kulwinderkk

Big_data_Wrangling_GoogleNgram_data_analysis

Loaded, filtered and visualized Google Ngrams dataset, which was created by Google's research team by analyzing all of the content in Google Books from the 1800s into the 2000s, in a cloud-based distributed computing environment using Hadoop, Spark, and the AWS S3 file system.

bixi_data_analysis

Analysis of Bixi Data

data-analysis-mass-shooting-us-plotly-dash

Dash App and Interactive Plotly Charts analyzing US Mass Shooting Data

esg_risk_variable_eda_datapipeline

In this repository, exploratory data analysis was performed on the ESG risk variable particularly temperature, precipitation and wildfire datasets downloaded from Copernicus website.

IBM_deepsearch_json_parsing

PDF Parsing using IBM DeepSearch

kulwinderkk.github.io

Personal portfolio website hosted using GitHub pages.

ner_experimentation

Experimenting with various approaches to NER.

recipe_recommender_nlp

This project is an unsupervised NLP-based recipe recommender system designed to provide personalized recipe suggestions. The system employs content-based filtering techniques, utilizing cosine similarity to measure the resemblance between user inputs and a database of recipes.

Sales-forecast-for-Brazilian-ecommerce-startup-olist

In this project I have tried different approaches to Sales forecast like SARIMAX, Facebook's Prophet, LSTM and XG Boost Regression. I have tried to optimize each of these models to get the best sales forecasting model suitable for Olist' limited historical data.

statistical_analysis_of_WNV_data

kulwinderkk/recipe_recommender_nlp

This project is an unsupervised NLP-based recipe recommender system designed to provide personalized recipe suggestions. The system employs content-based filtering techniques, utilizing cosine similarity to measure the resemblance between user inputs and a database of recipes.

kulwinderkk/Big_data_Wrangling_GoogleNgram_data_analysis

Loaded, filtered and visualized Google Ngrams dataset, which was created by Google's research team by analyzing all of the content in Google Books from the 1800s into the 2000s, in a cloud-based distributed computing environment using Hadoop, Spark, and the AWS S3 file system.

kulwinderkk/bixi_data_analysis

Analysis of Bixi Data

kulwinderkk/data-analysis-mass-shooting-us-plotly-dash

Dash App and Interactive Plotly Charts analyzing US Mass Shooting Data

kulwinderkk/esg_risk_variable_eda_datapipeline

In this repository, exploratory data analysis was performed on the ESG risk variable particularly temperature, precipitation and wildfire datasets downloaded from Copernicus website.

kulwinderkk/IBM_deepsearch_json_parsing

PDF Parsing using IBM DeepSearch

kulwinderkk/kulwinderkk.github.io

Personal portfolio website hosted using GitHub pages.

kulwinderkk/ner_experimentation

Experimenting with various approaches to NER.

kulwinderkk/Sales-forecast-for-Brazilian-ecommerce-startup-olist

In this project I have tried different approaches to Sales forecast like SARIMAX, Facebook's Prophet, LSTM and XG Boost Regression. I have tried to optimize each of these models to get the best sales forecasting model suitable for Olist' limited historical data.

kulwinderkk/statistical_analysis_of_WNV_data

kulwinderkk/structify_take_home_assignment

Take home assignment to calculate number of intersection for given number of chords.

kulwinderkk/webscraping

Webscraping PDFs using Selenium and scraping content from Power BI dashboard embedded on the webpage.