tutorial
https://www.kaggle.com/code/aiswaryaramachandran/eda-and-feature-engineering
https://www.kaggle.com/code/alexisbcook/intro-to-automl
https://www.kaggle.com/code/willkoehrsen/a-walkthrough-and-a-challenge
https://www.kaggle.com/code/nicapotato/taxi-rides-time-analysis-and-oof-lgbm
https://www.kaggle.com/code/amar09/fare-prediction-stacked-ensemble-xgboost-lgbm
Part 2 of best Kaggle Notebooks : Coming soon!
For complete 60 days of Data Science and ML : Day 1 — Day 60 : Quick Recap of 60 days of Data Science and ML
Follow for more updates. Stay tuned and keep coding!
For other projects, tune to —
Build Machine Learning Pipelines( With Code)
Recurrent Neural Network with Keras
Clustering Geolocation Data in Python using DBSCAN and K-Means
Facial Expression Recognition using Keras
Hyperparameter Tuning with Keras Tuner
Custom Layers in Keras
