fixed accuracy

CONTRIBUTING.md

@@ -55,3 +55,7 @@ sudo make install
 #  Run the tests against the installed extension.
 make test
 ```
+
+## Submitting contributions
+
+Before opening a pull request (or submitting a contribution) you will need to sign a Contributor License Agreement (CLA) before making a submission, [learn more here](https://carto.com/contributions).

src/pg/sql/12_fastcontour.sql

@@ -0,0 +1,318 @@
+CREATE OR REPLACE FUNCTION CDB_contour2(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN classmethod integer,
+    IN steps integer,
+    IN polygons integer DEFAULT 0
+    )
+-- RETURNS geometry  AS $$
+RETURNS TABLE(cartodb_id bigint, the_geom geometry, break numeric)   AS $$
+DECLARE
+    geoplane geometry[];
+    breaks numeric[];
+    bucketin integer[];
+    gs geometry[];
+    g geometry;
+    vertex geometry[];
+    vv numeric[];
+    bu integer[];
+    inter numeric[];
+    interp12 geometry[];
+    interp23 geometry[];
+    interp31 geometry[];
+    segment geometry[];
+    running_merge geometry[];
+    cartodb_id bigint;
+    the_geom geometry;
+    break numeric;
+    i integer;
+BEGIN
+
+    -- debug info
+    raise notice 'Points: %', array_length(colin,1);
+
+    -- translate to planar to avoid ST_LineInterpolatePoint errors for points far from equator
+    WITH a AS(
+        SELECT ST_transform(t.x, 3857) as gp FROM unnest(geomin) as t(x)
+    )
+    SELECT array_agg(gp) into geoplane FROM a;
+
+    -- generate the breaks
+    SELECT
+        CASE
+            classmethod
+        WHEN 0 THEN
+            cdb_crankshaft.CDB_EqualIntervalBins(colin, steps)
+        WHEN 1 THEN
+            cdb_crankshaft.CDB_HeadsTailsBins(colin, steps)
+        WHEN 2 THEN
+            cdb_crankshaft.CDB_JenksBins(colin, steps)
+        ELSE
+            cdb_crankshaft.CDB_QuantileBins(colin, steps)
+        END
+    INTO breaks;
+
+    -- assign bucket to each point
+    WITH
+    a as(
+        SELECT
+            width_bucket(t.x, breaks) as bin
+        FROM unnest(colin) as t(x)
+    )
+    SELECT array_agg(bin) INTO bucketin FROM a;
+
+    -- generate the TIN
+    WITH
+        -- a as (SELECT ST_transform(x, 3857) as e FROM unnest(geomin) t(x)),
+        a as (SELECT unnest(geomin) AS e),
+        b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e)) AS t FROM a),
+        c as (SELECT (ST_Dump(t)).geom AS v FROM b)
+    SELECT array_agg(v) INTO gs FROM c;
+
+    RAISE NOTICE 'TIN size: %', array_length(gs,1);
+    raise notice 'ratio: %', array_length(gs,1)::numeric /  array_length(colin,1)::numeric;
+
+   i:= 0;
+
+    -- ======================================================================================
+
+    -- loop in the TIN
+    FOREACH g IN ARRAY gs
+    LOOP
+        -- retrieve the value and bucket of each vertex
+        SELECT
+            -- array_agg(a.v),array_agg(b.c), array_agg(b.bk)
+            array_agg(b.gp),array_agg(b.c), array_agg(b.bk)
+            INTO vertex, vv, bu
+        FROM
+        (
+            SELECT (ST_DumpPoints(g)).geom AS v limit 3
+        ) as a
+        CROSS JOIN LATERAL
+        (
+            SELECT
+                t.*
+            FROM
+                unnest(geomin, colin, bucketin, geoplane) as t(geo, c, bk, gp)
+            WHERE ST_Equals(geo, a.v)
+            LIMIT 1
+        ) as b;
+
+        -- continue when there is no contour line crossing the current cell
+        CONTINUE WHEN bu[1] = bu[2] and bu[1] = bu[3];
+
+
+        -- we have contour lines in this cell, let's find their intersections with triangle sides
+
+        interp12 := _get_cell_intersects(vertex, vv , bu, breaks, 1, 2);
+        interp23 := _get_cell_intersects(vertex, vv , bu, breaks, 2, 3);
+        interp31 := _get_cell_intersects(vertex, vv , bu, breaks, 3, 1);
+
+        -- raise notice 'interp12 %', interp12;
+
+        -- create segments crossing the cell per break
+        WITH
+        a as(
+            SELECT
+            t.*
+            FROM
+            unnest(breaks, interp12, interp23, interp31) as t(br, p12 , p23, p31)
+        ),
+        b as(
+            SELECT
+                case
+                when
+                    (p12 is not null and p23 is not null and ST_equals(p12, p23)=false) OR
+                    (p23 is not null and p31 is not null and ST_equals(p23, p31)=false) OR
+                    (p31 is not null and p12 is not null and ST_equals(p31, p12)=false)
+                then ST_MakeLine(ARRAY[p12, p23, p31]::geometry[])
+                else null::geometry end as segm,
+                br
+            FROM a
+        )
+        SELECT
+            array_agg(b.segm) into segment
+        FROM unnest(breaks) as c(x) left join b on b.br = c.x;
+
+
+        -- sew the segments and assign breaks
+        IF i = 0 THEN
+            running_merge = segment;
+            i := 1;
+        ELSE
+            WITH
+            a AS(
+                SELECT
+                    ST_CollectionExtract(x, 2) as x,
+                    y
+                FROM unnest(running_merge,segment) as t(x,y)
+            ),
+            b AS(
+                SELECT
+                    ST_collect(x,y) as element
+                FROM a
+            )
+            SELECT
+                array_agg(element) into running_merge
+            FROM b;
+
+        END IF;
+
+    -- loop end
+    END LOOP;
+
+    -- ====== ^^^ LOOP END ===========================================================================
+
+    -- return some stuff
+    IF polygons = 1 THEN
+        RETURN QUERY
+        with a as(
+            SELECT
+                br,
+                ST_CollectionExtract(geo, 2) as geo
+            FROM unnest(running_merge, breaks) as t(geo, br)
+        ),
+        b as(
+            SELECT
+                ST_LineMerge(geo) as v
+            FROM a
+        ),
+        c as(
+            SELECT
+                ST_Polygonize(
+                    ST_Node(
+                        ST_LineMerge(
+                            ST_Union(
+                                v,
+                                ST_ExteriorRing(
+                                    ST_Convexhull(v)
+                                )
+                            )
+                        )
+                    )
+                ) as g1
+            FROM
+                b
+        ),
+        d as(
+            SELECT
+            (st_dump(g1)).geom as geo
+            FROM c
+        )
+        SELECT
+        row_number() over() as cartodb_id,
+        ST_Transform(geo, 4326) as the_geom,
+        1::numeric as break
+        from d
+        WHERE ST_GeometryType(geo) = 'ST_Polygon';
+    ELSE
+        RETURN QUERY
+        with a as(
+            SELECT
+                br,
+                ST_CollectionExtract(geo, 2) as geo
+            FROM unnest(running_merge, breaks) as t(geo, br)
+        ),
+        b as(
+            SELECT
+                ST_LineMerge(geo) as geo,
+                br
+            FROM a
+        )
+        SELECT
+        row_number() over() as cartodb_id,
+        ST_Transform(geo, 4326) as the_geom,
+        br as break
+        from b;
+    END IF;
+
+END;
+$$ language plpgsql IMMUTABLE;
+
+
+
+-- ========================= support function =========================
+
+CREATE OR REPLACE FUNCTION _get_cell_intersects(
+    IN vertex geometry[],
+    IN vv numeric[],
+    IN bu integer[],
+    IN breaks numeric[],
+    IN i1 integer,
+    IN i2 integer
+    )
+RETURNS geometry[]  AS $$
+DECLARE
+    result geometry[];
+BEGIN
+
+    result := array_fill(null::geometry, ARRAY[array_length(breaks, 1)]);
+
+    IF bu[i1] <> bu[i2] THEN
+
+        SELECT
+            array_agg(b.point) INTO result
+        FROM
+        (
+            SELECT
+                (t.x-vv[i1])/(vv[i2]-vv[i1]) as p
+            FROM unnest(breaks) as t(x)
+        ) AS a
+        LEFT JOIN LATERAL
+        (
+            SELECT
+                ST_LineInterpolatePoint(
+                    ST_MakeLine(
+                        vertex[i1],
+                        vertex[i2]
+                    ), a.p)
+                as point
+            WHERE a.p BETWEEN 0 AND 1
+        ) AS b
+        ON 1=1;
+    END IF;
+
+    return result;
+
+END;
+$$ language plpgsql IMMUTABLE;
+
+
+
+
+-- ============ test query ==========================================================================
+-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================-- ============ test query ==========================================================================
+
+
+with
+a0 as(
+    select * from table_4804232032
+    -- where cartodb_id % 2 = 0
+),
+a as(
+  SELECT
+  array_agg(the_geom)  as geomin,
+  array_agg(temp::numeric) as   colin
+  FROM a0
+  where temp is not   null
+  ),
+b as(
+  SELECT
+     c.*
+   from a, CDB_contour2(
+        a.geomin,
+        a.colin,
+        3,
+        7
+      )  c
+  )
+  SELECT
+  *,
+  st_astext(the_geom) as text,
+  st_transform(the_geom, 3857) as the_geom_webmercator
+  from b
+  where the_geom is not null;
+
+
+
+

src/pg/sql/22_maxp.sql

@@ -1,17 +0,0 @@
--- max-p regionalization
-
-CREATE OR REPLACE FUNCTION
-  CDB_MaxP(
-      subquery TEXT,
-      colnames TEXT[],
-      floor_variable TEXT,
-      min_size int default 1,
-      initial int default 99,
-      geom_col TEXT DEFAULT 'the_geom',
-      id_col TEXT DEFAULT 'cartodb_id')
-RETURNS TABLE (region_class text, p_val numeric, rowid bigint)
-AS $$
-  from crankshaft.clustering import MaxP
-  maxp = MaxP()
-  return maxp.maxp(subquery, colnames, floor_variable, floor=min_size)
-$$ LANGUAGE plpythonu;

src/py/crankshaft/crankshaft/analysis_data_provider.py

@@ -65,17 +65,3 @@ class AnalysisDataProvider:
             return data
         except plpy.SPIError, err:
             plpy.error('Analysis failed: %s' % err)
-
-    def get_maxp(self, params):
-        """fetch data for max-p"""
-        try:
-            query = pu.construct_neighbor_query('queen', params)
-            data = plpy.execute(query)
-
-            if len(data) == 0:
-                # TODO: replace with better message in PR#157
-                plpy.error('No non-null valued rows')
-
-            return data
-        except plpy.SPIError, err:
-            plpy.error('Analysis failed: %s' % err)

src/py/crankshaft/crankshaft/clustering/__init__.py

@@ -2,4 +2,3 @@
 from moran import *
 from kmeans import *
 from getis import *
-from maxp import *

src/py/crankshaft/crankshaft/clustering/getis.py

@@ -38,7 +38,7 @@ class Getis:
                              ("num_ngbrs", num_ngbrs)])
 
         result = self.data_provider.get_getis(w_type, qvals)
-        attr_vals = pu.get_attribute(result)
+        attr_vals = pu.get_attributes(result)
 
         # build PySAL weight object
         weight = pu.get_weight(result, w_type, num_ngbrs)

src/py/crankshaft/crankshaft/clustering/maxp.py

@@ -1,85 +0,0 @@
-"""
-  max-p clustering
-"""
-
-import pysal as ps
-import numpy as np
-import random
-import time
-
-import crankshaft.pysal_utils as pu
-from crankshaft.analysis_data_provider import AnalysisDataProvider
-
-
-class MaxP:
-    def __init__(self, data_provider=None):
-        if data_provider:
-            self.data_provider = data_provider
-        else:
-            self.data_provider = AnalysisDataProvider()
-
-    def maxp(self, subquery, colnames, floor_variable=None,
-            floor=1,
-            geom_col='the_geom', id_col='cartodb_id',
-            ):
-        """
-            Inputs:
-            @param subquery (text): subquery to expose the data need for the
-                                    analysis. This query needs to expose all
-                                    of the columns in `colnames`, `id_col`, and
-                                    `geom_col`
-            @param colnames (list): list of column names (as strings). This is
-                                    used to calculate intra-regional homogeneity.
-            @param floor_variable (text): name of column variable for the floor
-            @param floor (int): the minimum bound for a variable that has to be
-                                obtained in each region,
-            @param geom_col (text): geometry column used for calculating the
-                                    spatial neighborhood
-            @param id_col (text): id column used for keeping the identity of
-                                  the data
-            Outputs: a list of tuples with the following columns:
-
-            classification_id: group that the geometry belongs to
-            rowid: identifier from id_col
-        """
-        params = {'subquery': subquery,
-                  'colnames': colnames,
-                  'id_col': id_col,
-                  'geom_col': geom_col,
-                  'floor':
-                  'floor_variable':floor_variable,
-                  }
-
-        resp = self.data_provider.get_maxp(params)
-        attr_vals = pu.get_attributes(resp, len(colnames))
-        weight = pu.get_weight(resp, w_type='queen')
-
-        if floor_variable == None:
-            floor_variable = np.ones((weight.n, 1))
-        else:
-            floor_column_id = colnames.index(floor_variable)
-            floor_variable = attr_vals.transpose()[floor_column_id]
-
-        start_time = time.time()
-        r = ps.Maxp(weight, attr_vals,
-                    floor=floor,
-                    floor_variable= floor_variable,
-                    initial=10)
-        # print r.regions
-        cluster_classes = get_cluster_classes(weight.id_order, r.regions)
-        r.inference()
-        # print "elapsed time: ", time.time() - start_time
-        return zip(cluster_classes, [r.pvalue] * len(weight.id_order),
-                   weight.id_order)
-
-
-def get_cluster_classes(ids, clusters):
-    """
-
-    """
-    cluster_classes = []
-    for i in ids:
-        for r_id, r in enumerate(clusters):
-            if i in r:
-                cluster_classes.append(r_id)
-    return cluster_classes

src/py/crankshaft/crankshaft/clustering/moran.py

@@ -39,7 +39,7 @@ class Moran:
         result = self.data_provider.get_moran(w_type, params)
 
         # collect attributes
-        attr_vals = pu.get_attribute(result, 1)
+        attr_vals = pu.get_attributes(result)
 
         # calculate weights
         weight = pu.get_weight(result, w_type, num_ngbrs)
@@ -68,7 +68,7 @@ class Moran:
 
         result = self.data_provider.get_moran(w_type, params)
 
-        attr_vals = pu.get_attribute(result, 1)
+        attr_vals = pu.get_attributes(result)
         weight = pu.get_weight(result, w_type, num_ngbrs)
 
         # calculate LISA values
@@ -96,8 +96,8 @@ class Moran:
         result = self.data_provider.get_moran(w_type, params)
 
         # collect attributes
-        numer = pu.get_attribute(result, 1)
+        numer = pu.get_attributes(result, 1)
-        denom = pu.get_attribute(result, 2)
+        denom = pu.get_attributes(result, 2)
 
         weight = pu.get_weight(result, w_type, num_ngbrs)
 
@@ -126,8 +126,8 @@ class Moran:
         result = self.data_provider.get_moran(w_type, params)
 
         # collect attributes
-        numer = pu.get_attribute(result, 1)
+        numer = pu.get_attributes(result, 1)
-        denom = pu.get_attribute(result, 2)
+        denom = pu.get_attributes(result, 2)
 
         weight = pu.get_weight(result, w_type, num_ngbrs)
 
@@ -157,8 +157,8 @@ class Moran:
         result = self.data_provider.get_moran(w_type, params)
 
         # collect attributes
-        attr1_vals = pu.get_attribute(result, 1)
+        attr1_vals = pu.get_attributes(result, 1)
-        attr2_vals = pu.get_attribute(result, 2)
+        attr2_vals = pu.get_attributes(result, 2)
 
         # create weights
         weight = pu.get_weight(result, w_type, num_ngbrs)

src/py/crankshaft/crankshaft/pysal_utils/pysal_utils.py

@@ -13,10 +13,10 @@ def construct_neighbor_query(w_type, query_vals):
         @param query_vals dict: values used to construct the query
     """
 
-    if w_type.lower() == 'queen':
+    if w_type.lower() == 'knn':
-        return queen(query_vals)
-    else:
         return knn(query_vals)
+    else:
+        return queen(query_vals)
 
 
 # Build weight object
@@ -60,17 +60,16 @@ def query_attr_select(params):
     attr_string = ""
     template = "i.\"%(col)s\"::numeric As attr%(alias_num)s, "
 
-    if ('time_cols' in params) or ('colnames' in params):
+    if 'time_cols' in params:
         # if markov analysis
-        attrs = (params['time_cols'] if 'time_cols' in params
+        attrs = params['time_cols']
-                 else params['colnames'])
 
         for idx, val in enumerate(attrs):
             attr_string += template % {"col": val, "alias_num": idx + 1}
     else:
         # if moran's analysis
         attrs = [k for k in params
-                 if k not in ('id_col', 'geom_col',
+                 if k not in ('id_col', 'geom_col', 'subquery',
                               'num_ngbrs', 'subquery')]
 
         for idx, val in enumerate(attrs):
@@ -101,12 +100,9 @@ def query_attr_where(params):
     attr_string = []
     template = "idx_replace.\"%s\" IS NOT NULL"
 
-    # TODO: generalize to colnames or not only?
+    if 'time_cols' in params:
-    #       this would reduce the complexity of the code here
+        # markov where clauses
-    if ('time_cols' in params) or ('colnames' in params):
+        attrs = params['time_cols']
-        # markov and max-p where clauses
-        attrs = (params['time_cols'] if 'time_cols' in params
-                 else params['colnames'])
         # add values to template
         for attr in attrs:
             attr_string.append(template % attr)
@@ -115,7 +111,7 @@ def query_attr_where(params):
 
         # get keys
         attrs = [k for k in params
-                 if k not in ('id_col', 'geom_col',
+                 if k not in ('id_col', 'geom_col', 'subquery',
                               'num_ngbrs', 'subquery')]
 
         # add values to template
@@ -194,24 +190,10 @@ def queen(params):
 # to add more weight methods open a ticket or pull request
 
 
-def get_attributes(query_resp, n_cols):
+def get_attributes(query_res, attr_num=1):
     """
-        Extract the time columns and bin appropriately
+        @param query_res: query results with attributes and neighbors
-    """
-    return np.array([[x['attr' + str(i + 1)] for x in query_resp]
-                     for i in range(n_cols)], dtype=float).transpose()
-
-
-def get_attribute(query_res, attr_num=1):
-    """
-        Inputs:
-        @param query_res: query results with attributes and other info, of the
-                          form [{'attr1': ..., 'id_col': ...},
-                                {'attr1': ..., 'id_col': ...},
-                                ...]
         @param attr_num: attribute number (1, 2, ...)
-        Returns:
-        a numpy array that represents the column in 'attr' number attr_num
     """
     return np.array([x['attr' + str(attr_num)] for x in query_res],
                     dtype=np.float)

src/py/crankshaft/crankshaft/space_time_dynamics/markov.py

@@ -68,7 +68,7 @@ class Markov:
         weights.transform = 'r'
 
         # prep time data
-        t_data = pu.get_attributes(query_result, len(time_cols))
+        t_data = get_time_data(query_result, time_cols)
 
         sp_markov_result = ps.Spatial_Markov(t_data,
                                              weights,
@@ -88,15 +88,61 @@ class Markov:
                                   sp_markov_result.classes[:, -1])
 
         # find the ups and down and overall distribution of each cell
-        trend_up, trend_down, trend, \
+        trend_up, trend_down, trend, volatility = get_prob_stats(prob_dist, sp_markov_result.classes[:, -1])
-            volatility = get_prob_stats(
-                prob_dist,
-                sp_markov_result.classes[:, -1])
 
         # output the results
         return zip(trend, trend_up, trend_down, volatility, weights.id_order)
 
 
+
+def get_time_data(markov_data, time_cols):
+    """
+        Extract the time columns and bin appropriately
+    """
+    num_attrs = len(time_cols)
+    return np.array([[x['attr' + str(i)] for x in markov_data]
+                     for i in range(1, num_attrs+1)], dtype=float).transpose()
+
+
+# not currently used
+def rebin_data(time_data, num_time_per_bin):
+    """
+        Convert an n x l matrix into an (n/m) x l matrix where the values are
+         reduced (averaged) for the intervening states:
+          1 2 3 4    1.5 3.5
+          5 6 7 8 -> 5.5 7.5
+          9 8 7 6    8.5 6.5
+          5 4 3 2    4.5 2.5
+
+          if m = 2, the 4 x 4 matrix is transformed to a 2 x 4 matrix.
+
+        This process effectively resamples the data at a longer time span n
+         units longer than the input data.
+        For cases when there is a remainder (remainder(5/3) = 2), the remaining
+         two columns are binned together as the last time period, while the
+         first three are binned together for the first period.
+
+        Input:
+          @param time_data n x l  ndarray: measurements of an attribute at
+           different time intervals
+          @param num_time_per_bin int: number of columns to average into a new
+           column
+        Output:
+          ceil(n / m) x l ndarray of resampled time series
+    """
+
+    if time_data.shape[1] % num_time_per_bin == 0:
+        # if fit is perfect, then use it
+        n_max = time_data.shape[1] / num_time_per_bin
+    else:
+        # fit remainders into an additional column
+        n_max = time_data.shape[1] / num_time_per_bin + 1
+
+    return np.array(
+      [time_data[:, num_time_per_bin * i:num_time_per_bin * (i+1)].mean(axis=1)
+       for i in range(n_max)]).T
+
+
 def get_prob_dist(transition_matrix, lag_indices, unit_indices):
     """
         Given an array of transition matrices, look up the probability

src/py/crankshaft/test/test_clustering_maxp.py

@@ -1,62 +0,0 @@
-import unittest
-import numpy as np
-
-
-# from mock_plpy import MockPlPy
-# plpy = MockPlPy()
-#
-# import sys
-# sys.modules['plpy'] = plpy
-from helper import fixture_file
-from crankshaft.clustering import MaxP
-from crankshaft.analysis_data_provider import AnalysisDataProvider
-import crankshaft.clustering as cc
-
-from crankshaft import random_seeds
-import json
-from collections import OrderedDict
-
-
-class FakeDataProvider(AnalysisDataProvider):
-    def __init__(self, fixturedata):
-        self.your_maxp_data = fixturedata
-
-    def get_maxp(self, params):
-        """
-          Replace this function name with the one used in your algorithm,
-          and make sure to use the same function signature that is written
-          for this algo in analysis_data_provider.py
-        """
-        return self.your_maxp_data
-
-class MaxPTest(unittest.TestCase):
-    """Testing class for max-p regionalization"""
-
-    def setUp(self):
-        self.neighbor_data = json.loads(
-          open(fixture_file('maxp.json')).read())
-        self.neighbor_data = self.neighbor_data['rows']
-        self.params = {"subquery": "select * from fake_table",
-                       "colnames": ['population','median_hh_income'],
-                       "floor_variable": 'population',
-                       "floor": 260000}
-
-    def test_maxp(self):
-        """
-        """
-        data = [{'id': d['id'],
-                 'attr1': d['attr1'],
-                 'attr2':d['attr2'],
-                 'neighbors': d['neighbors']} for d in self.neighbor_data]
-
-        random_seeds.set_random_seeds(1234)
-        maxp = MaxP(FakeDataProvider(data))
-        regions = maxp.maxp('select * from research_nothing',['population','median_hh_income'],floor_variable='population',floor=260000)
-        region_labels = [a[0] for a in regions]
-        data_regionalized = zip(data,region_labels)
-        for i in set(region_labels):
-            sum_pop = 0
-            for n in data_regionalized:
-                if n[1] == i:
-                    sum_pop += n[0]['attr1']
-            self.assertGreaterEqual(sum_pop, 260000)

src/py/crankshaft/test/test_pysal_utils.py

@@ -1,10 +1,8 @@
 import unittest
-import json
 
 import crankshaft.pysal_utils as pu
 from crankshaft import random_seeds
 from collections import OrderedDict
-from helper import fixture_file
 
 
 class PysalUtilsTest(unittest.TestCase):
@@ -37,8 +35,6 @@ class PysalUtilsTest(unittest.TestCase):
                              "subquery": "SELECT * FROM a_list",
                              "geom_col": "the_geom",
                              "num_ngbrs": 321}
-        self.neighbors_data = json.loads(
-            open(fixture_file('neighbors_markov.json')).read())
 
     def test_query_attr_select(self):
         """Test query_attr_select"""
@@ -162,184 +158,3 @@ class PysalUtilsTest(unittest.TestCase):
         ans4 = [(None, None, None, None)]
         self.assertEqual(pu.empty_zipped_array(2), ans2)
         self.assertEqual(pu.empty_zipped_array(4), ans4)
-
-    def test_get_attributes(self):
-        """Test get_time_data"""
-        import numpy as np
-        data = [{'attr1': d['y1995'],
-                 'attr2': d['y1996'],
-                 'attr3': d['y1997'],
-                 'attr4': d['y1998'],
-                 'attr5': d['y1999'],
-                 'attr6': d['y2000'],
-                 'attr7': d['y2001'],
-                 'attr8': d['y2002'],
-                 'attr9': d['y2003'],
-                 'attr10': d['y2004'],
-                 'attr11': d['y2005'],
-                 'attr12': d['y2006'],
-                 'attr13': d['y2007'],
-                 'attr14': d['y2008'],
-                 'attr15': d['y2009']} for d in self.neighbors_data]
-
-        result = pu.get_attributes(
-            data, len(['y1995', 'y1996', 'y1997', 'y1998',
-                       'y1999', 'y2000', 'y2001', 'y2002',
-                       'y2003', 'y2004', 'y2005', 'y2006',
-                       'y2007', 'y2008', 'y2009']))
-
-        # expected was prepared from PySAL example:
-        # f = ps.open(ps.examples.get_path("usjoin.csv"))
-        # pci = np.array([f.by_col[str(y)]
-        #                 for y in range(1995, 2010)]).transpose()
-        # rpci = pci / (pci.mean(axis = 0))
-
-        expected = np.array(
-          [[0.87654416, 0.863147, 0.85637567, 0.84811668, 0.8446154,
-            0.83271652,  0.83786314, 0.85012593, 0.85509656, 0.86416612,
-            0.87119375, 0.86302631,  0.86148267, 0.86252252, 0.86746356],
-           [0.9188951,  0.91757931, 0.92333258, 0.92517289, 0.92552388,
-            0.90746978,  0.89830489, 0.89431991, 0.88924794, 0.89815176,
-            0.91832091, 0.91706054,  0.90139505, 0.87897455, 0.86216858],
-           [0.82591007, 0.82548596, 0.81989793, 0.81503235, 0.81731522,
-            0.78964559,  0.80584442, 0.8084998,  0.82258551, 0.82668196,
-            0.82373724, 0.81814804,  0.83675961, 0.83574199, 0.84647177],
-           [1.09088176, 1.08537689, 1.08456418, 1.08415404, 1.09898841,
-            1.14506948,  1.12151133, 1.11160697, 1.10888621, 1.11399806,
-            1.12168029, 1.13164797,  1.12958508, 1.11371818, 1.09936775],
-           [1.10731446, 1.11373944, 1.13283638, 1.14472559, 1.15910025,
-            1.16898201,  1.17212488, 1.14752303, 1.11843284, 1.11024964,
-            1.11943471, 1.11736468,  1.10863242, 1.09642516, 1.07762337],
-           [1.42269757, 1.42118434, 1.44273502, 1.43577571, 1.44400684,
-            1.44184737,  1.44782832, 1.41978227, 1.39092208, 1.4059372,
-            1.40788646, 1.44052766,  1.45241216, 1.43306098, 1.4174431],
-           [1.13073885, 1.13110513, 1.11074708, 1.13364636, 1.13088149,
-            1.10888138,  1.11856629, 1.13062931, 1.11944984, 1.12446239,
-            1.11671008, 1.10880034,  1.08401709, 1.06959206, 1.07875225],
-           [1.04706124, 1.04516831, 1.04253372, 1.03239987, 1.02072545,
-            0.99854316,  0.9880258,  0.99669587, 0.99327676, 1.01400905,
-            1.03176742, 1.040511,  1.01749645, 0.9936394,  0.98279746],
-           [0.98996986, 1.00143564, 0.99491,  1.00188408, 1.00455845,
-            0.99127006,  0.97925917, 0.9683482,  0.95335147, 0.93694787,
-            0.94308213, 0.92232874,  0.91284091, 0.89689833, 0.88928858],
-           [0.87418391, 0.86416601, 0.84425695, 0.8404494,  0.83903044,
-            0.8578708,  0.86036185, 0.86107306, 0.8500772,  0.86981998,
-            0.86837929, 0.87204141,  0.86633032, 0.84946077, 0.83287146],
-           [1.14196118, 1.14660262, 1.14892712, 1.14909594, 1.14436624,
-            1.14450183,  1.12349752, 1.12596664, 1.12213996, 1.1119989,
-            1.10257792, 1.10491258,  1.11059842, 1.10509795, 1.10020097],
-           [0.97282463, 0.96700147, 0.96252588, 0.9653878,  0.96057687,
-            0.95831051,  0.94480909, 0.94804195, 0.95430286, 0.94103989,
-            0.92122519, 0.91010201,  0.89280392, 0.89298243, 0.89165385],
-           [0.94325468, 0.96436902, 0.96455242, 0.95243009, 0.94117647,
-            0.9480927,  0.93539182, 0.95388718, 0.94597005, 0.96918424,
-            0.94781281, 0.93466815,  0.94281559, 0.96520315, 0.96715441],
-           [0.97478408, 0.98169225, 0.98712809, 0.98474769, 0.98559897,
-            0.98687073,  0.99237486, 0.98209969, 0.9877653,  0.97399471,
-            0.96910087, 0.98416665,  0.98423613, 0.99823861, 0.99545704],
-           [0.85570269, 0.85575915, 0.85986132, 0.85693406, 0.8538012,
-            0.86191535,  0.84981451, 0.85472102, 0.84564835, 0.83998883,
-            0.83478547, 0.82803648,  0.8198736,  0.82265395, 0.8399404],
-           [0.87022047, 0.85996258, 0.85961813, 0.85689572, 0.83947136,
-            0.82785597,  0.86008789, 0.86776298, 0.86720209, 0.8676334,
-            0.89179317, 0.94202108,  0.9422231,  0.93902708, 0.94479184],
-           [0.90134907, 0.90407738, 0.90403991, 0.90201769, 0.90399238,
-            0.90906632,  0.92693339, 0.93695966, 0.94242697, 0.94338265,
-            0.91981796, 0.91108804,  0.90543476, 0.91737138, 0.94793657],
-           [1.1977611,  1.18222564, 1.18439158, 1.18267865, 1.19286723,
-            1.20172869,  1.21328691, 1.22624778, 1.22397075, 1.23857042,
-            1.24419893, 1.23929384,  1.23418676, 1.23626739, 1.26754398],
-           [1.24919678, 1.25754773, 1.26991161, 1.28020651, 1.30625667,
-            1.34790023,  1.34399863, 1.32575181, 1.30795492, 1.30544841,
-            1.30303302, 1.32107766,  1.32936244, 1.33001241, 1.33288462],
-           [1.06768004, 1.03799276, 1.03637303, 1.02768449, 1.03296093,
-            1.05059016,  1.03405057, 1.02747623, 1.03162734, 0.9961416,
-            0.97356208, 0.94241549,  0.92754547, 0.92549227, 0.92138102],
-           [1.09475614, 1.11526796, 1.11654299, 1.13103948, 1.13143264,
-            1.13889622,  1.12442212, 1.13367018, 1.13982256, 1.14029944,
-            1.11979401, 1.10905389,  1.10577769, 1.11166825, 1.09985155],
-           [0.76530058, 0.76612841, 0.76542451, 0.76722683, 0.76014284,
-            0.74480073,  0.76098396, 0.76156903, 0.76651952, 0.76533288,
-            0.78205934, 0.76842416,  0.77487118, 0.77768683, 0.78801192],
-           [0.98391336, 0.98075816, 0.98295341, 0.97386015, 0.96913803,
-            0.97370819,  0.96419154, 0.97209861, 0.97441313, 0.96356162,
-            0.94745352, 0.93965462,  0.93069645, 0.94020973, 0.94358232],
-           [0.83561828, 0.82298088, 0.81738502, 0.81748588, 0.80904801,
-            0.80071489,  0.83358256, 0.83451613, 0.85175032, 0.85954307,
-            0.86790024, 0.87170334,  0.87863799, 0.87497981, 0.87888675],
-           [0.98845573, 1.02092428, 0.99665283, 0.99141823, 0.99386619,
-            0.98733195,  0.99644997, 0.99669587, 1.02559097, 1.01116651,
-            0.99988024, 0.97906749,  0.99323123, 1.00204939, 0.99602148],
-           [1.14930913, 1.15241949, 1.14300962, 1.14265542, 1.13984683,
-            1.08312397,  1.05192626, 1.04230892, 1.05577278, 1.08569751,
-            1.12443486, 1.08891079,  1.08603695, 1.05997314, 1.02160943],
-           [1.11368269, 1.1057147,  1.11893431, 1.13778669, 1.1432272,
-            1.18257029,  1.16226243, 1.16009196, 1.14467789, 1.14820235,
-            1.12386598, 1.12680236,  1.12357937, 1.1159258,  1.12570828],
-           [1.30379431, 1.30752186, 1.31206366, 1.31532267, 1.30625667,
-            1.31210239,  1.29989156, 1.29203193, 1.27183516, 1.26830786,
-            1.2617743,  1.28656675,  1.29734097, 1.29390205, 1.29345446],
-           [0.83953719, 0.82701448, 0.82006005, 0.81188876, 0.80294864,
-            0.78772975,  0.82848011, 0.8259679,  0.82435705, 0.83108634,
-            0.84373784, 0.83891093,  0.84349247, 0.85637272, 0.86539395],
-           [1.23450087, 1.2426022,  1.23537935, 1.23581293, 1.24522626,
-            1.2256767,  1.21126648, 1.19377804, 1.18355337, 1.19674434,
-            1.21536573, 1.23653297,  1.27962009, 1.27968392, 1.25907738],
-           [0.9769662,  0.97400719, 0.98035944, 0.97581531, 0.95543282,
-            0.96480308,  0.94686376, 0.93679073, 0.92540049, 0.92988835,
-            0.93442917, 0.92100464,  0.91475304, 0.90249622, 0.9021363],
-           [0.84986886, 0.8986851,  0.84295997, 0.87280534, 0.85659368,
-            0.88937573,  0.894401, 0.90448993, 0.95495898, 0.92698333,
-            0.94745352, 0.92562488,  0.96635366, 1.02520312, 1.0394296],
-           [1.01922808, 1.00258203, 1.00974428, 1.00303417, 0.99765073,
-            1.00759019,  0.99192968, 0.99747298, 0.99550759, 0.97583768,
-            0.9610168,  0.94779638,  0.93759089, 0.93353431, 0.94121705],
-           [0.86367411, 0.85558932, 0.85544346, 0.85103025, 0.84336613,
-            0.83434854,  0.85813595, 0.84667961, 0.84374558, 0.85951183,
-            0.87194227, 0.89455097,  0.88283929, 0.90349491, 0.90600675],
-           [1.00947534, 1.00411055, 1.00698819, 0.99513687, 0.99291086,
-            1.00581626,  0.98850522, 0.99291168, 0.98983209, 0.97511924,
-            0.96134615, 0.96382634,  0.95011401, 0.9434686,  0.94637765],
-           [1.05712571, 1.05459419, 1.05753012, 1.04880786, 1.05103857,
-            1.04800023,  1.03024941, 1.04200483, 1.0402554,  1.03296979,
-            1.02191682, 1.02476275,  1.02347523, 1.02517684, 1.04359571],
-           [1.07084189, 1.06669497, 1.07937623, 1.07387988, 1.0794043,
-            1.0531801,  1.07452771, 1.09383478, 1.1052447,  1.10322136,
-            1.09167939, 1.08772756,  1.08859544, 1.09177338, 1.1096083],
-           [0.86719222, 0.86628896, 0.86675156, 0.86425632, 0.86511809,
-            0.86287327,  0.85169796, 0.85411285, 0.84886336, 0.84517414,
-            0.84843858, 0.84488343,  0.83374329, 0.82812044, 0.82878599],
-           [0.88389211, 0.92288667, 0.90282398, 0.91229186, 0.92023286,
-            0.92652175,  0.94278865, 0.93682452, 0.98655146, 0.992237,
-            0.9798497,  0.93869677,  0.96947771, 1.00362626, 0.98102351],
-           [0.97082064, 0.95320233, 0.94534081, 0.94215593, 0.93967,
-            0.93092109,  0.92662519, 0.93412152, 0.93501274, 0.92879506,
-            0.92110542, 0.91035556,  0.90430364, 0.89994694, 0.90073864],
-           [0.95861858, 0.95774543, 0.98254811, 0.98919472, 0.98684824,
-            0.98882205,  0.97662234, 0.95601578, 0.94905385, 0.94934888,
-            0.97152609, 0.97163004,  0.9700702,  0.97158948, 0.95884908],
-           [0.83980439, 0.84726737, 0.85747,  0.85467221, 0.8556751,
-            0.84818516,  0.85265681, 0.84502402, 0.82645665, 0.81743586,
-            0.83550406, 0.83338919,  0.83511679, 0.82136617, 0.80921874],
-           [0.95118156, 0.9466212,  0.94688098, 0.9508583,  0.9512441,
-            0.95440787,  0.96364363, 0.96804412, 0.97136214, 0.97583768,
-            0.95571724, 0.96895368,  0.97001634, 0.97082733, 0.98782366],
-           [1.08910044, 1.08248968, 1.08492895, 1.08656923, 1.09454249,
-            1.10558188,  1.1214086,  1.12292577, 1.13021031, 1.13342735,
-            1.14686068, 1.14502975,  1.14474747, 1.14084037, 1.16142926],
-           [1.06336033, 1.07365823, 1.08691496, 1.09764846, 1.11669863,
-            1.11856702,  1.09764283, 1.08815849, 1.08044313, 1.09278827,
-            1.07003204, 1.08398066,  1.09831768, 1.09298232, 1.09176125],
-           [0.79772065, 0.78829196, 0.78581151, 0.77615922, 0.77035744,
-            0.77751194,  0.79902974, 0.81437881, 0.80788828, 0.79603865,
-            0.78966436, 0.79949807,  0.80172182, 0.82168155, 0.85587911],
-           [1.0052447,  1.00007696, 1.00475899, 1.00613942, 1.00639561,
-            1.00162979,  0.99860739, 1.00814981, 1.00574316, 0.99030032,
-            0.97682565, 0.97292596,  0.96519561, 0.96173403, 0.95890284],
-           [0.95808419, 0.9382568,  0.9654441,  0.95561201, 0.96987289,
-            0.96608031,  0.99727185, 1.00781194, 1.03484236, 1.05333619,
-            1.0983263,  1.1704974,  1.17025154, 1.18730553, 1.14242645]])
-
-        self.assertTrue(np.allclose(result, expected))
-        self.assertTrue(type(result) == type(expected))
-        self.assertTrue(result.shape == expected.shape)

src/py/crankshaft/test/test_space_time_dynamics.py

@@ -105,6 +105,204 @@ class SpaceTimeTests(unittest.TestCase):
              ) in zip(result, expected):
             self.assertAlmostEqual(res_trend, exp_trend)
 
+    def test_get_time_data(self):
+        """Test get_time_data"""
+        data = [{'attr1': d['y1995'],
+                 'attr2': d['y1996'],
+                 'attr3': d['y1997'],
+                 'attr4': d['y1998'],
+                 'attr5': d['y1999'],
+                 'attr6': d['y2000'],
+                 'attr7': d['y2001'],
+                 'attr8': d['y2002'],
+                 'attr9': d['y2003'],
+                 'attr10': d['y2004'],
+                 'attr11': d['y2005'],
+                 'attr12': d['y2006'],
+                 'attr13': d['y2007'],
+                 'attr14': d['y2008'],
+                 'attr15': d['y2009']} for d in self.neighbors_data]
+
+        result = std.get_time_data(data, ['y1995', 'y1996', 'y1997', 'y1998',
+                                          'y1999', 'y2000', 'y2001', 'y2002',
+                                          'y2003', 'y2004', 'y2005', 'y2006',
+                                          'y2007', 'y2008', 'y2009'])
+
+        # expected was prepared from PySAL example:
+        # f = ps.open(ps.examples.get_path("usjoin.csv"))
+        # pci = np.array([f.by_col[str(y)]
+        #                 for y in range(1995, 2010)]).transpose()
+        # rpci = pci / (pci.mean(axis = 0))
+
+        expected = np.array(
+          [[0.87654416, 0.863147, 0.85637567, 0.84811668, 0.8446154,
+            0.83271652,  0.83786314, 0.85012593, 0.85509656, 0.86416612,
+            0.87119375, 0.86302631,  0.86148267, 0.86252252, 0.86746356],
+           [0.9188951,  0.91757931, 0.92333258, 0.92517289, 0.92552388,
+            0.90746978,  0.89830489, 0.89431991, 0.88924794, 0.89815176,
+            0.91832091, 0.91706054,  0.90139505, 0.87897455, 0.86216858],
+           [0.82591007, 0.82548596, 0.81989793, 0.81503235, 0.81731522,
+            0.78964559,  0.80584442, 0.8084998,  0.82258551, 0.82668196,
+            0.82373724, 0.81814804,  0.83675961, 0.83574199, 0.84647177],
+           [1.09088176, 1.08537689, 1.08456418, 1.08415404, 1.09898841,
+            1.14506948,  1.12151133, 1.11160697, 1.10888621, 1.11399806,
+            1.12168029, 1.13164797,  1.12958508, 1.11371818, 1.09936775],
+           [1.10731446, 1.11373944, 1.13283638, 1.14472559, 1.15910025,
+            1.16898201,  1.17212488, 1.14752303, 1.11843284, 1.11024964,
+            1.11943471, 1.11736468,  1.10863242, 1.09642516, 1.07762337],
+           [1.42269757, 1.42118434, 1.44273502, 1.43577571, 1.44400684,
+            1.44184737,  1.44782832, 1.41978227, 1.39092208, 1.4059372,
+            1.40788646, 1.44052766,  1.45241216, 1.43306098, 1.4174431],
+           [1.13073885, 1.13110513, 1.11074708, 1.13364636, 1.13088149,
+            1.10888138,  1.11856629, 1.13062931, 1.11944984, 1.12446239,
+            1.11671008, 1.10880034,  1.08401709, 1.06959206, 1.07875225],
+           [1.04706124, 1.04516831, 1.04253372, 1.03239987, 1.02072545,
+            0.99854316,  0.9880258,  0.99669587, 0.99327676, 1.01400905,
+            1.03176742, 1.040511,  1.01749645, 0.9936394,  0.98279746],
+           [0.98996986, 1.00143564, 0.99491,  1.00188408, 1.00455845,
+            0.99127006,  0.97925917, 0.9683482,  0.95335147, 0.93694787,
+            0.94308213, 0.92232874,  0.91284091, 0.89689833, 0.88928858],
+           [0.87418391, 0.86416601, 0.84425695, 0.8404494,  0.83903044,
+            0.8578708,  0.86036185, 0.86107306, 0.8500772,  0.86981998,
+            0.86837929, 0.87204141,  0.86633032, 0.84946077, 0.83287146],
+           [1.14196118, 1.14660262, 1.14892712, 1.14909594, 1.14436624,
+            1.14450183,  1.12349752, 1.12596664, 1.12213996, 1.1119989,
+            1.10257792, 1.10491258,  1.11059842, 1.10509795, 1.10020097],
+           [0.97282463, 0.96700147, 0.96252588, 0.9653878,  0.96057687,
+            0.95831051,  0.94480909, 0.94804195, 0.95430286, 0.94103989,
+            0.92122519, 0.91010201,  0.89280392, 0.89298243, 0.89165385],
+           [0.94325468, 0.96436902, 0.96455242, 0.95243009, 0.94117647,
+            0.9480927,  0.93539182, 0.95388718, 0.94597005, 0.96918424,
+            0.94781281, 0.93466815,  0.94281559, 0.96520315, 0.96715441],
+           [0.97478408, 0.98169225, 0.98712809, 0.98474769, 0.98559897,
+            0.98687073,  0.99237486, 0.98209969, 0.9877653,  0.97399471,
+            0.96910087, 0.98416665,  0.98423613, 0.99823861, 0.99545704],
+           [0.85570269, 0.85575915, 0.85986132, 0.85693406, 0.8538012,
+            0.86191535,  0.84981451, 0.85472102, 0.84564835, 0.83998883,
+            0.83478547, 0.82803648,  0.8198736,  0.82265395, 0.8399404],
+           [0.87022047, 0.85996258, 0.85961813, 0.85689572, 0.83947136,
+            0.82785597,  0.86008789, 0.86776298, 0.86720209, 0.8676334,
+            0.89179317, 0.94202108,  0.9422231,  0.93902708, 0.94479184],
+           [0.90134907, 0.90407738, 0.90403991, 0.90201769, 0.90399238,
+            0.90906632,  0.92693339, 0.93695966, 0.94242697, 0.94338265,
+            0.91981796, 0.91108804,  0.90543476, 0.91737138, 0.94793657],
+           [1.1977611,  1.18222564, 1.18439158, 1.18267865, 1.19286723,
+            1.20172869,  1.21328691, 1.22624778, 1.22397075, 1.23857042,
+            1.24419893, 1.23929384,  1.23418676, 1.23626739, 1.26754398],
+           [1.24919678, 1.25754773, 1.26991161, 1.28020651, 1.30625667,
+            1.34790023,  1.34399863, 1.32575181, 1.30795492, 1.30544841,
+            1.30303302, 1.32107766,  1.32936244, 1.33001241, 1.33288462],
+           [1.06768004, 1.03799276, 1.03637303, 1.02768449, 1.03296093,
+            1.05059016,  1.03405057, 1.02747623, 1.03162734, 0.9961416,
+            0.97356208, 0.94241549,  0.92754547, 0.92549227, 0.92138102],
+           [1.09475614, 1.11526796, 1.11654299, 1.13103948, 1.13143264,
+            1.13889622,  1.12442212, 1.13367018, 1.13982256, 1.14029944,
+            1.11979401, 1.10905389,  1.10577769, 1.11166825, 1.09985155],
+           [0.76530058, 0.76612841, 0.76542451, 0.76722683, 0.76014284,
+            0.74480073,  0.76098396, 0.76156903, 0.76651952, 0.76533288,
+            0.78205934, 0.76842416,  0.77487118, 0.77768683, 0.78801192],
+           [0.98391336, 0.98075816, 0.98295341, 0.97386015, 0.96913803,
+            0.97370819,  0.96419154, 0.97209861, 0.97441313, 0.96356162,
+            0.94745352, 0.93965462,  0.93069645, 0.94020973, 0.94358232],
+           [0.83561828, 0.82298088, 0.81738502, 0.81748588, 0.80904801,
+            0.80071489,  0.83358256, 0.83451613, 0.85175032, 0.85954307,
+            0.86790024, 0.87170334,  0.87863799, 0.87497981, 0.87888675],
+           [0.98845573, 1.02092428, 0.99665283, 0.99141823, 0.99386619,
+            0.98733195,  0.99644997, 0.99669587, 1.02559097, 1.01116651,
+            0.99988024, 0.97906749,  0.99323123, 1.00204939, 0.99602148],
+           [1.14930913, 1.15241949, 1.14300962, 1.14265542, 1.13984683,
+            1.08312397,  1.05192626, 1.04230892, 1.05577278, 1.08569751,
+            1.12443486, 1.08891079,  1.08603695, 1.05997314, 1.02160943],
+           [1.11368269, 1.1057147,  1.11893431, 1.13778669, 1.1432272,
+            1.18257029,  1.16226243, 1.16009196, 1.14467789, 1.14820235,
+            1.12386598, 1.12680236,  1.12357937, 1.1159258,  1.12570828],
+           [1.30379431, 1.30752186, 1.31206366, 1.31532267, 1.30625667,
+            1.31210239,  1.29989156, 1.29203193, 1.27183516, 1.26830786,
+            1.2617743,  1.28656675,  1.29734097, 1.29390205, 1.29345446],
+           [0.83953719, 0.82701448, 0.82006005, 0.81188876, 0.80294864,
+            0.78772975,  0.82848011, 0.8259679,  0.82435705, 0.83108634,
+            0.84373784, 0.83891093,  0.84349247, 0.85637272, 0.86539395],
+           [1.23450087, 1.2426022,  1.23537935, 1.23581293, 1.24522626,
+            1.2256767,  1.21126648, 1.19377804, 1.18355337, 1.19674434,
+            1.21536573, 1.23653297,  1.27962009, 1.27968392, 1.25907738],
+           [0.9769662,  0.97400719, 0.98035944, 0.97581531, 0.95543282,
+            0.96480308,  0.94686376, 0.93679073, 0.92540049, 0.92988835,
+            0.93442917, 0.92100464,  0.91475304, 0.90249622, 0.9021363],
+           [0.84986886, 0.8986851,  0.84295997, 0.87280534, 0.85659368,
+            0.88937573,  0.894401, 0.90448993, 0.95495898, 0.92698333,
+            0.94745352, 0.92562488,  0.96635366, 1.02520312, 1.0394296],
+           [1.01922808, 1.00258203, 1.00974428, 1.00303417, 0.99765073,
+            1.00759019,  0.99192968, 0.99747298, 0.99550759, 0.97583768,
+            0.9610168,  0.94779638,  0.93759089, 0.93353431, 0.94121705],
+           [0.86367411, 0.85558932, 0.85544346, 0.85103025, 0.84336613,
+            0.83434854,  0.85813595, 0.84667961, 0.84374558, 0.85951183,
+            0.87194227, 0.89455097,  0.88283929, 0.90349491, 0.90600675],
+           [1.00947534, 1.00411055, 1.00698819, 0.99513687, 0.99291086,
+            1.00581626,  0.98850522, 0.99291168, 0.98983209, 0.97511924,
+            0.96134615, 0.96382634,  0.95011401, 0.9434686,  0.94637765],
+           [1.05712571, 1.05459419, 1.05753012, 1.04880786, 1.05103857,
+            1.04800023,  1.03024941, 1.04200483, 1.0402554,  1.03296979,
+            1.02191682, 1.02476275,  1.02347523, 1.02517684, 1.04359571],
+           [1.07084189, 1.06669497, 1.07937623, 1.07387988, 1.0794043,
+            1.0531801,  1.07452771, 1.09383478, 1.1052447,  1.10322136,
+            1.09167939, 1.08772756,  1.08859544, 1.09177338, 1.1096083],
+           [0.86719222, 0.86628896, 0.86675156, 0.86425632, 0.86511809,
+            0.86287327,  0.85169796, 0.85411285, 0.84886336, 0.84517414,
+            0.84843858, 0.84488343,  0.83374329, 0.82812044, 0.82878599],
+           [0.88389211, 0.92288667, 0.90282398, 0.91229186, 0.92023286,
+            0.92652175,  0.94278865, 0.93682452, 0.98655146, 0.992237,
+            0.9798497,  0.93869677,  0.96947771, 1.00362626, 0.98102351],
+           [0.97082064, 0.95320233, 0.94534081, 0.94215593, 0.93967,
+            0.93092109,  0.92662519, 0.93412152, 0.93501274, 0.92879506,
+            0.92110542, 0.91035556,  0.90430364, 0.89994694, 0.90073864],
+           [0.95861858, 0.95774543, 0.98254811, 0.98919472, 0.98684824,
+            0.98882205,  0.97662234, 0.95601578, 0.94905385, 0.94934888,
+            0.97152609, 0.97163004,  0.9700702,  0.97158948, 0.95884908],
+           [0.83980439, 0.84726737, 0.85747,  0.85467221, 0.8556751,
+            0.84818516,  0.85265681, 0.84502402, 0.82645665, 0.81743586,
+            0.83550406, 0.83338919,  0.83511679, 0.82136617, 0.80921874],
+           [0.95118156, 0.9466212,  0.94688098, 0.9508583,  0.9512441,
+            0.95440787,  0.96364363, 0.96804412, 0.97136214, 0.97583768,
+            0.95571724, 0.96895368,  0.97001634, 0.97082733, 0.98782366],
+           [1.08910044, 1.08248968, 1.08492895, 1.08656923, 1.09454249,
+            1.10558188,  1.1214086,  1.12292577, 1.13021031, 1.13342735,
+            1.14686068, 1.14502975,  1.14474747, 1.14084037, 1.16142926],
+           [1.06336033, 1.07365823, 1.08691496, 1.09764846, 1.11669863,
+            1.11856702,  1.09764283, 1.08815849, 1.08044313, 1.09278827,
+            1.07003204, 1.08398066,  1.09831768, 1.09298232, 1.09176125],
+           [0.79772065, 0.78829196, 0.78581151, 0.77615922, 0.77035744,
+            0.77751194,  0.79902974, 0.81437881, 0.80788828, 0.79603865,
+            0.78966436, 0.79949807,  0.80172182, 0.82168155, 0.85587911],
+           [1.0052447,  1.00007696, 1.00475899, 1.00613942, 1.00639561,
+            1.00162979,  0.99860739, 1.00814981, 1.00574316, 0.99030032,
+            0.97682565, 0.97292596,  0.96519561, 0.96173403, 0.95890284],
+           [0.95808419, 0.9382568,  0.9654441,  0.95561201, 0.96987289,
+            0.96608031,  0.99727185, 1.00781194, 1.03484236, 1.05333619,
+            1.0983263,  1.1704974,  1.17025154, 1.18730553, 1.14242645]])
+
+        self.assertTrue(np.allclose(result, expected))
+        self.assertTrue(type(result) == type(expected))
+        self.assertTrue(result.shape == expected.shape)
+
+    def test_rebin_data(self):
+        """Test rebin_data"""
+        # sample in double the time (even case since 10 % 2 = 0):
+        #   (0+1)/2, (2+3)/2, (4+5)/2, (6+7)/2, (8+9)/2
+        # = 0.5,     2.5,     4.5,     6.5,     8.5
+        ans_even = np.array([(i + 0.5) * np.ones(10, dtype=float)
+                             for i in range(0, 10, 2)]).T
+
+        self.assertTrue(
+          np.array_equal(std.rebin_data(self.time_data, 2), ans_even))
+
+        # sample in triple the time (uneven since 10 % 3 = 1):
+        #   (0+1+2)/3, (3+4+5)/3, (6+7+8)/3, (9)/1
+        # = 1,         4,         7,         9
+        ans_odd = np.array([i * np.ones(10, dtype=float)
+                            for i in (1, 4, 7, 9)]).T
+        self.assertTrue(
+          np.array_equal(std.rebin_data(self.time_data, 3), ans_odd))
+
     def test_get_prob_dist(self):
         """Test get_prob_dist"""
         lag_indices = np.array([1, 2, 3, 4])