From ce58cc97866605fe64df479e96d455e90f56f8e2 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Sun, 8 Dec 2019 21:22:09 -0500 Subject: fixed useless coordinates in Landscape if min and max are computed from data --- src/python/doc/representations.rst | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'src/python/doc/representations.rst') diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index b3131a25..b338f7f0 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -8,9 +8,9 @@ Representations manual .. include:: representations_sum.inc -This module, originally named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning tools, in particular scikit-learn. It provides tools, using the scikit-learn standard interface, to compute distances and kernels on diagrams, and to convert diagrams into vectors. +This module, originally available at https://github.com/MathieuCarriere/sklearn-tda and named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning, by providing implementations of most of the vector representations for persistence diagrams in the literature, in a scikit-learn format. More specifically, it provides tools, using the scikit-learn standard interface, to compute distances and kernels on persistence diagrams, and to convert these diagrams into vectors in Euclidean space. -A diagram is represented as a numpy array of shape (n,2), as can be obtained from :func:`~gudhi.SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. +A diagram is represented as a numpy array of shape (n,2), as can be obtained from `SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. A small example is provided @@ -46,3 +46,24 @@ Metrics :members: :special-members: :show-inheritance: + +Basic example +------------- + +This example computes the first two Landscapes associated to a persistence diagram with four points. The landscapes are evaluated on ten samples, leading to two vectors with ten coordinates each, that are eventually concatenated in order to produce a single vector representation. + +.. testcode:: + + import numpy as np + from gudhi.representations import Landscape + # A single diagram with 4 points + D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.]]) + diags = [D] + l=Landscape(num_landscapes=2,resolution=10).fit_transform(diags) + print(l) + +The output is: + +.. testoutput:: + + [[0. 1.25707872 2.51415744 1.88561808 0.7856742 2.04275292 3.29983165 2.51415744 1.25707872 0. 0. 0. 0.31426968 0. 0.62853936 0. 0. 0.31426968 1.25707872 0. ]] -- cgit v1.2.3 From 5ecc15ba30e7a20604d50c1fdec9e7da2de64898 Mon Sep 17 00:00:00 2001 From: mathieu Date: Tue, 10 Dec 2019 14:24:52 -0500 Subject: fixed doc and examples --- src/python/doc/representations.rst | 4 ++-- src/python/example/diagram_vectorizations_distances_kernels.py | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'src/python/doc/representations.rst') diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index b338f7f0..409e97da 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -10,7 +10,7 @@ Representations manual This module, originally available at https://github.com/MathieuCarriere/sklearn-tda and named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning, by providing implementations of most of the vector representations for persistence diagrams in the literature, in a scikit-learn format. More specifically, it provides tools, using the scikit-learn standard interface, to compute distances and kernels on persistence diagrams, and to convert these diagrams into vectors in Euclidean space. -A diagram is represented as a numpy array of shape (n,2), as can be obtained from `SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. +A diagram is represented as a numpy array of shape (n,2), as can be obtained from :func:`~gudhi.SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. A small example is provided @@ -66,4 +66,4 @@ The output is: .. testoutput:: - [[0. 1.25707872 2.51415744 1.88561808 0.7856742 2.04275292 3.29983165 2.51415744 1.25707872 0. 0. 0. 0.31426968 0. 0.62853936 0. 0. 0.31426968 1.25707872 0. ]] + [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 2.95699199 3.08555686 0. 0.64282435 0. 0. 0.51425948 0. 0. 0. ]] diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index f777984c..0ea4ba79 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -26,9 +26,9 @@ plt.show() LS = Landscape(resolution=1000) L = LS.fit_transform(diags) -plt.plot(L[0][:999]) -plt.plot(L[0][999:2*999]) -plt.plot(L[0][2*999:3*999]) +plt.plot(L[0][:998]) +plt.plot(L[0][998:2*998]) +plt.plot(L[0][2*998:3*998]) plt.title("Landscape") plt.show() -- cgit v1.2.3 From 682f8c8cb18ba898a3d23a82fff454e862541aed Mon Sep 17 00:00:00 2001 From: Mathieu Carrière Date: Wed, 11 Dec 2019 13:48:26 -0500 Subject: Update src/python/doc/representations.rst Co-Authored-By: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> --- src/python/doc/representations.rst | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/python/doc/representations.rst') diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index 409e97da..470b57bf 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -66,4 +66,6 @@ The output is: .. testoutput:: - [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 2.95699199 3.08555686 0. 0.64282435 0. 0. 0.51425948 0. 0. 0. ]] + [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 + 2.95699199 3.08555686 0. 0.64282435 0. 0. + 0.51425948 0. 0. 0. ]] -- cgit v1.2.3 From 9e75cc1832403f8ffec38fc3a4f6b1081fe4770e Mon Sep 17 00:00:00 2001 From: mathieu Date: Wed, 11 Dec 2019 13:57:15 -0500 Subject: update example --- src/python/doc/representations.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'src/python/doc/representations.rst') diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index 470b57bf..11dcbcf9 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -67,5 +67,6 @@ The output is: .. testoutput:: [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 - 2.95699199 3.08555686 0. 0.64282435 0. 0. - 0.51425948 0. 0. 0. ]] + 2.95699199 3.08555686 2.05703791 1.02851895 0. 0.64282435 + 0. 0. 0.51425948 0. 0. 0. + 0.77138922 1.02851895]] -- cgit v1.2.3