This repository is a culmination of the Data Wrangling techniques I've learned through Udacity and is in no way an authoritative resource. Rather, it'll become a personal library.
Data provided as is.
Examples:
- Zip code has wrong datatype
- Contact info needs separating & formating
- Totals wrong
- Missing records
- Consolidation of data
- etc.
Notebook: cleaning-student.ipynb, .py should also be present as a clone
Data: data/patients.csv, data/adverse_reactions.csv, data/treatments.csv
The culmination of gathering & assessing data. The data contains a mock pharmeceutical study with ~400 patients who received 2 medications. One is insulin for diabetes treatment, administered intravenously. The other is insulin that can be taken with a pill. It's a study to determine the efficacy of the oral insulin.