yang5hi Goto Github PK

50_javascript_projects

ant-learn-pandas

pandas学习课程代码仓库

api_webcrawler

big-data-amazon-review

This project is analyzing amazon reviews on video games and luggage. Each dataset contains over 1.5 million rows. The ETL process was performed completely in the cloud, and the DataFrame was uploaded to an RDS instance. Basic statistical analysis was also performed on one of the datasets.

boardgame-analysis

BoardGameGeek is a valuable resource for boardgame information. We built a webpage to visualize the data related to board games. Using machine learning, we predict board game ratings based on 10 independent variables.

boardgame-dashboard

We built a webpage to visualize the data related to board games. The page scrapes and loads the latest news, and uses SQL database to load the data, and javascript to visualize the filtered information.

boardgame_ratings

We explored the BoardGameGeek dataset. Using machine learning, we predict board game ratings based on 10 independent variables.

climate-analysis-of-honolulu

Climate Analysis of Honolulu, Hawaii

data-journalism-and-d3

I used JavaScript to create charts, graphs, and interactive elements to help readers understand the health risks facing particular demographics.

etl_tax_school_ohio

Education and housing are closely related to our socio-economic life. In this project, we extracted data on those fields from three different resources: Ohio Tax Information, Census API on Social (DP02), Economic(DP03), and Housing(DP04) Characteristics of Ohio (state:39) Counties (88 total), and Greatschools.org. The gathered data will then be cleaned and transformed into a PostgreSQL database.

fintech

FinTech_Upskill

healtchare_fraud_detector

Healthcare provider fraud detector is a classification machine learning project to predict the potential fraudulent providers based on the healthcare claims filed.

healthcare_fraud_provider_detector_webapp

Flask app is created to be used as API to predict the fraudulent healthcare provider based on information gathered.

healthcare_provider_fraud_detection_collab

Binary classification to detect fraudulent providers using logistic regression, XGBclassifier, randomforestclassifier.

leaflet-usgs

In this project, I used leaflet to visualize the United States Geological Survey (USGS) past 30 days M4.5+ earthquakes dataset. I created layers of maps with circles represent all of the earthquakes from this data set based on their tectonic plates, longitude, latitude, depth, and magnitude.

machine-learning-basics

This project is to study the NASA Kepler space telescope data based on a planet-hunting mission. I created several machine learning models that are capable of classifying candidate exoplanets from the raw dataset.

machine_learning_journal

matplotlib-challenge

Matplotlib

pandas_basics

Pandas

pitch_pyfect

In this project, we mined through the SpotifyⓇ music database and identified the optimal ranges of music theory and song structure—for example, key signature, beats per minute, beats per measure, tempo, etc.

plotly_bio

I built an interactive dashboard to explore the microbes that colonize human navels. The plots used here are bar, pie, and gauge with data selection from a dropdown menu.

python-api-challenge

weather API, Google Places API

python_basics

Python basics

sql-challenge

pgAdmin, postgreSQL, sqlalchemy

ufo_sightings

vba-challenge

Stock market analysis using BVA

web-design-challenge

HTML CSS Bootstrap 4.6

web-scraping-missions-to-mars

I scraped the NASA Mars News Site, JPL Featured Space Image website, Mars Facts webpage, and USGS Astrogeology site to obtain news titles, news content, tables, and high-resolution images. The information was stored in MongoDB and deployed to an HTML page with a flask application.

zihaopython

follow me and learn python easily