Update trcrpm to Python 3.

pythenv.sh

@@ -7,8 +7,8 @@ set -Ceu
 
 : ${PYTHON:=python}
 root=`cd -- "$(dirname -- "$0")" && pwd`
-platform=`"${PYTHON}" -c 'import distutils.util as u; print u.get_platform()'`
-version=`"${PYTHON}" -c 'import sys; print sys.version[0:3]'`
+platform=`"${PYTHON}" -c 'import distutils.util as u; print(u.get_platform())'`
+version=`"${PYTHON}" -c 'import sys; print(sys.version[0:3])'`
 
 # The lib directory varies depending on
 #

setup.py

@@ -78,22 +78,22 @@ def get_version():
 
 def write_version_py(path):
     try:
-        with open(path, 'rb') as f:
+        with open(path, 'r') as f:
             version_old = f.read()
     except IOError:
         version_old = None
     version_new = '__version__ = %r\n' % (full_version,)
     if version_old != version_new:
-        print 'writing %s' % (path,)
-        with open(path, 'wb') as f:
+        print('writing %s' % (path,))
+        with open(path, 'w') as f:
             f.write(version_new)
 
 def readme_contents():
     readme_path = os.path.join(
         os.path.abspath(os.path.dirname(__file__)),
         'README.md')
     with open(readme_path) as readme_file:
-        return unicode(readme_file.read(), 'UTF-8')
+        return str(readme_file.read())
 
 class local_build_py(build_py):
     def run(self):

src/trcrpm.py

@@ -61,7 +61,7 @@ def __init__(self, chains, lag, variables, rng, dependencies=None):
         # Derived attributes.
         self.window = self.lag + 1
         self.variables_lagged = list(itertools.chain.from_iterable([
-            ['%s.lag.%d' % (varname, i,) for i in xrange(self.lag, -1, -1)]
+            ['%s.lag.%d' % (varname, i,) for i in range(self.lag, -1, -1)]
             for varname in self.variables
         ]))
         self.variable_index = {var: i for i, var in enumerate(self.variables)}
@@ -202,7 +202,7 @@ def simulate_ancestral(self, timepoints, variables, nsamples, multiprocess=1):
                 constraints, parents, self._variable_to_index, nsamples)
             for state in self.engine.states
         ]
-        mapper = parallel_map if multiprocess else map
+        mapper = parallel_map if multiprocess else itertools.starmap
         self.engine._seed_states()
         samples_raw_list = mapper(_simulate_ancestral_mp, args)
         samples_raw = itertools.chain.from_iterable(samples_raw_list)
@@ -285,15 +285,16 @@ def _incorporate_new_timepoints(self, frame):
         """Incorporate fresh sample ids as new cgpm rows."""
         new_timepoints = frame.index[~frame.index.isin(self.dataset.index)]
         new_observations = frame[self.variables].loc[new_timepoints]
-        self.dataset = self.dataset.append(new_observations)
+        self.dataset = pd.concat([self.dataset, new_observations],
+                                 ignore_index=False)
         new_rows = [self._get_timepoint_row(t) for t in new_timepoints]
         if self.initialized:
             outputs = self.engine.states[0].outputs
             assert all(len(row) == len(outputs) for row in new_rows)
-            rowids_cgpm = range(
+            rowids_cgpm = list(range(
                 self.engine.states[0].n_rows(),
                 self.engine.states[0].n_rows() + len(new_rows)
-            )
+            ))
             observations_cgpm = [
                 {i: row[i] for i in outputs if not np.isnan(row[i])}
                 for row in new_rows
@@ -353,7 +354,7 @@ def _convert_nan_timepoint_to_cgpm_rowid_cells(
         in, and dict containing columns and values to populate."""
         nan_col_names = nan_timepoint_mask[nan_timepoint_mask].index
         nan_col_idxs = [self._variable_to_index(col) for col in nan_col_names]
-        nan_col_values = frame.loc[nan_timepoint, nan_col_names].as_matrix()
+        nan_col_values = frame.loc[nan_timepoint, nan_col_names].to_numpy()
         cgpm_rowids = self._timepoint_to_rowids(nan_timepoint)
         cgpm_rowids_cells = [
             {col_idx - lag: value
@@ -398,7 +399,7 @@ def _timepoint_to_rowids(self, timepoint):
 
     def _get_timepoint_window(self, timepoint):
         """Return the previous timepoints in the window of this timepoint."""
-        return range(timepoint, timepoint + self.window)
+        return list(range(timepoint, timepoint + self.window))
 
     def _variable_to_index(self, variable, lag=0):
         """Convert variable name to cgpm output index."""
@@ -407,7 +408,7 @@ def _variable_to_index(self, variable, lag=0):
 
     def _variable_to_window_indexes(self, variable):
         """Convert variable name to list of cgpm output indexes in its window."""
-        return [self._variable_to_index(variable, l) for l in xrange(self.window)]
+        return [self._variable_to_index(variable, l) for l in range(self.window)]
 
     def _variable_indexes(self):
         """Return list of cgpm output indexes, one per variable at lag 0."""
@@ -574,14 +575,14 @@ def to_metadata(self):
 # These functions must be defined top-level in the module to work with
 # parallel_map.
 
-def _simulate_ancestral_mp((state, timepoints, variables, rowids, targets,
-        constraints, parents, variable_to_index, nsamples)):
+def _simulate_ancestral_mp(state, timepoints, variables, rowids, targets,
+        constraints, parents, variable_to_index, nsamples):
     """Simulate timepoints and variables ancestrally (multiple samples)."""
     return [
         _simulate_ancestral_one(
             state, timepoints, variables, rowids, targets, constraints, parents,
             variable_to_index)
-        for _i in xrange(nsamples)
+        for _i in range(nsamples)
     ]
 
 

tests/test_data_transforms.py

@@ -279,7 +279,7 @@ def test_timepoint_to_rowid():
     rng = np.random.RandomState(2)
     trcrpm = TRCRP_Mixture(chains=1, lag=0, variables=FRAME.columns, rng=rng)
     trcrpm.incorporate(FRAME)
-    for i in xrange(len(FRAME)):
+    for i in range(len(FRAME)):
         assert trcrpm._timepoint_to_rowid(i) == i
         assert trcrpm._timepoint_to_rowid(i) == i