Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/prakhar21/50-Days-of-ML

A day to day plan for this challenge (50 Days of Machine Learning) . Covers both theoretical and practical aspects
https://github.com/prakhar21/50-Days-of-ML

100daysofcode 100daysofmlcode dataprocessing deep-learning deep-neural-networks machine-learning pandas python siraj-raval tutorial

Last synced: 4 days ago
JSON representation

A day to day plan for this challenge (50 Days of Machine Learning) . Covers both theoretical and practical aspects

Awesome Lists containing this project

README 

        
# 50-Days-of-ML

A day to day plan for this challenge. Covers both theoritical and practical aspects.



I have build [ __Docker Image__](https://hub.docker.com/r/prakhar21/ml-utilities/) with all the required dependencies till __Day 21__. Feel free to use it by pulling it using -> __docker pull prakhar21/ml-utilities__



Please see [__Deep Work__](https://www.quora.com/What-is-the-one-skill-that-if-you-have-it-will-completely-change-your-life/answer/Shashank-Shekhar-221) which compliments our challenge and increases productivity. You can follow me on [__@Medium__](https://medium.com/@prakhar.mishra) for interesting blog articles.



## Day-1  (31st July, 2018)

* Learn about Pandas. [See Videos(1-5)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Learn in general about ML [See Video (Blackbox Machine Learning)](https://www.youtube.com/watch?v=MsD28INtSv8)

* Read/Practice [Day-1 and Day-2](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* See [Intro to Linear Regression](https://www.youtube.com/watch?v=zPG4NjIkCjc)

* Read [LR Docs](http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html)



## Day-2  (1st August, 2018)

* Learn about Pandas. [See Videos(6-10)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Learn in general about ML [See Video (Case Study: Churn Prediction)](https://www.youtube.com/watch?v=kE_t3Mm8Z50)

* Read/Practice [Day-3](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* See [Data Spread](https://www.khanacademy.org/math/probability/data-distributions-a1/summarizing-spread-distributions/v/range-variance-and-standard-deviation-as-measures-of-dispersion)

* Andrew Ng [See Videos (1-3)](https://www.youtube.com/watch?v=-la3q9d7AKQ&list=PLNeKWBMsAzboR8vvhnlanxCNr2V7ITuxy)



## Day-3 (2nd August, 2018)

* Learn about Pandas. [See Videos(11-15)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Learn in general about ML [See Video (Statistical Learning Theory)](https://www.youtube.com/watch?v=rqJ8SrnmWu0)

* Read/Practice [Day-4 and Day-8](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* Visualization in Python [See Official Docs](https://matplotlib.org/users/pyplot_tutorial.html)



## Day-4 (3rd August, 2018)

* Learn about Pandas. [See Videos(16-18)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Read [KNN-1](https://www.analyticsvidhya.com/blog/2018/03/introduction-k-neighbours-algorithm-clustering/)

* Read [KNN-2](https://medium.com/@adi.bronshtein/a-quick-introduction-to-k-nearest-neighbors-algorithm-62214cea29c7)



## Day-5 (4th August, 2018)

* Learn about Pandas. [See Videos(19-22)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Read/Practice [Day-7](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* General read on [Medium](https://blog.usejournal.com/cracking-eaadhar-password-in-3-seconds-with-maths-9533c8e8f9c2)



## Day-6 (5th August, 2018)

* Learn about Pandas. [See Videos(23-26)](https://www.dataschool.io/easier-data-analysis-with-pandas/)

* Implementing KNN

* Read/Practice [Day-12](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* KNN-Sklearn [See Official Docs](http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html)



## Day-7 (6th August, 2018)

* Learn about Numpy. [Read this](https://www.dataquest.io/blog/numpy-tutorial-python/)

* [Naive Bayes - 1](https://www.analyticsvidhya.com/blog/2017/09/naive-bayes-explained/)

* [Naive Bayes - 2](https://medium.com/machine-learning-101/chapter-1-supervised-learning-and-naive-bayes-classification-part-1-theory-8b9e361897d5)

* [Naive Bayes - 3](https://machinelearningmastery.com/naive-bayes-for-machine-learning/)

* [Naive Bayes - 4](https://www.youtube.com/watch?v=6xBU74VWEuE)



## Day-8 (7th August, 2018)

* [Lime](https://github.com/marcotcr/lime)

* [Building Trust in ML models](https://www.analyticsvidhya.com/blog/2017/06/building-trust-in-machine-learning-models/)

* [Interpretable ML models](https://www.oreilly.com/learning/introduction-to-local-interpretable-model-agnostic-explanations-lime)

* Implementing Naive Bayes

* Learn in general about ML [See Video (Stochastic Gradient Descent)](https://www.youtube.com/watch?v=5TZww5bTROE) - 10 mins onwards



## Day-9 (8th August, 2018)

* Lime hands-on news dataset

* Light read about [Averaging Ensemble Techniques](http://sebastianraschka.com/Articles/2014_ensemble_classifier.html) for more accurate predictions.

* Light reading on [Ensemble Techniques](https://www.dataquest.io/blog/introduction-to-ensembles/)

* Implementing Support Vector Machines

* See [Ensemble learners](https://www.youtube.com/watch?v=Un9zObFjBH0)



## Day-10 (9th August, 2018)

* Implement Average Voting Ensemble Meta Model

* Read about [Stacking Ensemble Technique](https://www.kdnuggets.com/2017/02/stacking-models-imropved-predictions.html)

* Read [Stacking from scratch](https://machinelearningmastery.com/implementing-stacking-scratch-python/)

* Read [Stacking-concept-pictures-code](https://github.com/vecxoz/vecstack/blob/master/examples/00_stacking_concept_pictures_code.ipynb)



## Day-11 (10th August, 2018)

* Read/Practice [Day-25](https://github.com/Avik-Jain/100-Days-Of-ML-Code/blob/master/Code/Day%2025%20Decision%20Tree.md)

* Read about [Feature Scaling](http://sebastianraschka.com/Articles/2014_about_feature_scaling.html)

* Read [Why, How and When to Scale](https://medium.com/greyatom/why-how-and-when-to-scale-your-features-4b30ab09db5e)

* Implementation of Feature scaling techniques

* See [Decision Trees - MMDS](https://www.youtube.com/watch?v=NsUqRe-9tb4)

* Glance through [Decision Trees - Coursera](https://www.coursera.org/learn/ml-classification/home/week/3)



## Day-12 (11th August, 2018)

* Implementing of Decision Trees

* See lectures from [Coursera - 2nd week](https://www.coursera.org/learn/ml-classification/home/week/2) and [Coursera - 4th week](https://www.coursera.org/learn/ml-classification/home/week/4)



## Day-13 (12th August, 2018)

* Khan Academy [Vector's Section](https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/vectors/v/vector-introduction-linear-algebra)

* Light read on [Stacking Classifier](https://rasbt.github.io/mlxtend/user_guide/classifier/StackingClassifier/)

* Implementing - Handeling missing values using pandas

* General read on [EM for data imputation](https://www.theanalysisfactor.com/em-imputation-and-missing-data-is-mean-imputation-really-so-terrible/)



## Day-14 (13th August, 2018)

* Read about [Model Evaluation](https://www.coursera.org/learn/ml-classification/home/week/6)

* See Khan Academy [Linear combinatations & span](https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/linear-combinations/v/linear-combinations-and-span) and [Linear Dependence/Independence](https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/linear-independence/v/linear-algebra-introduction-to-linear-independence)

* Explore a [Helper Lib](https://github.com/rasbt/mlxtend/)



## Day-15 (14th August, 2018)

* See Khan Academy [Subspaces](https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/subspace-basis/v/linear-subspaces)

* Practice [Mlxtend](https://github.com/rasbt/mlxtend/)

* Read/Practice [Day-33 & Day-34](https://github.com/Avik-Jain/100-Days-Of-ML-Code)



## Day-16 (15th August, 2018)

* Light read on [Vector Quantization](https://machinelearningmastery.com/learning-vector-quantization-for-machine-learning/)

* Reading about [Boosting Algorithms](https://www.youtube.com/watch?v=wPqtzj5VZus)

* See all videos under [Ensembling](https://www.coursera.org/lecture/competitive-data-science/introduction-into-ensemble-methods-MJKCi)



## Day-17 (16th August, 2018)

* Performance Metrics Hands-on

* Khan Academy [Vector dot products](https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/dot-cross-products/v/vector-dot-product-and-vector-length)

* See [Metrics Optimization](https://www.coursera.org/learn/competitive-data-science/home/week/3)



## Day-18 (20th August, 2018)

* General read on [Medium](https://medium.com/@ageitgey/natural-language-processing-is-fun-9a0bff37854e)

* Read about [Text Classification](https://medium.com/@ageitgey/text-classification-is-your-new-secret-weapon-7ca4fad15788)

* Read about [scrape method in Pandas](https://medium.com/@ageitgey/quick-tip-the-easiest-way-to-grab-data-out-of-a-web-page-in-python-7153cecfca58)

* Read about [FastText](https://research.fb.com/fasttext/)



## Day-19 (21st August, 2018)

* Glance through [Sklearn Docs on Feature Selection](http://scikit-learn.org/stable/modules/feature_selection.html)

* Read [Feature Selection - Analytics Vidhya](https://www.analyticsvidhya.com/blog/2016/12/introduction-to-feature-selection-methods-with-an-example-or-how-to-select-the-right-variables/)

* See [C2W1L4](https://www.youtube.com/watch?v=6g0t3Phly2M) and [C2W1L5](https://www.youtube.com/watch?v=NyG-7nRpsW8)

* Implementing Feature Selection Methods



## Day-20 (22nd August, 2018)

* Explore [A fast and simple progress bar](https://github.com/tqdm/tqdm)

* Casual read on [Pandas - Tips/Tricks - 1](https://cambridgespark.com/content/tutorials/quick-panda-tricks/index.html) and [Pandas - Tips/Tricks - 2](https://towardsdatascience.com/pandas-tips-and-tricks-33bcc8a40bb9)

* See [Day 35](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* Implement data resampling techniques



## Day-21 (23rd August, 2018)

* See all videos under [C2W2](https://www.youtube.com/watch?v=SjQyLhQIXSM&list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc&index=2)

* Implement saving/loading of ML models

* Write Dockerfile



## Day-22 (24th August, 2018)

* See and follow along [Introduction to PyTorch](https://www.youtube.com/watch?v=fJZew-fdNxw)

* Push Dockerfile and update Docker Readme.



## Day-23 (25th August, 2018)

* Read Chapter 6 (till 6.1.2) from the book Mining Massive Datasets

* Read/Practice [Day-26](https://github.com/Avik-Jain/100-Days-Of-ML-Code)



## Day-24 (26th August, 2018)

* Read Chapter 6 (till 6.1) from the book Mining Massive Datasets



## Day-25 (27th August, 2018)

* Read/Practice [Day-27](https://github.com/Avik-Jain/100-Days-Of-ML-Code) and [Day-28](https://github.com/Avik-Jain/100-Days-Of-ML-Code)



## Day-26 (28th August, 2018)

* See 1, 2, 3 videos from [Calculus](https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr)

* See [Week-1 (Video by David Silver)](https://github.com/yandexdataschool/Practical_RL/tree/master/week1_intro)



## Day-27 (29th August, 2018)

* Read about article on [RL 1, 2, 3, 4](https://medium.com/@prakhar.mishra)

* Implement randomised cartpole balancer



## Day-28 (30th August, 2018)

* Read [paper](https://arxiv.org/pdf/1808.07913.pdf)

* Implement neural network in PyTorch

* PyTorch + TensorBoard

* Update Docker File/Image



## Day-29 (31st August, 2018)

* See 4, 5, 6 videos from [Calculus](https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr)

* See 1, 2, 3, 4 videos from [Linear Algebra](https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)



## Day-30 (1st September, 2018)

* Implementing NN from scratch

* See 5, 6 videos from [Linear Algebra](https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)



## Day-31 (3rd September, 2018)

* Implement Cartpole using Cross Entropy method



## Day-32 (4th September, 2018)

* Read about Q-Learning.

* See 7, 8, 9 videos from [Linear Algebra](https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)

* See 7, 8 videos from [Calculus](https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr)



## Day-33 (5th September, 2018)

* Read/Practice [Day 51](https://github.com/Avik-Jain/100-Days-Of-ML-Code)

* See [But what *is* a Neural Network?](https://www.youtube.com/watch?v=aircAruvnKk&t=7s)

* Read [Grammar correction in text](http://ww.panl10n.net/english/final%20reports/pdf%20files/Bangladesh/BAN21.pdf) usecase



## Day-34 (6th September, 2018)

* See [How Neural Networks learn](https://www.youtube.com/watch?v=IHZwWFHWa-w&t=0s&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&index=3)

* Read [Text Summarization](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.19.5237&rep=rep1&type=pdf)

* See 10, 11 videos from [Linear Algebra](https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)

* Read [Neural Networks, Manifolds, and Topology](http://colah.github.io/posts/2014-03-NN-Manifolds-Topology/)



## Day-35 (7th September, 2018)

* Implement Q-Learning



## Day-36 (10th September, 2018)

* Complete [Equations/Graphs/Functions](https://courses.edx.org/courses/course-v1:Microsoft+DAT256x+2T2018/courseware/72190688919b4f72a3e81a7fdbc4ec19/be5df94381c74baf8fdd83c36f71e0f0/?child=first)

* See 9, 10 videos from [Calculus](https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr)

* See [What does Backpropagation really do ?](https://www.youtube.com/watch?v=Ilg3gGewQ5U&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&index=3)



## Day-37 (11th September, 2018)

* See [Backpropagation Calculus](https://www.youtube.com/watch?v=tIeHLnjs5U8&index=4&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi)

* See 1, 2, 3 from [Statistics - Khan Academy](https://www.youtube.com/watch?v=uhxtUt_-GyM&list=PL1328115D3D8A2566)



## Day-38 (12th September, 2018)

* Read 7 in [Assignments](https://mlcourse.ai/assignments)

* See 4, 5, 6 from [Statistics - Khan Academy](https://www.youtube.com/watch?v=uhxtUt_-GyM&list=PL1328115D3D8A2566)



## Day-39 (13th September, 2018)

* Read about Agglomerative Clustering



## Day-40 (14th September, 2018)

* Read about Deep-Q-Networks and understand epsilon-greedy, replay buffer and target network in the same context.

* See 7, 8 from [Statistics - Khan Academy](https://www.youtube.com/watch?v=uhxtUt_-GyM&list=PL1328115D3D8A2566)



## Day-41 (15th September, 2018)

* Read about Spectral Clustering

* See 9, 10, 11, 12 [Statistics - Khan Academy](https://www.youtube.com/watch?v=uhxtUt_-GyM&list=PL1328115D3D8A2566)

* Complete [Finance and Python](https://campus.datacamp.com/courses/importing-managing-financial-data-in-python/importing-stock-listing-data-from-excel)



## Day-42 (17th September, 2018)

* Read [Autoencoders Notebook](https://www.kaggle.com/shivamb/how-autoencoders-work-intro-and-usecases?utm_medium=social&utm_source=linkedin.com&utm_campaign=Weekly-Kernel-Awards)

* Complete [Week-1](https://www.coursera.org/learn/fundamentals-machine-learning-in-finance/home/week/1)



## Day-43 (18th September, 2018)

* See [Neural Voice Cloning](https://www.youtube.com/watch?v=gVehTbi6Ipc&feature=youtu.be)

* Complete [Week-2](https://www.coursera.org/learn/fundamentals-machine-learning-in-finance/home/week/2)

* Read [Autoencoder in Text](https://www.doc.ic.ac.uk/~js4416/163/website/nlp/)



## Day-44 (19th September, 2018)

* Read 1-10 pages of [A Primer on Neural Network Modelsfor Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-45 (20th Spetember, 2018)

* Read 11-20 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-46 (21st September, 2018)

* Read 21-30 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-47 (22nd Spetember, 2018)

* Read 31-40 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-48 (22nd Spetember, 2018)

* Read 41-50 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-49 (23rd September, 2018)

* Read 51-60 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)



## Day-50 (24th Spetember, 2018)

* Read 61-76 pages of [A Primer on Neural Network Models for Natural Language Processing](http://u.cs.biu.ac.il/~yogo/nnlp.pdf)