Merge pull request #2 from mindearth/dev

Included urban spatial structure indicators and analyses.
mindearth · Nov 22, 2022 · c8c7f21 · c8c7f21
2 parents 26a426f + cebc809
commit c8c7f21
Show file tree

Hide file tree

Showing 15 changed files with 14,463 additions and 232 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,4 +1,11 @@
+docs/_build
+dist
+build
+mobilkit.egg-info
 *.pyc
 *.gz
 *.pyo
 .ipynb_checkpoints
+dist/
+docs/_build/
+docs/mobilkit.*.rst
diff --git a/docs/examples/USS01_Mumbai.ipynb b/docs/examples/USS01_Mumbai.ipynb
diff --git a/docs/examples/USS02_CityComparison.ipynb b/docs/examples/USS02_CityComparison.ipynb
diff --git a/docs/examples/figures/pings_stops_locs.png b/docs/examples/figures/pings_stops_locs.png
diff --git a/docs/index.rst b/docs/index.rst
@@ -127,15 +127,16 @@ If you use `mobilkit` please cite us:
   2021, KDD 2021 Humanitarian Mapping Workshop, https://arxiv.org/abs/2107.14297
 
 Bibtex:
-
     @misc{ubaldi2021mobilkit,
         title={Mobilkit: A Python Toolkit for Urban Resilience and Disaster Risk Management Analytics using High Frequency Human Mobility Data},
         author={Enrico Ubaldi and Takahiro Yabe and Nicholas K. W. Jones and Maham Faisal Khan and Satish V. Ukkusuri and Riccardo Di Clemente and Emanuele Strano},
         year={2021},
         eprint={2107.14297},
-        primaryClass={cs.CY}
-        archivePrefix={arXiv},
-    }
+        primaryClass={cs.CY},
+        archivePrefix={arXiv}}
+
+
+
 
 
 Credits and contacts
@@ -145,6 +146,8 @@ This code has been developed by `Mindearth <https://mindearth.ch>`_, the `Global
 
 Funding was provided by the Spanish Fund for Latin America and the Caribbean (SFLAC) under the Disruptive Technologies for Development (DT4D) program.
 
+The findings, interpretations, and conclusions expressed in this repository and in the example notebooks are entirely those of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they represent.
+
 The code is released under the MIT license (see the LICENSE file for details).
 
 
@@ -157,6 +160,8 @@ The code is released under the MIT license (see the LICENSE file for details).
    examples/M4R_02_DisplacementAnalysis.ipynb
    examples/M4R_03_POI_visit_analysis.ipynb
    examples/M4R_04_Population_Density_Analysis.ipynb
+   examples/USS01_Mumbai.ipynb
+   examples/USS02_CityComparison.ipynb
    reference/Loading_data.rst
    mobilkit
 

diff --git a/docs/modules.rst b/docs/modules.rst
@@ -0,0 +1,7 @@
+mobilkit
+========
+
+.. toctree::
+   :maxdepth: 4
+
+   mobilkit
diff --git a/mobilkit/__init__.py b/mobilkit/__init__.py
@@ -18,4 +18,4 @@
 The `mobilkit` module documentation.
 '''
 
-__version__ = "0.1.7"
+__version__ = "0.2.4.b"
diff --git a/mobilkit/dask_schemas.py b/mobilkit/dask_schemas.py
@@ -25,13 +25,29 @@
     finalize=lambda s1: s1.apply(lambda final: len(set(final))),
 )
 
+sets2nunique = dd.Aggregation(
+    name="sets2nunique",
+    chunk=lambda s: s.apply(lambda x: list(set([e for es in x for e in es]))),
+    agg=lambda s0: s0.obj.groupby(level=list(range(s0.obj.index.nlevels))).sum(),
+    finalize=lambda s1: s1.apply(lambda final: len(set(final))),
+)
+
+# Constant column names
 accColName = "acc"
 lonColName = "lng"
 latColName = "lat"
 uidColName = "uid"
 utcColName = "UTC"
 dttColName = "datetime"
 zidColName = "tile_ID"
+stpColName = 'stops'
+ldtColName = 'leaving_datetime'
+durColName = 'duration'
+medLatColName = latColName + '_medoid'
+medLonColName = lonColName + '_medoid'
+radLonColName = lonColName + '_RAD_'
+radLatColName = latColName + '_RAD_'
+locColName = "loc_ID"
 
 
 eventLineRAW = [

diff --git a/mobilkit/loader.py b/mobilkit/loader.py
@@ -264,12 +264,13 @@ def loaddata_takeapeek(dirpath, sep, ext):
 
 def compute_datetime_col(df, selected_tz):
     if dttColName in df.columns:
-        print("Warning, %s column already present, not computing it...")
+        print("Warning, '%s' column already present, not computing it..." % dttColName)
     else:
         df[dttColName] = dd.to_datetime(df[utcColName]*1e9, utc=False, unit="ns")\
                         .dt.tz_localize("UTC")\
                         .dt.tz_convert(selected_tz)\
                         .dt.tz_localize(None)
+        df[dttColName] = df[dttColName].astype('datetime64[s]')
 
     return df