jerrywang0928 Goto Github PK

311_pothole_complaints_data_warehouse

Taking a look at 311 complaints, we can see that a majority of the complaints are about street conditions, unsanitary conditions, and plumbing issues- all which could be considered an infrastructure issue. One particular type of problem that NYC faces that we hope to address is its street conditions, racking up a total of 93,270 complaints to 311 in just the year 2017 alone. As citizens who ride on the streets of New York daily and are frustrated with the conditions, we as data analysts were determined to figure out why the street or road conditions were so bad. We plan to use Street Pothole Work Orders and/or a weather dataset in combination with the street conditions complaints from 311 to dig deeper into the issue.

api_football_parser

chrome-extensions

All the Chrome Extensions from the Youtube tutorial series!

covid_sql_queries

cs224n-reading-notes

CS224n Reading Notes in Chinese 中文阅读笔记

csv_to_gbq_automation

Python script that automates CSV file imports to a Google BigQuery database

customer-clustering

Identify and Recommend Top 1000 Customer to Target from Datasets

data-glacier

Data Glacier Project Internship

day_2_exercise

day_2_exercise_1

dbt

Database ELT tool

ds_learning

Source for self-paced DS learning path

fake-news-detection

Fake News Detection using Machine Learning Algorithm i.e naive Bayes. Model-2 Contains the same thing as LSTM.

gafa-stock-analysis

The project is GAFA stock analysis. [GAFA: Alphabet (GOOG), Amazon (AMZN), Facebook (FB), and Apple (AAPL)]. We are going to try to analyze the stock prices of GAFA over the last 5 years. We will come to a conclusion about how they performed, the corelation between each of these four companies, which one earned the most profit, which one was most stable.

hr_analytics

What is the problem? As the HR department in big data companies, it’s important to know which of current employees are planning to leave the company, the reason behind it and takes corresponding actions. How can we do it? The goal of this task is building model(s) that uses the current credentials, demographics, experience to predict whether a current employee is looking for a new job or not. It’s a classification problem. It helps to prevent the loss of precious human resources, feedback of the company current working environment and gives guidance in the future recruiting.

learn_git

mlops-with-aws-datascientists

Practical MLOps for Data Scientists , Machine Learning & DevOps Engineers - Implement MLOps - Deploy Models and Operate

my-second-repo

recommendation-system-for-fashion-products

Applied machine learning group project on H&M dataset

singapore-condo-rental-market-analysis

Singapore Condo Rental Prices - From Data Acquisition to Prediction

test

test

us-covid-19-prediction

Please visit: https://www.kaggle.com/jerrywang96/us-covid-19-eda-exponential-arima-prediction

zhe-wang.github.io