Relative Importance Calculator
Introduction
Key driver analysis is a popular and powerful tool in marketing research to quantify the relative importance of individual drivers in predicting an outcome variable. For example, marketing researchers conduct key driver analysis using customer experience survey responses to understand which aspects of the customer experience would drive the customer overall satisfaction the most.
As drivers are often highly correlated with each other, typical multiple regression analysis would produce flawed indicators of driver importance. Instead, we adopt the relative weight analysis approach which accurately partitions variance among the correlated drivers.
The Relative Importance Calculator produces the raw and normalized relative importance by driver for a specified outcome variable. The sum of the raw relative importance equals R-squared (i.e. the total proportion of variation in the outcome variable that can be explained by all the drivers) and the sum of the normalized relative importance equals one.
Prerequisite
To use the Relative Importance Calculator, you need to have pandas and NumPy installed.
Installation
Install the Relative Importance Calculator from PyPI:
pip install relativeImp
Input and Output
The Relative Importance Calculator takes three mandatory input parameters and returns a pandas DataFrame:
Input Parameters:
df: pandas.core.frame.DataFrame
Raw input data, e.g. survey responses
outcomeName: str
Name of the single outcome variable, e.g. overall satisfaction scores
driverNames: list
Names of the driver variables, e.g. satisfication drivers such as quality, ease of use etc.
Output:
pandas.core.frame.DataFrame with three columns:
driver: names of the driver variables
rawRelaImpt: the raw relative importance whose sum equals R-squared
normRelaImpt: the normalized relative importance whose sum equals one
Example Code
import pandas as pd
from relativeImp import relativeImp
df = pd.read_excel("raw_survey_responses.xlsx")
yName = 'Overall Satisfaction'
xNames = ['Response Time to the Service Call',
'Efficiency of Handling the Service Call',
'Answer/Solution Provided',
'Knowledge of the Service Personnel',
'Communication Skills of the Service Personnel',
'Professionalism of the Service Personnel']
df_results = relativeImp(df, outcomeName = yName, driverNames = xNames)
Creator
Copyright © 2019 Dan Yang
Metadata
Release files for relativeImp 0.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| relativeImp-0.0.2.tar.gz | 2.8 kB | Without provenance | Details for relativeImp-0.0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| relativeImp-0.0.2-py3-none-any.whl | Python 3 | none | any | Details for relativeImp-0.0.2-py3-none-any.whl |
Total release size: 7.0 kB
Release files / relativeImp-0.0.2.tar.gz
| Download URL | relativeImp-0.0.2.tar.gz |
|---|---|
| Size | 2.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
16e025546a7149eb038e3278ecf0e4364b2ea7ab57f59af7bbbbd655aff11fbc
|
|
BLAKE2b-256 checksum How to use checksums |
519b8442550de1c1c76c295953ffb99277b7001e0f9c6574345e081c7650386d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.1.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
|
Release files / relativeImp-0.0.2-py3-none-any.whl
| Download URL | relativeImp-0.0.2-py3-none-any.whl |
|---|---|
| Size | 4.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7db59c76b09178d8fa3cdb5c764b3dabb4f644c3ea9be019b24c4c71c4eed511
|
|
BLAKE2b-256 checksum How to use checksums |
2ea6d02857fb2ffb19d3660e70a1ab7bff9308f914351e0b00ad8a0da3c8de63
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.1.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
|
Security for relativeImp 0.0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.