gismap 0.1.0__py3-none-any.whl

gismap/utils/text.py

@@ -0,0 +1,93 @@
+from bof.fuzz import Process
+
+
+class Corrector:
+    """
+    A simple word corrector base on input vocabulary. Short words are discarded.
+
+    Parameters
+    ----------
+    voc: :class:`list`
+        Words (each entry may contain multiple words).
+    score_cutoff: :class:`int`, default=20
+        Threshold for correction.
+    min_length: :class:`int`, default=3
+        Minimal number of caracters for correction to kick in.
+
+    Examples
+    --------
+
+    >>> vocabulary = ['My Taylor Swift is Rich']
+    >>> phrase = "How riche ise Tailor Swyft"
+    >>> cor = Corrector(vocabulary, min_length=4)
+    >>> cor(phrase)
+    'How rich ise taylor swift'
+    >>> cor = Corrector(vocabulary, min_length=2)
+    >>> cor(phrase)
+    'How rich is taylor swift'
+    """
+
+    def __init__(self, voc, score_cutoff=20, min_length=3):
+        self.voc = {k.lower() for w in voc for k in w.split() if len(k) >= min_length}
+        self.cutoff = score_cutoff
+        self.min_length = min_length
+        self.p = Process()
+        self.p.fit(list(self.voc))
+
+    def correct_word(self, w):
+        if len(w) < self.min_length or w.lower() in self.voc:
+            return w
+        ww = self.p.extractOne(w, score_cutoff=self.cutoff)
+        return ww[0] if ww is not None else w
+
+    def __call__(self, text):
+        return " ".join(self.correct_word(w) for w in text.split())
+
+
+def reduce_keywords(kws):
+    """
+    Remove redundant subparts.
+
+    Parameters
+    ----------
+    kws: :class:`list`
+        List of words / co-locations.
+
+    Returns
+    -------
+    :class:`list`
+        Reduced list
+
+    Examples
+    --------
+
+    >>> reduce_keywords(['P2P', 'Millimeter Waves', 'Networks', 'P2P Networks', 'Waves'])
+    ['Millimeter Waves', 'P2P Networks']
+    """
+    indices = []
+    for i, kw1 in enumerate(kws):
+        accept = True
+        for j, kw2 in enumerate(kws):
+            if j != i and kw1 in kw2:
+                accept = False
+                break
+        if accept:
+            indices.append(i)
+    return [kws[i] for i in indices]
+
+
+def clean_aliases(name, alias_list):
+    """
+    Parameters
+    ----------
+    name: :class:`str`
+        Main name.
+    alias_list: :class:`list` or :class:`set`
+        Aliases.
+
+    Returns
+    -------
+    :class:`list`
+        Aliases deduped, sorted, and with main name removed.
+    """
+    return sorted(set(n for n in alias_list if n != name))

gismap-0.1.0.dist-info/METADATA

@@ -0,0 +1,62 @@
+Metadata-Version: 2.4
+Name: gismap
+Version: 0.1.0
+Summary: GISMAP leverages DBLP and HAL databases to provide cartography tools for you and your lab.
+Project-URL: Repository, https://github.com/balouf/gismap
+Project-URL: Documentation, https://balouf.github.io/gismap
+Author-email: Fabien Mathieu <fabien.mathieu@normalesup.org>
+Maintainer-email: Fabien Mathieu <fabien.mathieu@normalesup.org>
+License-Expression: MIT
+License-File: AUTHORS.md
+Requires-Python: >=3.10
+Requires-Dist: bof>=0.3.5
+Requires-Dist: gismo>=0.5.2
+Description-Content-Type: text/markdown
+
+# Generic Information Search: Mapping and Analysis of Publications
+
+
+[![PyPI Status](https://img.shields.io/pypi/v/gismap.svg)](https://pypi.python.org/pypi/gismap)
+[![Build Status](https://github.com/balouf/gismap/actions/workflows/build.yml/badge.svg?branch=main)](https://github.com/balouf/gismap/actions?query=workflow%3Abuild)
+[![Documentation Status](https://github.com/balouf/gismap/actions/workflows/docs.yml/badge.svg?branch=main)](https://github.com/balouf/gismap/actions?query=workflow%3Adocs)
+[![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Code Coverage](https://codecov.io/gh/balouf/gismap/branch/main/graphs/badge.svg)](https://codecov.io/gh/balouf/gismap/tree/main)
+
+GISMAP leverages DBLP and HAL databases to provide cartography tools for you and your lab.
+
+- Free software: MIT
+- Documentation: <https://balouf.github.io/gismap/>.
+- Github: <https://github.com/balouf/gismap>
+
+## Features
+
+- Can be used by all researchers in Computer Science (DBLP endpoint) or based in France (HAL endpoint).
+- Aggregate publications from multiple databases, including multiple author keys inside the same database.
+- Automatically keeps track of a Lab/Department members and publications.
+- Builds interactive collaboration graphs.
+
+## Quickstart
+
+Install GISMAP:
+
+```console
+$ pip install gismap
+```
+
+Use GISMAP to produce a collaboration graph (HTML):
+
+```pycon
+>>> from gismap.sources.hal import HAL
+>>> from gismap.lab import ListLab, lab2graph
+>>> lab = ListLab(["Mathilde Labbé", "Anne Reverseau", "David Martens", "Marcela Scibiorska", "Nathalie Grande"], dbs=[HAL])
+>>> lab.update_authors()
+>>> lab.update_publis()
+>>> collabs = lab2graph(lab)
+```
+
+## Credits
+
+This package was created with [Cookiecutter][CC] and the [Package Helper 3][PH3] project template.
+
+[CC]: <https://github.com/audreyr/cookiecutter>
+[PH3]: <https://balouf.github.io/package-helper-3/>

gismap-0.1.0.dist-info/RECORD

@@ -0,0 +1,25 @@
+gismap/__init__.py,sha256=TFBKB5AwAxzmcpIB48EpT4Ud9S417i5Obh85w2t1-Zc,598
+gismap/author.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gismap/gismap.py,sha256=h0hwdogXGFqerm-5ZPeT-irPn91pCcQRjiHThXsRzEk,19
+gismap/gismo.py,sha256=kBzvlo-fqcvEgwQt-c_hHkfI1oTjBbKKb54vM8il_nI,6295
+gismap/search.py,sha256=nsUoDsFGeEtvCZ0dB7ooRPC_6qsazkiWx_oM7dHdNV4,4932
+gismap/lab/__init__.py,sha256=UQVY6Sk7o9O0YREArXA8_8ZfrDO0JYLy8tikSHBEbzo,377
+gismap/lab/graph.py,sha256=LOHNnmFqgsZc7YGUcFQ1GKl0DFiStFfoYqx-2IrjFAk,6525
+gismap/lab/lab.py,sha256=-mBcHcP9JaBAiiZlWRygac5MQdO0b6AriHWiLgTveWc,4224
+gismap/lab/lip6.py,sha256=yRx-RWgcGhGWUk_oyfgC9QYJSVnATnp6YlNvaOlr8Gw,1410
+gismap/lab/toulouse.py,sha256=KkzNOCFt3OU6pDJmDmli6wRNuMwH8CPXHj_S6aOcYeg,1462
+gismap/lab/vis.py,sha256=1QgLgLQjcB7rGiZ946lhLU1kR38oXp_Y8l8U-Ukn65k,5497
+gismap/sources/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gismap/sources/dblp.py,sha256=5ZKngU66xgXffmiGHsbXGXJfU_NIybnuzXXZPcWIZoE,5381
+gismap/sources/hal.py,sha256=mWyiG12wXE9A8w81YGFicx8Yy9mX-anvIEoBueU2U6Q,9136
+gismap/sources/models.py,sha256=yJPBXcJO6MgOrSXgpGPepHDDtniJP1OsK8OSz__VzYc,543
+gismap/sources/multi.py,sha256=jfvBVgmnLT85RaEWcMNCZ8YtmSRuQuq8CkCHWY8u-hc,3515
+gismap/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gismap/utils/common.py,sha256=BV5mma4aikHyPIhH4theLkiNHaiqLv5_EfxhT0yajZo,1509
+gismap/utils/logger.py,sha256=1YALIaNYKTqeIyyCnYxzvZTK7x4FTSfYYl5CP9IMw8E,86
+gismap/utils/requests.py,sha256=DV5rmyuy7jpMp63kzGXe848pmwMb5397wGHgF0o_0BM,721
+gismap/utils/text.py,sha256=R7tKWevfF4g-LsohF6FeiRdCuNYz4jQ1VcQJIyhwei0,2393
+gismap-0.1.0.dist-info/METADATA,sha256=bTM9vZl81oJ5dUYakrCEL1uAbTZzEgC1AGSePg1TBU8,2499
+gismap-0.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+gismap-0.1.0.dist-info/licenses/AUTHORS.md,sha256=oDR4mptVUBMq0WKIpt19Km1Bdfz3cO2NAOVgwVfTO8g,131
+gismap-0.1.0.dist-info/RECORD,,

gismap-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.27.0
+Root-Is-Purelib: true
+Tag: py3-none-any

gismap-0.1.0.dist-info/licenses/AUTHORS.md

@@ -0,0 +1,9 @@
+# Credits
+
+## Development Lead
+
+- Fabien Mathieu <fabien.mathieu@normalesup.org>
+
+## Contributors
+
+None yet. Why not be the first?