DAND Project 4 - Analyze A/B Test Results
A/B tests are very commonly performed by data analysts and data scientists. It is important to get some practice working with the difficulties of these. For this project, the goal is to understand the results of an A/B test run by an e-commerce website. Work through this notebook to help the company understand if they should implement the new page, keep the old page, or perhaps run the experiment longer to make their decision.
This project uses NumPy, Pandas, Matplotlib, and Jupyter Notebooks to analyze a dataset and communicate findings. A dataset curated by Udacity will be utilized.
This project was created and tested on Windows 10 64bit using Python 3.6.5 32bit and the following libraries:
- NumPy 1.14.3
- Pandas 0.22.0
- Matplotlib 2.2.2
- Jupyter 1.0.0
- IPykernel 4.8.2
- IPython 6.3.1
- Jupyter-client 5.2.3
- Jupyter-core 4.4.0
- IPywidgets 7.2.1
- nbformat 4.4.0
- traitlets 4.3.2
- widgetsnbextension 3.2.1
- notebook 5.4.1
- Jupyter-console 5.2.0
- nbconvert 5.3.1
- Install Python
- Note 1: Due to the features used, Python v3.6 or later is required
- Install NumPy, Pandas, Matplotlilb, and Jupyter Notebook
- Download the Udacity curated project data
- Clone this repo
- From the repo's Proj4 directory, run:
jupyter notebook - From Jupyter, open
Analyze_ab_test_results_notebook.ipynb
- Using the provided notebook, complete the analysis
- The following resources were used in coming up with the solution for this project:
- StackOverflow
- StackExchange
- NumPy, Pandas, StatsModel documentation
- Project 4 - Analyze ab test results notebook - Jupyter Notebook for project
- Project 4 - Analyze ab test results HTML web page - Web Page (HTML) from converted Jupyter Notebook project