Merge pull request #143 from UDST/node-id-fix

[v0.5.1] Patch restoring get_node_ids() performance
UDST · Aug 6, 2020 · 740c1d7 · 740c1d7
2 parents 3ed8e40 + 3593222
commit 740c1d7
Show file tree

Hide file tree

Showing 8 changed files with 24 additions and 11 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,10 @@
+v0.5.1
+======
+
+2020/08/05
+
+* Fixes a performance bug in network.get_node_ids()
+
 v0.5
 ====
 

diff --git a/README.md b/README.md
@@ -1,6 +1,3 @@
-![Version](https://img.shields.io/badge/version-0.5-blue.svg)
-[![Travis build status](https://travis-ci.org/UDST/pandana.svg?branch=master)](https://travis-ci.org/UDST/pandana)
-[![Appveyor build status](https://ci.appveyor.com/api/projects/status/a90kvns7qe56kg57?svg=true)](https://ci.appveyor.com/project/smmaurer/pandana)
 [![Coverage Status](https://coveralls.io/repos/github/UDST/pandana/badge.svg?branch=master)](https://coveralls.io/github/UDST/pandana?branch=master)
 
 # Pandana

diff --git a/docs/source/changelog.rst b/docs/source/changelog.rst
@@ -1,6 +1,13 @@
 Change log
 ==========
 
+v0.5.1
+------
+
+2020/08/05
+
+* Fixes a performance bug in network.get_node_ids()
+
 v0.5
 ----
 

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -57,9 +57,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '0.5'
+version = '0.5.1'
 # The full version, including alpha/beta/rc tags.
-release = '0.5'
+release = '0.5.1'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -8,7 +8,7 @@ Pandana
 
 Pandana is a Python library for network analysis that uses `contraction hierarchies <https://en.wikipedia.org/wiki/Contraction_hierarchies>`_ to calculate super-fast travel accessibility metrics and shortest paths. The numerical code is in C++.
 
-v0.5, released July 28, 2020
+v0.5.1, released August 5, 2020
 
 
 Acknowledgments

diff --git a/pandana/__init__.py b/pandana/__init__.py
@@ -1,3 +1,3 @@
 from .network import Network
 
-version = __version__ = '0.5'
+version = __version__ = '0.5.1'
diff --git a/pandana/network.py b/pandana/network.py
@@ -2,7 +2,7 @@
 
 import numpy as np
 import pandas as pd
-from scipy.spatial import KDTree
+from sklearn.neighbors import KDTree
 
 from .cyaccess import cyaccess
 from .loaders import pandash5 as ph5
@@ -379,7 +379,7 @@ def aggregate(self, distance, type="sum", decay="linear", imp_name=None,
         decay : string, optional (default 'linear')
             The type of decay to apply, which makes things that are further
             away count less in the aggregation: 'linear', 'exponential', or
-            'flat' (no decay). 
+            'flat' (no decay).
 
             *Additional notes:* see ``aggregateAccessibilityVariable`` in
             accessibility.cpp to read through the code that applies decays.
@@ -468,6 +468,8 @@ def get_node_ids(self, x_col, y_col, mapping_distance=None):
         xys = pd.DataFrame({'x': x_col, 'y': y_col})
 
         distances, indexes = self.kdtree.query(xys.values)
+        indexes = np.transpose(indexes)[0]
+        distances = np.transpose(distances)[0]
 
         node_ids = self.nodes_df.iloc[indexes].index
 

diff --git a/setup.py b/setup.py
@@ -131,7 +131,7 @@ def run(self):
 ## Standard setup
 ###############################################
 
-version = '0.5'
+version = '0.5.1'
 
 packages = find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests"])
 
@@ -154,7 +154,7 @@ def run(self):
         'numpy >=1.8',
         'pandas >=0.17',
         'requests >=2.0',
-        'scipy >=0.9',
+        'scikit-learn >=0.18',
         'tables >=3.1, <3.6; python_version <"3.6"',
         'tables >=3.1, <3.7; python_version >="3.6"'
     ],
-Original file line number
+Diff line change
@@ -1,3 +1,10 @@
+    v0.5.1
+    ======
+/08/05
+    * Fixes a performance bug in network.get_node_ids()
     v0.5
     ====
@@ Expand Down @@