pysal / Mapclassify
Licence: bsd-3-clause
Classification schemes for choropleth mapping.
Stars: ✭ 72
Projects that are alternatives of or similar to Mapclassify
Servenet
Service Classification based on Service Description
Stars: ✭ 21 (-70.83%)
Mutual labels: jupyter-notebook, classification
Satellite imagery analysis
Implementation of different techniques to find insights from the satellite data using Python.
Stars: ✭ 31 (-56.94%)
Mutual labels: jupyter-notebook, classification
Geemap
A Python package for interactive mapping with Google Earth Engine, ipyleaflet, and folium
Stars: ✭ 959 (+1231.94%)
Mutual labels: jupyter-notebook, gis
Earthengine Py Notebooks
A collection of 360+ Jupyter Python notebook examples for using Google Earth Engine with interactive mapping
Stars: ✭ 807 (+1020.83%)
Mutual labels: jupyter-notebook, gis
Urban Sound Classification
Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)
Stars: ✭ 39 (-45.83%)
Mutual labels: jupyter-notebook, classification
Skin Cancer Image Classification
Skin cancer classification using Inceptionv3
Stars: ✭ 16 (-77.78%)
Mutual labels: jupyter-notebook, classification
The Deep Learning With Keras Workshop
An Interactive Approach to Understanding Deep Learning with Keras
Stars: ✭ 34 (-52.78%)
Mutual labels: jupyter-notebook, classification
Food Recipe Cnn
food image to recipe with deep convolutional neural networks.
Stars: ✭ 448 (+522.22%)
Mutual labels: jupyter-notebook, classification
Face Mask Detection
Face masks are crucial in minimizing the propagation of Covid-19, and are highly recommended or even obligatory in many situations. In this project, we develop a pipeline to detect unmasked faces in images. This can, for example, be used to alert people that do not wear a mask when entering a building.
Stars: ✭ 37 (-48.61%)
Mutual labels: jupyter-notebook, classification
Mlj.jl
A Julia machine learning framework
Stars: ✭ 982 (+1263.89%)
Mutual labels: jupyter-notebook, classification
Tensorflow cookbook
Code for Tensorflow Machine Learning Cookbook
Stars: ✭ 5,984 (+8211.11%)
Mutual labels: jupyter-notebook, classification
Applied Text Mining In Python
Repo for Applied Text Mining in Python (coursera) by University of Michigan
Stars: ✭ 59 (-18.06%)
Mutual labels: jupyter-notebook, classification
Breast cancer classifier
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
Stars: ✭ 614 (+752.78%)
Mutual labels: jupyter-notebook, classification
Bayesian Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
Stars: ✭ 900 (+1150%)
Mutual labels: jupyter-notebook, classification
Tensorflow Book
Accompanying source code for Machine Learning with TensorFlow. Refer to the book for step-by-step explanations.
Stars: ✭ 4,448 (+6077.78%)
Mutual labels: jupyter-notebook, classification
Prediciting Binary Options
Predicting forex binary options using time series data and machine learning
Stars: ✭ 33 (-54.17%)
Mutual labels: jupyter-notebook, classification
Pythonfromspace
Python Examples for Remote Sensing
Stars: ✭ 344 (+377.78%)
Mutual labels: jupyter-notebook, gis
Transformers Tutorials
Github repo with tutorials to fine tune transformers for diff NLP tasks
Stars: ✭ 384 (+433.33%)
Mutual labels: jupyter-notebook, classification
Ml Classification Algorithms Poverty
A comparative assessment of machine learning classification algorithms applied to poverty prediction
Stars: ✭ 36 (-50%)
Mutual labels: jupyter-notebook, classification
Machine Learning From Scratch
Succinct Machine Learning algorithm implementations from scratch in Python, solving real-world problems (Notebooks and Book). Examples of Logistic Regression, Linear Regression, Decision Trees, K-means clustering, Sentiment Analysis, Recommender Systems, Neural Networks and Reinforcement Learning.
Stars: ✭ 42 (-41.67%)
Mutual labels: jupyter-notebook, classification
mapclassify: Classification Schemes for Choropleth Maps
mapclassify implements a family of classification schemes for choropleth maps.
Its focus is on the determination of the number of classes, and the assignment
of observations to those classes. It is intended for use with upstream mapping
and geovisualization packages (see
geopandas and
geoplot)
that handle the rendering of the maps.
For further theoretical background see Rey, S.J., D. Arribas-Bel, and L.J. Wolf (2020) "Geographic Data Science with PySAL and the PyData Stack”.
Using mapclassify
Load built-in example data reporting employment density in 58 California counties:
>>> import mapclassify
>>> y = mapclassify.load_example()
>>> y.mean()
125.92810344827588
>>> y.min(), y.max()
(0.13, 4111.4499999999998)
Map Classifiers Supported
BoxPlot
>>> mapclassify.BoxPlot(y)
BoxPlot
Interval Count
--------------------------
( -inf, -52.88] | 0
( -52.88, 2.57] | 15
( 2.57, 9.36] | 14
( 9.36, 39.53] | 14
( 39.53, 94.97] | 6
( 94.97, 4111.45] | 9
EqualInterval
>>> mapclassify.EqualInterval(y)
EqualInterval
Interval Count
--------------------------
[ 0.13, 822.39] | 57
( 822.39, 1644.66] | 0
(1644.66, 2466.92] | 0
(2466.92, 3289.19] | 0
(3289.19, 4111.45] | 1
FisherJenks
>>> import numpy as np
>>> np.random.seed(123456)
>>> mapclassify.FisherJenks(y, k=5)
FisherJenks
Interval Count
--------------------------
[ 0.13, 75.29] | 49
( 75.29, 192.05] | 3
( 192.05, 370.50] | 4
( 370.50, 722.85] | 1
( 722.85, 4111.45] | 1
FisherJenksSampled
>>> np.random.seed(123456)
>>> x = np.random.exponential(size=(10000,))
>>> mapclassify.FisherJenks(x, k=5)
FisherJenks
Interval Count
----------------------
[ 0.00, 0.64] | 4694
( 0.64, 1.45] | 2922
( 1.45, 2.53] | 1584
( 2.53, 4.14] | 636
( 4.14, 10.61] | 164
>>> mapclassify.FisherJenksSampled(x, k=5)
FisherJenksSampled
Interval Count
----------------------
[ 0.00, 0.70] | 5020
( 0.70, 1.63] | 2952
( 1.63, 2.88] | 1454
( 2.88, 5.32] | 522
( 5.32, 10.61] | 52
HeadTailBreaks
>>> mapclassify.HeadTailBreaks(y)
HeadTailBreaks
Interval Count
--------------------------
[ 0.13, 125.93] | 50
( 125.93, 811.26] | 7
( 811.26, 4111.45] | 1
JenksCaspall
>>> mapclassify.JenksCaspall(y, k=5)
JenksCaspall
Interval Count
--------------------------
[ 0.13, 1.81] | 14
( 1.81, 7.60] | 13
( 7.60, 29.82] | 14
( 29.82, 181.27] | 10
( 181.27, 4111.45] | 7
JenksCaspallForced
>>> mapclassify.JenksCaspallForced(y, k=5)
JenksCaspallForced
Interval Count
--------------------------
[ 0.13, 1.34] | 12
( 1.34, 5.90] | 12
( 5.90, 16.70] | 13
( 16.70, 50.65] | 9
( 50.65, 4111.45] | 12
JenksCaspallSampled
>>> mapclassify.JenksCaspallSampled(y, k=5)
JenksCaspallSampled
Interval Count
--------------------------
[ 0.13, 12.02] | 33
( 12.02, 29.82] | 8
( 29.82, 75.29] | 8
( 75.29, 192.05] | 3
( 192.05, 4111.45] | 6
MaxP
>>> mapclassify.MaxP(y)
MaxP
Interval Count
--------------------------
[ 0.13, 8.70] | 29
( 8.70, 16.70] | 8
( 16.70, 20.47] | 1
( 20.47, 66.26] | 10
( 66.26, 4111.45] | 10
MaximumBreaks
>>> mapclassify.MaximumBreaks(y, k=5)
MaximumBreaks
Interval Count
--------------------------
[ 0.13, 146.00] | 50
( 146.00, 228.49] | 2
( 228.49, 546.67] | 4
( 546.67, 2417.15] | 1
(2417.15, 4111.45] | 1
NaturalBreaks
>>> mapclassify.NaturalBreaks(y, k=5)
NaturalBreaks
Interval Count
--------------------------
[ 0.13, 75.29] | 49
( 75.29, 192.05] | 3
( 192.05, 370.50] | 4
( 370.50, 722.85] | 1
( 722.85, 4111.45] | 1
Quantiles
>>> mapclassify.Quantiles(y, k=5)
Quantiles
Interval Count
--------------------------
[ 0.13, 1.46] | 12
( 1.46, 5.80] | 11
( 5.80, 13.28] | 12
( 13.28, 54.62] | 11
( 54.62, 4111.45] | 12
Percentiles
>>> mapclassify.Percentiles(y, pct=[33, 66, 100])
Percentiles
Interval Count
--------------------------
[ 0.13, 3.36] | 19
( 3.36, 22.86] | 19
( 22.86, 4111.45] | 20
StdMean
>>> mapclassify.StdMean(y)
StdMean
Interval Count
--------------------------
( -inf, -967.36] | 0
(-967.36, -420.72] | 0
(-420.72, 672.57] | 56
( 672.57, 1219.22] | 1
(1219.22, 4111.45] | 1
UserDefined
>>> mapclassify.UserDefined(y, bins=[22, 674, 4112])
UserDefined
Interval Count
--------------------------
[ 0.13, 22.00] | 38
( 22.00, 674.00] | 18
( 674.00, 4112.00] | 2
Alternative API
As of version 2.4.0 the API has been extended. A classify function is now
available for a streamlined interface:
>>> classify(y, 'boxplot')
BoxPlot
Interval Count
--------------------------
( -inf, -52.88] | 0
( -52.88, 2.57] | 15
( 2.57, 9.36] | 14
( 9.36, 39.53] | 14
( 39.53, 94.97] | 6
( 94.97, 4111.45] | 9
Use Cases
Creating and using a classification instance
>>> bp = mapclassify.BoxPlot(y)
>>> bp
BoxPlot
Interval Count
--------------------------
( -inf, -52.88] | 0
( -52.88, 2.57] | 15
( 2.57, 9.36] | 14
( 9.36, 39.53] | 14
( 39.53, 94.97] | 6
( 94.97, 4111.45] | 9
>>> bp.bins
array([ -5.28762500e+01, 2.56750000e+00, 9.36500000e+00,
3.95300000e+01, 9.49737500e+01, 4.11145000e+03])
>>> bp.counts
array([ 0, 15, 14, 14, 6, 9])
>>> bp.yb
array([5, 1, 2, 3, 2, 1, 5, 1, 3, 3, 1, 2, 2, 1, 2, 2, 2, 1, 5, 2, 4, 1, 2,
2, 1, 1, 3, 3, 3, 5, 3, 1, 3, 5, 2, 3, 5, 5, 4, 3, 5, 3, 5, 4, 2, 1,
1, 4, 4, 3, 3, 1, 1, 2, 1, 4, 3, 2])
Apply
>>> import mapclassify
>>> import pandas
>>> from numpy import linspace as lsp
>>> data = [lsp(3,8,num=10), lsp(10, 0, num=10), lsp(-5, 15, num=10)]
>>> data = pandas.DataFrame(data).T
>>> data
0 1 2
0 3.000000 10.000000 -5.000000
1 3.555556 8.888889 -2.777778
2 4.111111 7.777778 -0.555556
3 4.666667 6.666667 1.666667
4 5.222222 5.555556 3.888889
5 5.777778 4.444444 6.111111
6 6.333333 3.333333 8.333333
7 6.888889 2.222222 10.555556
8 7.444444 1.111111 12.777778
9 8.000000 0.000000 15.000000
>>> data.apply(mapclassify.Quantiles.make(rolling=True))
0 1 2
0 0 4 0
1 0 4 0
2 1 4 0
3 1 3 0
4 2 2 1
5 2 1 2
6 3 0 4
7 3 0 4
8 4 0 4
9 4 0 4
Development Notes
Because we use geopandas in development, and geopandas has stable mapclassify as a dependency, setting up a local development installation involves creating a conda environment, then replacing the stable mapclassify with the development version of mapclassify in the development environment. This can be accomplished with the following steps:
conda-env create -f environment.yml
conda activate mapclassify
conda remove -n mapclassify mapclassify
pip install -e .
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].