better fix for #57, fake node test, refactored NetworkPlan init

sequencer/NetworkPlan.py

@@ -4,8 +4,6 @@
 import fiona
 import numpy as np
 import networkx as nx
-from scipy.sparse import csr_matrix
-import scipy.sparse.csgraph as graph
 import pandas as pd
 import logging
 import copy
@@ -26,13 +24,18 @@ def __init__(self, network, metrics, **kwargs):
         self.priority_metric = kwargs['prioritize'] if 'prioritize' in kwargs else 'population'
         self.proj = kwargs['proj'] if 'proj' in kwargs else 'utm'
 
-        # do the real init
+        # FIXME:
+        # Remove the dependency that sequencer has on the
+        # original metrics file (this is terrible coupling)
+        # see sequencer:_clean_results()
+        self._original_metrics = metrics
+
         self._init_helper(network, metrics)
 
 
     def _init_helper(self, network, metrics):
         """
-        re-usable init bypassing read shp,csv
+        All initialization (cleaning up metrics, network, etc)
         """
 
         # Load in and align input data
@@ -41,7 +44,7 @@ def _init_helper(self, network, metrics):
                                                  metrics, 
                                                  loc_tol = self.TOL)
 
-        self.coord_values = np.array(self.coords.values())
+        self.coord_values = self.coords.values()
 
         # Set the edge weight to the distance between those nodes
         self._weight_edges()
@@ -83,14 +86,7 @@ def from_files(cls, shp, csv, **kwargs):
         # Pass along the projection
         kwargs['proj'] = shapefile.crs['proj']
 
-        nwp = cls(nx.read_shp(shp), pd.read_csv(csv, header=1), **kwargs)
-
-        # FIXME:  
-        # This is a really bad way to do this...the sequencer has a dependency
-        # on the csv_p attribute (i.e. the original csv) so leave it for now
-        nwp.csv_p = csv
-        return nwp
-
+        return cls(nx.read_shp(shp), pd.read_csv(csv, header=1), **kwargs)
 
     @classmethod
     def _assert_proj_match(self, shp, csv):
@@ -283,12 +279,16 @@ def network(self):
         """returns the DiGraph Object representation of the graph"""
         return self._network
 
+    @property
+    def original_metrics(self):
+        """returns the original (unprocessed) metrics data_frame"""
+        return self._original_metrics
+
     @property
     def metrics(self):
         """returns the nodal metrics Pandas DataFrame"""
         return self._metrics
 
-
 def download_scenario(scenario_number, directory_name=None, username=None, password=None,
                       np_url='http://networkplanner.modilabs.org/'):
 

sequencer/Sequencer.py

@@ -132,8 +132,7 @@ def upstream_distance(self, node):
         return 0.0
 
     def sequence(self):
-        self.results = pd.DataFrame(self._sequence()).set_index('Sequence..Far.sighted.sequence')
-
+        self.results = pd.DataFrame(self._sequence(), dtype=object).set_index('Sequence..Far.sighted.sequence')
         # Post process for output
         self._build_node_wkt()
         self._build_edge_wkt()
@@ -235,7 +234,7 @@ def _build_edge_wkt(self):
         r = self.results
         # Iterate through the nodes and their parent
         for rank, fnode, tnode in zip(r.index, r['Sequence..Upstream.id'], r['Sequence..Vertex.id']):
-            if not np.isnan(fnode):
+            if fnode:
                 if np.any(np.mod([fnode, tnode], 1) != 0):
                     raise Exception('Non-integral node index in results.')
                 # Set the edge attributes with those found in sequencing
@@ -291,11 +290,8 @@ def _clean_results(self):
         """This joins the sequenced results on the metrics dataframe and reappends the dropped rows"""
 
         logger.info('Joining Sequencer Results on Input Metrics')
-        if not hasattr(self.networkplan, 'csv_p'):
-            logger.info('no original csv file found, skipping')
-            return
-
-        orig = pd.read_csv(self.networkplan.csv_p, header=1)
+        # FIXME:  Remove this dependency on original_metrics
+        orig = self.networkplan.original_metrics
         orig.columns = parse_cols(orig)
         self.networkplan.metrics.index.name = 'Sequence..Vertex.id'
         sequenced_metrics = pd.merge(self.networkplan.metrics.reset_index(), self.results.reset_index(), on='Sequence..Vertex.id')