Repositorio para la competición de Kaggle Intel & MobileODT Cervical Cancer Screening. Predict which cancer treatment will be most effective?

Aspect based sentiment analysis is the determination of sentiment orientation of different textual review or post based on the aspect terms associated with that review or post. After pre-processing the data, classification report is obtained for multiple ML and Neural Network Models on training data-set and the best among them is then used for c…

My side project about Data Scientist

Comparing and finding the best model to predict the Status of a Loan Application.

Analyzing the spread of COVID-19 in India. Emphasized on the usage of data visualization and data preprocessing and drawing a final report based on the accuracy of the analysis.

Analyzing the HR Criteria of a Company and how they promote their Employees and keep Balance between them using Data Analytics, Data Visualizations, and Machine Learning Models for Classification Purposes.

Scripts developed for the "Knowledge Extraction and Machine Learning" (ECAC) class "To Loan or Not To Loan" data mining case study / Kaggle competition.

useful python scripts for data preprocessing

Manipulation of time series data and forecast CAD/USD currency using commodities

Code snippet for different machine learning and deep learning techniques for model building, feature engineering, missing value imputation, EDA, and data reading/pulling/extraction/cleaning.

HDB flats resale price prediction. Neural network in Python. Machine learning models in R. Data pre-processing, feature engineering and feature selection mainly in R.

Novel based movies dataset creation

A pharmacokinetic model for predicting propofol concentration in a patient's body

Predicts the risk of Cardiovascular disease among patients using Machine Learning and Deep Learning techniques. Data Mining techniques are used to extract and analyse the information from the clinical records of the patient.

a Practical application on Data Cleaning and Preprocessing Using NumPy Package

In this project, I worked on a classification problem using an imbalanced dataset which predicts ecological footprints. The aim of the project was not necessarily to build a classification model but to investigate the different methods of correcting an imbalanced dataset in order not to build a biased classifier

NLP project to classify toxicity of tweets and comments on Twitter

Engine for automated the process of scraping PDFs into local and convert those PDFs into text by performing OCR.