Facebook’s Analysis on Relationships

Facebook ran a series of blog entries about relationships for Valentine's Day in 2014. Here they are: the latest and greatest data on love from people who love data. Love and Religion The Age of…

How to choose a Machine Learning algorithm

This post is taken from Microsoft's blog and gives a good approach on the dilemma of algorithm selection. Considerations when choosing an algorithm Accuracy Getting the most accurate answer possible isn't always necessary. Sometimes an…

A hypothesis of life

At any point of time we have x number of possibilities for a given action. The action can be a random variable or a calculated variable. The logic which is used to calculate the variable…

How to train your Neural Network

[latexpage] The value of a neural network lies in its hyper-tuning. General intuition The VA(validation accuracy) of your NN(Neural network) is always going to be less than TA(train accuracy). So if the maximum TA it…

Sentiment Analysis – Part 1

Sentiment Analysis is the use of natural language processing to determine the polarity of a public opinion, whether it is negative, positive or neutral. Such analysis can help organizations gain insights on current trends and…

Recommendation Algorithms – Part 1

[latexpage] Imagine you love to read books and don't have a friend to suggest one. How do you find out books pertaining to your taste? One way is to Google and read descriptions and reviews…

NLTK Vs Spacy Vs Stanford CoreNLP

POS(Part of  Speech) and NER(Named Entity Recognition) are one of the most important tasks in NLP. It's important to select a library which can perform these tasks with high accuracy and low latency for real…

Best Python libraries for Data Science

It's not debatable to say that it's always good to know libraries in case of a need. Core libraries that you have to start with Pandas Numpy Scikit Matplotlib Seaborn Jupyter notebook - For interactive Python (Highly…

Handling missing data with Pandas

Real data is always imperfect and requires cleaning. Our desired prediction algorithm can work well only if it is fed with the right data. Hence, preprocessing of data is of utmost importance and it also…