Difference between revisions of "ANLY482 AY2017-18 T1 Group1: Project Findings"
Jump to navigation
Jump to search
| Line 33: | Line 33: | ||
Since we are awaiting signing of the NDA, we have not received the data from our sponsors yet. However, the initial steps we will undertake upon receiving the data are as follows: | Since we are awaiting signing of the NDA, we have not received the data from our sponsors yet. However, the initial steps we will undertake upon receiving the data are as follows: | ||
| + | |||
| + | [[File:Data Steps.png|700 px|centre|]] | ||
| + | |||
| + | <br /> | ||
| + | |||
| + | * Understanding the data using metadata | ||
| + | * Data Cleaning to check for mistakes, handle missing values, remove outliers, standardize formatting and integrate datasets if needed. | ||
| + | * Exploratory Data Analysis to extract important variables, look for patterns, test our hypothesis and determine relationships across variables. | ||
| + | * Data Transformation by creating metrics and using techniques such as binning if needed | ||
Revision as of 17:20, 14 January 2018
Methodology
Since we are awaiting signing of the NDA, we have not received the data from our sponsors yet. However, the initial steps we will undertake upon receiving the data are as follows:
- Understanding the data using metadata
- Data Cleaning to check for mistakes, handle missing values, remove outliers, standardize formatting and integrate datasets if needed.
- Exploratory Data Analysis to extract important variables, look for patterns, test our hypothesis and determine relationships across variables.
- Data Transformation by creating metrics and using techniques such as binning if needed
