You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
**tda-mapper** is a Python library based on the Mapper algorithm, a key tool in
16
-
Topological Data Analysis (TDA). Designed for efficient computations and backed
17
-
by advanced spatial search techniques, it scales seamlessly to high dimensional
18
-
data, making it suitable for applications in machine learning, data mining, and
19
-
exploratory data analysis.
13
+
**tda-mapper** is a Python library built around the Mapper algorithm, a core technique in Topological Data Analysis (TDA) for extracting topological structure from complex data. Designed for computational efficiency and scalability, it leverages optimized spatial search methods to support high-dimensional datasets. The library is well-suited for integration into machine learning pipelines, unsupervised learning tasks, and exploratory data analysis.
Leverages optimized spatial search techniques and parallelization to accelerate the construction of Mapper graphs, supporting the analysis of high-dimensional datasets.
25
+
26
+
-**Scikit-learn integration**
27
27
28
-
-**Fast Mapper graph construction**: Accelerates computations with efficient spatial search, enabling analysis of large, high-dimensional datasets.
28
+
Provides custom estimators that are fully compatible with scikit-learn's API, enabling seamless integration into scikit-learn pipelines for tasks such as dimensionality reduction, clustering, and feature extraction.
29
29
30
-
-**Scikit-learn compatibility**: Easily integrate Mapper as a part of your machine learning workflows.
30
+
-**Flexible visualization**
31
31
32
-
-**Flexible visualization options**: Visualize Mapper graphs with multiple supported backends, tailored to your needs.
32
+
Multiple visualization backends supported (e.g., Plotly, Matplotlib) for generating high-quality Mapper graph representations with adjustable layouts and styling.
33
33
34
-
-**Interactive exploration**: Explore data interactively through a user-friendly app.
34
+
-**Interactive app**
35
+
36
+
Provides an interactive web-based interface (via Streamlit) for dynamic exploration of Mapper graph structures, offering real-time adjustments to parameters and visualizations.
35
37
36
38
## Background
37
39
38
-
The Mapper algorithm transforms complex datasets into graph representations
39
-
that highlight clusters, transitions, and topological features. These insights
40
-
reveal hidden patterns in data, applicable across fields like social sciences,
41
-
biology, and machine learning. For an in-depth coverage of Mapper, including
42
-
its mathematical foundations and applications, read the
43
-
[the original paper](https://research.math.osu.edu/tgda/mapperPBG.pdf).
40
+
The Mapper algorithm extracts topological features from complex datasets, representing them as graphs that highlight clusters, transitions, and key structural patterns. These insights reveal hidden data relationships and are applicable across diverse fields, including social sciences, biology, and machine learning. For an in-depth overview of Mapper, including its mathematical foundations and practical applications, read [the original paper](https://research.math.osu.edu/tgda/mapperPBG.pdf).
44
41
45
42
| Step 1 | Step 2 | Step 3 | Step 4 |
46
43
| ------ | ------ | ------ | ------ |
@@ -49,15 +46,7 @@ its mathematical foundations and applications, read the
49
46
50
47
## Citations
51
48
52
-
If you use **tda-mapper** in your work, please consider citing both the
53
-
[library](https://doi.org/10.5281/zenodo.10642381), archived in a permanent
54
-
Zenodo record, and the [paper](https://openreview.net/pdf?id=lTX4bYREAZ),
55
-
which provides a broader methodological overview.
56
-
We recommend citing the specific version of the library used in your research,
If you use **tda-mapper** in your work, please consider citing both the [library](https://doi.org/10.5281/zenodo.10642381), archived in a permanent Zenodo record, and the [paper](https://openreview.net/pdf?id=lTX4bYREAZ), which provides a broader methodological overview. We recommend citing the specific version of the library used in your research, along with the paper. For citation examples, please refer to the [documentation](https://tda-mapper.readthedocs.io/en/main/#citations).
61
50
62
51
## Quick Start
63
52
@@ -71,12 +60,7 @@ pip install tda-mapper
71
60
72
61
### How to Use
73
62
74
-
Here's a minimal example using the **circles dataset** from `scikit-learn` to demonstrate how to use **tda-mapper**.
75
-
We start by generating the data and visualizing it.
76
-
The dataset consists of two concentric circles.
77
-
The goal is to compute a Mapper graph that summarizes this structure while preserving topological features.
78
-
We proceed as follows:
79
-
63
+
Here's a minimal example using the **circles dataset** from `scikit-learn` to demonstrate how to use **tda-mapper**. This example demonstrates how to apply the Mapper algorithm on a synthetic dataset (concentric circles). The goal is to extract a topological graph representation using `PCA` as a lens and `DBSCAN` for clustering. We proceed as follows:
80
64
81
65
```python
82
66
import matplotlib.pyplot as plt
@@ -124,10 +108,16 @@ More examples can be found in the
124
108
Use our Streamlit app to visualize and explore your data without writing code.
or locally on your machine. The first time you run the app locally, you may need to install the required dependencies from the `requirements.txt` file by running
- **Fast Mapper graph construction**: Accelerates computations with efficient
49
-
spatial search, enabling analysis of large, high-dimensional datasets.
51
+
- **Efficient construction**
52
+
53
+
Leverages optimized spatial search techniques and parallelization to accelerate the construction of Mapper graphs, supporting the analysis of high-dimensional datasets.
54
+
55
+
- **Scikit-learn integration**
56
+
57
+
Provides custom estimators that are fully compatible with scikit-learn's API, enabling seamless integration into scikit-learn pipelines for tasks such as dimensionality reduction, clustering, and feature extraction.
58
+
59
+
- **Flexible visualization**
60
+
61
+
Multiple visualization backends supported (e.g., Plotly, Matplotlib) for generating high-quality Mapper graph representations with adjustable layouts and styling.
50
62
51
-
- **Scikit-learn compatibility**: Easily integrate Mapper as a part of your
52
-
machine learning workflows.
63
+
- **Interactive app**
53
64
54
-
- **Flexible visualization options**: Visualize Mapper graphs with multiple
55
-
supported backends, tailored to your needs.
65
+
Provides an interactive web-based interface (via Streamlit) for dynamic exploration of Mapper graph structures, offering real-time adjustments to parameters and visualizations.
56
66
57
-
- **Interactive exploration**: Explore data interactively through a
58
-
user-friendly app.
59
67
60
68
Background
61
69
----------
62
70
63
-
The Mapper algorithm transforms complex datasets into graph representations
64
-
that highlight clusters, transitions, and topological features. These insights
65
-
reveal hidden patterns in data, applicable across fields like social sciences,
66
-
biology, and machine learning. For an in-depth coverage of Mapper, including
67
-
its mathematical foundations and applications, read the
68
-
`original paper <https://research.math.osu.edu/tgda/mapperPBG.pdf>`__.
71
+
The Mapper algorithm extracts topological features from complex datasets,
72
+
representing them as graphs that highlight clusters, transitions, and key
73
+
structural patterns. These insights reveal hidden data relationships and are
74
+
applicable across diverse fields, including social sciences, biology, and
75
+
machine learning. For an in-depth overview of Mapper, including its
76
+
mathematical foundations and practical applications, read
77
+
`the original paper <https://research.math.osu.edu/tgda/mapperPBG.pdf>`__.
0 commit comments