Six-Sigma based analysis of manufacturing data
Project description
Purpose
To provide analysis tools and metrics useful in manufacturing environments.
I am slowly generating the documentation and, as that is maturing, I will begin to move information
from this readme.md
into that location. If you don't find something here, head over to the
documentation.
Project Maturity
Every effort is being made to ensure that the results are accurate, but the user is ultimately responsible for any resulting analysis.
The API should not be considered stable until v1.0 or greater. Until then, breaking changes may be released as different API options are explored.
During the v0.X.X
versioning, I am using the package in my own analyses in order to find any bugs. Once
I am reasonably satisfied that the package is feature complete, usable, and bug-free, I will break out
the v1.X.X
releases.
Installation
To install from pypi
:
pip install manufacturing
To install from source download and install using poetry:
poetry install
Usage
Visualizations with Jupyter Notebooks
Visualizations work approximately as expected within a jupyter notebook.
data = np.random.normal(0, 1, size=30) # generate some data
manufacturing.ppk_plot(data, lower_specification_limit=-2, upper_specification_limit=2)
There is a sample jupyter notebook in the examples directory.
Cpk Visualization
The most useful feature of the manufacturing
package is the visualization of Cpk.
As hinted previously, the ppk_plot()
function is the primary method for display of
Cpk visual information. First, get your data into a list
, numpy.array
, or
pandas.Series
; then supply that data, along with the lower_control_limit
and
upper_control_limit
into the ppk_plot()
function.
manufacturing.ppk_plot(data, lower_control_limit=-2, upper_control_limit=2)
In this example, it appears that the manufacturing processes are not up to the task of making consistent product within the specified limits.
Zone Control Visualization
Another useful feature is the zone control visualization.
manufacturing.control_chart(data)
RoadMap
Continuous Integration
Add use github actions for deploymentTransition topoetry
AddI-MR Chart
(seeexamples/imr_chart.py
)AddXbar-R Chart
(subgroups between 2 and 10)AddXbar-S Chart
(subgroups of 11 or more)
Gallery
Currently, no distinction is made between Ppk and Cpk, so the entire chart shows the Cpk.
Some of the data for the zone control chard was manipulated in order to display the results. Note that, if a phenomenon is not present within the data, then it will not be plotted at all.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for manufacturing-1.1.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3c2f7e205c4c9147ab3f87afa4fec239a5221176c8ffa0ca0d57d52d77c9424d |
|
MD5 | be4821beeb3acae5fea7b19c4748b939 |
|
BLAKE2b-256 | 655bd83b493c6d4af1de6a7da1d67b0d1d7f9b72e40f86e9b54321ac18b3c17b |