My work projectsr for the Nodegree. Including:
The primarily goal of the project is to get started with data analysis--- extract data, visualized data and analyze datat. Use basic SQL query to extract the temperature data of my city, and make charts visualization to compare and make observation.
In this project, I wrote a Python script to create an interactive exprience in the terminal to present statistics for US Bikeshare Data in three major cities. Through the interactive exprience, user would get summary statistics of bike share systems in Chicago, New York City, or Washington.
In this project, I analyzed the TMDb movie dataset by using Python libraries NumPy, pandas, and Matplotlib. The dataset, which is originally from Kaggle, was cleaned and provided by Udacity. The dataset contains 5000+ movies basic information and some metrics that measured can be classified how successful these movies are. These metrics include popularity, revenue and vote average. Basic information are like cast, director, keywords, runtime, genres, etc. The goal for this project is to go through the general data analysis process project. And the research I investigated is focus on finding properties are associated with successful movies as well as some interesting trends like keywords trends by generation.
Link to my blog article for the project
In this project, I demonstrated a A/B Test for a e-commerce company's website to decide whether they should implement their new page or keep the old page. Using the data with groups of control, treatment and their conversion, I performed the two-tailed hypothesis test and regression approach to determine results. The technique was primary using Python and I used the Boostrate Sampling method to perform the hypothesis test. Besides, I also demonstrated z-test to comoare the results. The regression method was Logit Regression, and the goal was to see if there is a significant difference in conversion based on which page a customer receives.