TensorFlow is mainly developed by Google and released under open source license. We can easily access Tensorflow in Python to create Deep Learning models. I had to use Keras library for Recurrent Neural Networks and found that I need to install Tensorflow to use Keras. I really found the process very tough. For people like me who has very less knowledge about Python or pip or conda, it was a nightmare. Finally, I could solve the issue and installed the package successfully but had to read hundreds of articles and followed more than 10-15 methods, installed Anaconda more than 7-10 times to get the right version. As I have faced all these issues and installed it successfully, I thought of writing about it. Also, one of my dearest friends keeps me pushing to write a blog at least once a week so hopefully this will help me. Though there are hundreds of articles and there is very less chance that my blog would appear in Google search like other articles, but it is worth sharing and writing.
Continue reading →
Few years back, I was working on a Demand forecasting project where I was dealing with thousands of combinations of Brand-SKU-Store combination. The challenge was to improve existing accuracy to provide better forecasts of each SKU at a store level. Even if you are dealing with 100 SKUs and 200 stores there will be 20,000 combinations and you can’t selectively pick a model for each combination. We tried various individual techniques such as ARIMA, ETS, UCM, NN, and many more but couldn’t meet the accuracy benchmark. Then one of my seniors introduced me to the OPERA package and asked me to research and optimize it for our needs. I successfully implemented it and today I will talk about the same package with detailed R code. Continue reading 
In Data Science visualization is a powerful tool. You can’t sell a concept but a product. Data analytics is science but presenting them through different graphs and charts is an art. We have many ways to present the numbers and a lot of software which make our life easy. Few of them which I have tried are Tableau, R Shiny, D3, QlikView and VBA Dashboard. Every tool has its own advantages and properties. Currently, I am working on R Shiny dashboard which is so beautiful and easy to learn. I would really encourage you to learn R Shiny if you do coding in R. It has a lot of in-built packages which can easily be deployed. Today let’s work on cascading filters one of the most important kinds of filters. Every other filter is connected to the predecessor filter. 
As being a data scientist, plotting data is one of the first things we generally do. Without studying the behavior of the data we can’t or rather should not move ahead. There can be a lot of analysis which we can perform by plotting the graphs for example univariate, bivariate and residual plots. In my earlier blog, I wrote about how to plot two graphs in the same plot using par () function in R which is very useful when we do bivariate analysis and want to see the behavior of 2 variables across different time duration. Today I will write how to export the plots in PDF and in a tabular format. Generally exporting plots in any format (JPG, PDF) is an easier task but when you have say 50 graphs, you won’t want 50 pages, rather you will want 4 graphs in one page which will be very easier to read or interpret. 
We as data analyst always have to do basic EDA or data manipulating before sorting the variable for developing any model. One of the first steps that we follow in EDA is bi-variate analysis. I will not go into details how or why we do bi-variate analysis, as you must know already and just want to learn how to plot 2 graphs in the same plot area in R. So let’s get started. I simply wrote an R code with comments to understand each step. Please check out the code below and comment if any step is not clear. Good luck. 
Topbullets - A Digital Notebook 