Pinned Repositories
recommender-system
This project aims to implement collaborative filtering-based recommender, content-based recommender and hybrid recommender for movie recommendation. The algorithms are also evaluated using different evaluation metrics and the results are compared.
Bitcoin_Price_Prediction
Cryptocurrencies have been trending for a while now, this project aims to help businesses and individuals access the risks and rewards of entering the markets, by giving them a tool to forecast the price of Bitcoin using sentiment analysis and price prediction using historical data. The proposed method combined Historical Data Analysis (Investing.com) and Sentiment Analysis (Twitter) to predict future trend of cryptocurrency.
Player-Performance-Improvement-Prediction
We designed a platform where users can get accurate predictions of players' DraftKings score for the next NBA game. The project is developed using Long Short-Term Memory (LSTM) model that provides precise predictions for the given problem. A web application offers a convenient user experience to search for a specific player’s predicted score.
Internet-Sales-Insights
This project was develop to understand end-to-end business problem and solve it using MS SQL Server and Power BI.
basic-weather-web-app
The project was developed as a part of curriculum and it was just to get familiar with basic web development in CI environment. We designed a simple weather web application that shows current date, time and weather details of Toronto city. The tools we used were: Angular, TypeScript, Netlify, and Buddy.Works.
Data-Structures-and-Algorithms-Python
Practicing data structures and algorithms with Python.
Exemplar-Based-Image-Inpainting
• Image inpainting is the process of seamlessly filling in holes of arbitrary topology in an image to preserve its overall continuity. It is an ancient art of fixing accidental damage and recreating lost information. • Object removal or modification in the original images can be carried out through image inpainting methods. • In this project, various algorithms of Partial Derivative Equation based and Exemplar-based families have been studied and implemented. Results using Total Variation (TV) and Curvature Driven Diffusion (CDD) methods show that CDD produces a better visual quality of results. However, it fails to restore texture information. • To solve this problem, Exemplar-based algorithms are studied and implemented. Traditionally, the data term present in this algorithm is based on the strength of the isophote found using the gradient. The problem with the gradient operator is studied, and a better contour preserving data term is proposed. The proposed data term uses the strength of structure line found using Infinite size Symmetric Exponential Filter (ISEF). This filter helps overcome the drawback of which overcomes the drawback of insensibility to noise and precision of edge localization present in traditional data term. • Results are compared by quantitative analysis using PSNR, SSIM, and FSIM. Subjective analysis is done using Mean Opinion Score. It is proved that the proposed method produces better visual results compared to few other existing exemplar-based methods. • Methods/Keywords: Exemplar-based Image Inpainting, PDE-based Image Inpainting, ISEF Filter, Priority Computation, Isophote, Curvature Driven Diffusion • Software/Tools/Programming Language Used: MATLAB, C
Medical-Appointment-Presence-Prediction
To analyze whether the patients who made the appointment will show up or not. • Data acquisition and cleaning • EDA – bar graphs, box plot, pie-chart • Data manipulation and treating categorical features • Train-Test Split • Models tested – KNN, Gaussian Naïve Bayes, Decision Tree Classifier, Random Forest, Gradient Boosting Classifier • Comparing models using performance metrics such as Area under ROC, Accuracy, Precision, Recall and Specificity • Software/Tools/Programming Language Used: Python, NumPy, Pandas, Matplotlib, Plotly
accenture-data-analytics
Bird-Classification-Using-ResNet
Bird identification is a difficult task due to limited visual abilities for humans. However, using computers and neural networks, bird recognition can be performed reliably and easily. The idea of this assignment is to implement bird classification problem using pre-trained ResNet models and compare the performance of different models such as ResNet34, ResNet50 and ResNet152 with respect to different number of epochs.
pratikgirigoswami's Repositories
pratikgirigoswami/Exemplar-Based-Image-Inpainting
• Image inpainting is the process of seamlessly filling in holes of arbitrary topology in an image to preserve its overall continuity. It is an ancient art of fixing accidental damage and recreating lost information. • Object removal or modification in the original images can be carried out through image inpainting methods. • In this project, various algorithms of Partial Derivative Equation based and Exemplar-based families have been studied and implemented. Results using Total Variation (TV) and Curvature Driven Diffusion (CDD) methods show that CDD produces a better visual quality of results. However, it fails to restore texture information. • To solve this problem, Exemplar-based algorithms are studied and implemented. Traditionally, the data term present in this algorithm is based on the strength of the isophote found using the gradient. The problem with the gradient operator is studied, and a better contour preserving data term is proposed. The proposed data term uses the strength of structure line found using Infinite size Symmetric Exponential Filter (ISEF). This filter helps overcome the drawback of which overcomes the drawback of insensibility to noise and precision of edge localization present in traditional data term. • Results are compared by quantitative analysis using PSNR, SSIM, and FSIM. Subjective analysis is done using Mean Opinion Score. It is proved that the proposed method produces better visual results compared to few other existing exemplar-based methods. • Methods/Keywords: Exemplar-based Image Inpainting, PDE-based Image Inpainting, ISEF Filter, Priority Computation, Isophote, Curvature Driven Diffusion • Software/Tools/Programming Language Used: MATLAB, C
pratikgirigoswami/Bitcoin_Price_Prediction
Cryptocurrencies have been trending for a while now, this project aims to help businesses and individuals access the risks and rewards of entering the markets, by giving them a tool to forecast the price of Bitcoin using sentiment analysis and price prediction using historical data. The proposed method combined Historical Data Analysis (Investing.com) and Sentiment Analysis (Twitter) to predict future trend of cryptocurrency.
pratikgirigoswami/Medical-Appointment-Presence-Prediction
To analyze whether the patients who made the appointment will show up or not. • Data acquisition and cleaning • EDA – bar graphs, box plot, pie-chart • Data manipulation and treating categorical features • Train-Test Split • Models tested – KNN, Gaussian Naïve Bayes, Decision Tree Classifier, Random Forest, Gradient Boosting Classifier • Comparing models using performance metrics such as Area under ROC, Accuracy, Precision, Recall and Specificity • Software/Tools/Programming Language Used: Python, NumPy, Pandas, Matplotlib, Plotly
pratikgirigoswami/Player-Performance-Improvement-Prediction
We designed a platform where users can get accurate predictions of players' DraftKings score for the next NBA game. The project is developed using Long Short-Term Memory (LSTM) model that provides precise predictions for the given problem. A web application offers a convenient user experience to search for a specific player’s predicted score.
pratikgirigoswami/accenture-data-analytics
pratikgirigoswami/basic-weather-web-app
The project was developed as a part of curriculum and it was just to get familiar with basic web development in CI environment. We designed a simple weather web application that shows current date, time and weather details of Toronto city. The tools we used were: Angular, TypeScript, Netlify, and Buddy.Works.
pratikgirigoswami/Bird-Classification-Using-ResNet
Bird identification is a difficult task due to limited visual abilities for humans. However, using computers and neural networks, bird recognition can be performed reliably and easily. The idea of this assignment is to implement bird classification problem using pre-trained ResNet models and compare the performance of different models such as ResNet34, ResNet50 and ResNet152 with respect to different number of epochs.
pratikgirigoswami/Customer-Service-Management
• The aim of this project is to develop a Customer Management System (CMS) which is one of the systems included in Enterprise Resource Planning (ERP). • The objective of the project is to build a system that can help businesses to decrease the defection rate in billing and in turn enhance customers’ experience. • This project not only improves the speed of billing but also keeps track of existing customers. • The project includes several modules such as customer addition, customer modification, customer identification, and billing information. • Each customer’s information is stored in a database using MySQL. Customer identification and modification help keep track of customers’ purchase history. • Billing module assists employers in entering and displaying billing amounts for the customer. • Software/Tools/Programming Language Used: Python, MySQL.
pratikgirigoswami/Data-Structures-and-Algorithms-Python
Practicing data structures and algorithms with Python.
pratikgirigoswami/EDA-of-UCI-Adult-Dataset
This project was aimed to practice exploratory data analysis for the defined dataset to get insights of data. The tasks performed were as per following: • Data acquisition of UCI Adult Dataset • Pre-processing – Imputation, Heatmap • EDA – Visualizing different graphs for understanding relationships among data components • Preparation for classification – label encoding, one-hot encoding, Train-Test Split • Model selection – KNN • Evaluation – prediction, confusion matrix, accuracy • Software/Tools/Programming Language Used: Python
pratikgirigoswami/Finance-BI
pratikgirigoswami/Internet-Sales-Insights
This project was develop to understand end-to-end business problem and solve it using MS SQL Server and Power BI.
pratikgirigoswami/Movie-Critique-System
People have been widely using online platforms such as blogs, websites, discussion forums, and other types of social media to provide feedback on various products and services. In this project, we designed a system that can summarize movie reviews and provide a summarized critique to help the user make the decision easily without going through plenty of reviews from different people. We have proposed a method that uses supervised learning for the binary classification of movie reviews.
pratikgirigoswami/Python-Practice-Codes
This repo includes the python exercises and their solutions.
pratikgirigoswami/recommender-system
This project aims to implement collaborative filtering-based recommender, content-based recommender and hybrid recommender for movie recommendation. The algorithms are also evaluated using different evaluation metrics and the results are compared.
pratikgirigoswami/Sales-BI-Practice
pratikgirigoswami/Sales-Tableau-Practice
pratikgirigoswami/Simple-ML-Templates
This repository contains simple templates for various ML algorithms. This is just for quick practice to have a look at different ML methods.
pratikgirigoswami/sql-mini-project
Self learning project for practicing SQL.
pratikgirigoswami/typing-assistant
Predicting the next word while user is typing is also called Language Modeling. It is one of the major tasks of Natural Language Processing (NLP) and has numerous applications. In this project, the idea of transfer learning to predict the next word from the typed words is employed. The proposed method is based on Long Short-Term Memory (LSTM) model. The Graphical User Interface (GUI) is also developed for better user experience where a user can type at least three words and get suggested next word on the same interface.