A Very Good Data Science Course in Python by Harvard

machine_learning
ipython
data_science
python
mooc

#1

Lectures and Slides
[Page on harvard.edu][1]
[Slides][2]

Assignments
Intro to Python, Numpy, Matplotlib ([Homework 0][3]) ([Solutions][4])
Poll Aggregation, Web Scraping, Plotting, Model Evaluation, and Forecasting ([Homework 1][5]) ([Solutions][6])
Data Prediction, Manipulation, and Evaluation ([Homework 2][7]) ([Solutions][8])
Predictive Modeling, Model Calibration, Sentiment Analysis ([Homework 3][9]) ([Solutions][10])
Recommendation Engines, Using Mapreduce ([Homework 4][11]) ([Solutions][12])
Network Visualization and Analysis ([Homework 5][13]) ([Solutions][14])

Labs
[Lab 2: Web Scraping][15]
[Lab 3: EDA, Pandas, Matplotlib][16]
[Lab 4: Scikit-Learn, Regression, PCA][17]
[Lab 5: Bias, Variance, Cross-Validation][18]
[Lab 6: Bayes, Linear Regression, and Metropolis Sampling][19]
[Lab 7: Gibbs Sampling][20]
[Lab 8: MapReduce][21]
[Lab 9: Networks][22]
[Lab 10: Support Vector Machines][23]

Also,You would need to install [The Anaconda Package][24].

KUDOS!!
[1]: http://cm.dce.harvard.edu/2014/01/14328/publicationListing.shtml
[2]: https://drive.google.com/folderview?id=0BxYkKyLxfsNVd0xicUVDS1dIS0k&usp=sharing
[3]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW0.ipynb
[4]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW0_solutions.ipynb
[5]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW1.ipynb
[6]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW1_solutions.ipynb
[7]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW2.ipynb
[8]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW2_solutions.ipynb
[9]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW3.ipynb
[10]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW3_solutions.ipynb
[11]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW4.ipynb
[12]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW4_solutions.ipynb
[13]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW5.ipynb
[14]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/HW5_solutions.ipynb
[15]: https://github.com/cs109/content/tree/master/labs/lab2
[16]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab3/lab3full.ipynb
[17]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab4/Lab4full.ipynb
[18]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab5/Lab5.ipynb
[19]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab6/BayesLinear.ipynb
[20]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab7/GibbsSampler.ipynb
[21]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab8/lab8_mapreduce.ipynb
[22]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab9/lab_9.ipynb
[23]: http://nbviewer.ipython.org/urls/raw.github.com/cs109/content/master/labs/lab10/Lab_10.ipynb
[24]: http://continuum.io/downloads


#2

Thank you for the rec., Rohan.

P.S.: You can opt for Miniconda for a minimal, customised installation of the packages.


#3

Rohan,

This is one of the best course indeed. We have picked up the best and relevant parts of the course and mixed it with a few hands on exercises and a few other missing parts to help people further. You can check out our learning path here: