I have expertise in Data Analysis, Data Engineering, Machine Learning, Azure & GCP Cloud Services. I have present couple of end-to-end projects along with Documentation
Our goal is to look through this dataset and classify songs as being either 'Hip-Hop' or 'Rock' - all without listening to a single one ourselves. In doing so, we will learn how to clean our data, do some exploratory data visualization, and use feature reduction towards the goal of feeding our data through some simple machine learning algorithms, such as decision trees and logistic regression.
You are required to model the price of cars with the available independent variables. It will be used by the management to understand how exactly the prices vary with the independent variables. They can accordingly manipulate the design of the cars, the business strategy etc. to meet certain price levels. Further, the model will be a good way for management to understand the pricing dynamics of a new market.
The objective of this project is to classify whether patient has diabetes or not.Understood data first in order to apply feature selection. In order to understand data patter used the EDA concept which helped me find Handling Imbalanced Data, an outlier. Used the Logistic regression, Decision tree, KNN (k-nearest neighbors), SVM (support vector machine) methods and create pipelines in Scikit-learn. To evaluate the quality of the resultant data, used a classification report at the end.
Created an automated AWS EC2 instance running Nginx using Terraform and AWS CLI. Configured IAM user and AWS credentials to set up Nginx web server in a few simple steps. Deployed and accessed Nginx web server via the instance's public IP address. Demonstrated knowledge of AWS services and infrastructure as code principles through the project..
I utilized various NLP techniques such as tokenization, text-cleaning, regular expression, stop word removal, and stemming to pre-process the data. I then implemented RNN-LSTM technique and word embedding method to determine sentence similarity. Using TensorFlow and Keras API, I was able to achieve an accuracy rate of 82%. Overall, this project focused on solving a classification problem through NLP techniques and was implemented using Python and Google Colab.