Compatibility with Python 3.5+

.gitignore

@@ -39,3 +39,4 @@ output/*/index.html
 
 # Sphinx
 docs/_build
+tutorials/1_basic_popgen_setup/*all_controls_ipu

.travis.yml

@@ -4,33 +4,38 @@ language: python
 
 python:
   - "2.7"
+  - "3.5"
+  - "3.6"
 
-#before_install:
-#  - sudo apt-get install liblapack-dev gfortran
-
-# command to install dependencies, e.g. pip install -r requirements.txt --use-mirrors
-# install:
-#  - travis_wait pip install -r requirements.txt
-
-
-before_install:
-  - wget http://repo.continuum.io/miniconda/Miniconda-latest-Linux-x86_64.sh -O miniconda.sh
-  - chmod +x miniconda.sh
-  - ./miniconda.sh -b
-  - export PATH=/home/travis/miniconda/bin:$PATH
-  # Update conda itself
-  - conda update --yes conda
-  # The next couple lines fix a crash with multiprocessing
-  # on Travis and are not specific to using Miniconda
-  - sudo rm -rf /dev/shm
-  - sudo ln -s /run/shm /dev/shm
 
 install:
-  - conda create --yes -n popgen_venv python=$TRAVIS_PYTHON_VERSION pip numpy scipy pandas PyYAML
+  - sudo apt-get update
+  # We do this conditionally because it saves us some downloading if the
+  # version is the same.
+  - if [[ "$TRAVIS_PYTHON_VERSION" == "2.7" ]]; then
+      wget https://repo.continuum.io/miniconda/Miniconda2-latest-Linux-x86_64.sh -O miniconda.sh;
+    else
+      wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh;
+    fi
+  - bash miniconda.sh -b -p $HOME/miniconda
+  - export PATH="$HOME/miniconda/bin:$PATH"
+  - hash -r
+  - conda config --set always_yes yes --set changeps1 no
+  - conda update -q conda
+  # Useful for debugging any issues with conda
+  - conda info -a
+
+  - conda create -q -n popgen_venv python=$TRAVIS_PYTHON_VERSION pip numpy scipy pandas PyYAML pytest
   - source activate popgen_venv
-  - pip install pytest
   - python setup.py install
 
 # command to run tests, e.g. python setup.py test
 script:
   - py.test
+
+
+
+
+
+
+

AUTHORS.rst

@@ -11,3 +11,5 @@ Contributors
 ------------
 
 * Daehyun You
+* Jeffrey Newman <[email protected]>
+

HISTORY.rst

@@ -3,7 +3,13 @@
 History
 -------
 
+2.1.b1 (March 23, 2017)
++++++++++++++++++++++++
+
+* Updated for Python 3.5+
+
+
 2.0.b1 (June 4, 2015)
-++++++++++++++++++
++++++++++++++++++++++
 
 * This is the first non-production release of PopGen 2.0

README.rst

@@ -1,6 +1,6 @@
-=============================
+==================================
 Synthetic Population Generator 2.0
-=============================
+==================================
 
 .. image:: https://badge.fury.io/py/popgen.png
     :target: http://badge.fury.io/py/popgen
@@ -12,15 +12,6 @@ Synthetic Population Generator 2.0
     :target: https://pypi.python.org/pypi/popgen
 
 
-Synthetic Population Generator 2.0
-
-
-Features
---------
 
-For PopGen 2.1
-* Automatic data validator
-* Census data importer
+This fork contains code that has been modified to be compatible with Python 2.7 and 3.5 and up.
 
-For PopGen 2.2
-* Output Data Analyzer with charting and table generation capabilities

bin/popgen_run

@@ -18,7 +18,7 @@ def run():
     """
     args = sys.argv[1:]
 
-    print args
+    print (args)
 
     if len(args) != 1:
         raise ArgumentsError(
@@ -35,6 +35,6 @@ def run():
     p_obj = Project(config_loc=args[0])
     p_obj.load_project()
     p_obj.run_scenarios()
-    print "Time it took: %.4f" % (time.time() - t)
+    print ("Time it took: %.4f" % (time.time() - t))
 
 run()

popgen/__init__.py

@@ -1 +1,3 @@
 from .project import Project
+
+__version__ = '2.1.b2'  # now for Python 3!

popgen/config.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 import yaml
 
 
@@ -16,7 +17,7 @@ def wrap_config_value(value):
     then attribute access x.attribute1.attribute2 is used to access "Value".
     Also, x.attribute can be used to access the dictionary {attribute: 'value'}
     """
-    if isinstance(value, basestring):
+    if isinstance(value, str):
         return value
 
     try:
@@ -45,7 +46,7 @@ def __getitem__(self, key):
     def return_value(self, key):
         try:
             value = self._data[key]
-        except KeyError, e:
+        except KeyError as e:
             raise ConfigError(
                 "Key - %s doesn't exist in the YAML configuration" % key)
         return value
@@ -78,5 +79,5 @@ def write_to_file(self, filepath):
 
     config_dict = yaml.load(yaml_f)
     config_obj = Config(config_dict)
-    print config_obj.project.name
-    print config_obj["project"]["name"]
+    print (config_obj.project.name)
+    print (config_obj["project"]["name"])

popgen/data.py

@@ -1,9 +1,10 @@
+from __future__ import print_function
 import os
 
 import pandas as pd
 import numpy as np
 
-from config import ConfigError
+from .config import ConfigError
 
 
 class DB(object):
@@ -89,8 +90,8 @@ def enumerate_geo_ids_for_scenario(self, scenario_config):
             self.geo_ids = []
             for region_id in self.region_ids:
                 self.geo_ids += self.get_geo_ids_for_region(region_id)
-        except ConfigError, e:
-            print "KeyError", e
+        except ConfigError as e:
+            print ("KeyError", e)
             self.geo_ids = self.geo_ids_all
             # self.sample_geo_ids = self.sample_geo_ids_all
             self.region_ids = self.region_ids_all

popgen/draw.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 import pandas as pd
 import numpy as np
 from scipy import stats
@@ -86,11 +87,11 @@ def _return_cumulative_probability(self, geo_sample_weights):
 
     def _pick_households(self, geo_id_frequencies, geo_cumulative_weights):
         last = 0
-        rand_numbers = np.random.random(geo_id_frequencies.sum())
+        rand_numbers = np.random.random(int(geo_id_frequencies.sum()))
         list_rows_syn_subpop = []
         for column in self.geo_frequencies.columns.values:
             rows = self.geo_row_idx[column]
-            column_frequency = geo_id_frequencies[column]
+            column_frequency = int(geo_id_frequencies[column])
             column_bins = np.searchsorted(geo_cumulative_weights[column],
                                           (rand_numbers[
                                            last:last + column_frequency]),

popgen/ipf.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 import copy
 
 import numpy as np
@@ -62,7 +63,7 @@ def __init__(self, seed_all, seed, idx, marginals, ipf_config,
     def run_ipf(self):
         self.frequencies = self._correct_zero_cell_issue()
         # self.frequencies = self.seed["frequency"].values
-        for c_iter in xrange(self.ipf_iters):
+        for c_iter in range(self.ipf_iters):
             # print "Iter:", c_iter
             self._adjust_cell_frequencies()
             # Checks for convergence every 5 iterations
@@ -273,7 +274,7 @@ def _run_ipf_all_geos(self, entity, seed_geo, seed_all, row_idx, marginals,
             sample_geo_id = geo_corr_to_sample.loc[geo_id,
                                                    self.sample_geo_name]
             if isinstance(sample_geo_id, pd.Series):
-                seed_geo_levels_list = range(len(seed_geo.index.names))
+                seed_geo_levels_list = tuple(range(len(seed_geo.index.names)))
                 seed_for_geo_id = (seed_geo.loc[sample_geo_id.tolist()]
                                    .sum(level=seed_geo_levels_list[1:]))
                 # print (seed_geo.loc[sample_geo_id.tolist()])
@@ -340,7 +341,7 @@ def _get_stacked_constraints(self, constraints_list):
 
     def _get_columns_constraints_dict(self, constraints_dict):
         columns_constraints_dict = {}
-        for entity, constraints in constraints_dict.iteritems():
+        for entity, constraints in constraints_dict.items():
             columns_constraints_dict[entity] = (constraints
                                                 .index.values.tolist())
         # print columns_constraints_dict