bigdatasciencegroup / chrome-bookmarks-analysis-using-nltk-python Goto Github PK

This project forked from kalyanparimi/chrome-bookmarks-analysis-using-nltk-python

Projects IoT Device Temperature Analysis for Home Automation Jul 2020 – Present Project descriptionIIoT 4.0 is coming to cover all enterprise monitoring and maintenance systems. Thus, we need bold and sustainable algorithms and approaches to analyze the IoT sensor data and find hidden patterns and insights. Heat Index ( temperature + humidity ) is one common data recorded on these IoT readers. The frequency of the upcoming data is very fast. The sensor reads hundreds to millions of data per second. There is a huge and versatile application of this data in the real world. like:- Agriculture, weather forecasting, soil monitoring and treatment, enterprise maintenance, Data centers, and many more. The dataset contains the temperature readings from IoT devices installed outside and inside of an anonymous Room (say - admin room). The device was in the alpha testing phase. So, It was uninstalled or shut off several times during the entire reading period ( 28-07-2018 to 08-12-2018). This random interval recordings and few misreadings ( outliers) makes it more challenging to perform analysis on this data. Let's see, what you can present in the plate out of this messy data. Chrome Bookmarks Analysis using NLTK Python Jun 2020 – Present Project descriptionIn this project, I exported all my chrome bookmarks since the year 2015 till 2020, performed Exploratory Data Analytics on it and cleaned my own data using various packages. In this process, I cleaned bookmarks such which had e-Commerce tags such as Amazon, Flipkart etc. Post EDA, I performed basic aggregations on the data to understand where I spent most of my time. Labelling & Classifying each tech buzz word in my bookmarks, I visualized an entire data of 5 years and obtained insights on the Programming languages and resources that I was reliant on most of the time. This gave me a new insight towards my learning curve and how I relied mostly on PDF's and preferred videos after going through content PDF. A self-assessment. Right now I am working on how to use sci-kit to predict the fruitfulness of my learning curve ahead of time.