SY - inference module with examples

brails/imputers/knn_imputer/knn_imputer.py

@@ -71,33 +71,54 @@ class KnnImputer(Imputation):
     Methods:
 
 
-
-
-
     """
 
-    def __init__(self):
-        pass
-
-    def impute(
-        self,
-        input_inventory: AssetInventory,
-        n_possible_worlds=1,
-        create_correlation=True,
-        exclude_features=[],
-        seed=1,
-        batch_size=50,
-        k_nn=5,
-    ) -> AssetInventory:
+    def __init__(self,
+                input_inventory: AssetInventory,
+                n_possible_worlds=1,
+                create_correlation=True,
+                exclude_features=[],
+                seed=1,
+                batch_size=50,
+                k_nn=5,
+                nbldg_per_cluster=500
+    ):
+        self.input_inventory = input_inventory
         self.n_pw = n_possible_worlds
-        self.batch_size = batch_size
+        self.create_correlation = create_correlation
+        self.exclude_features = exclude_features
         self.seed = seed
-        self.k_nn = k_nn  # knn
-        if create_correlation:
+        self.batch_size = batch_size
+        self.k_nn = k_nn
+        self.nbldg_per_cluster = nbldg_per_cluster
+
+    # def impute(
+    #     self,
+    #     input_inventory: AssetInventory,
+    #     n_possible_worlds=1,
+    #     create_correlation=True,
+    #     exclude_features=[],
+    #     seed=1,
+    #     batch_size=50,
+    #     k_nn=5,
+    #     nbldg_per_cluster=500
+    # ) -> AssetInventory:
+
+    def impute(self)-> AssetInventory:
+
+        #self.n_pw = n_possible_worlds
+        #self.batch_size = batch_size
+        #self.seed = seed
+        #self.k_nn = k_nn  # knn
+
+        if self.create_correlation:
             self.gen_method = "sequential"
         else:
             self.gen_method = "non-sequential"
 
+        exclude_features = self.exclude_features
+        nbldg_per_cluster = self.nbldg_per_cluster
+        input_inventory = self.input_inventory
         #
         # set seed
         #
@@ -141,7 +162,7 @@ def impute(
         bldg_properties_df = bldg_properties_df.drop(columns=column_entirely_missing)
         mask = mask.drop(columns=column_entirely_missing)
 
-        if len(column_entirely_missing) > 1:
+        if len(column_entirely_missing) >= 1:
             print(
                 "Features with no reference data cannot be imputed. Removing them from the imputation target: "
                 + ", ".join(list(column_entirely_missing))
@@ -175,7 +196,7 @@ def impute(
         cluster_ids, n_cluster = self.clustering(
             bldg_properties_encoded,
             bldg_geometries_df,
-            nbldg_per_cluster=500,
+            nbldg_per_cluster=nbldg_per_cluster,
             seed=self.seed,
         )
 
@@ -347,9 +368,10 @@ def category_in_df_to_indices(self, bldg_properties_df, mask):
             idxs = np.array(mask[column] == False)  # removing nans  # noqa: E712
 
             # if not is_numeric_dtype(values):
+
             if math.isnan(sum(pd.to_numeric(values[idxs], errors="coerce"))):
                 is_category[column] = True
-            elif len(np.unique(values)) < 20:
+            elif len(np.unique(values[~np.isnan(values.astype(float))])) < 20:
                 is_category[column] = True
             else:
                 is_category[column] = False
@@ -515,7 +537,16 @@ def sequential_imputer(
                 # sample indices
                 #
 
+                distances[distances==0] = np.min(distances[distances!=0])/100 # if dist is zero
+
+                ndup = np.sum(distances==0)
+                if ndup>0:
+                    print(f'Warning: Found {ndup} duplicated assets that has distance 0.')
+
+
                 invdistance = 1 / distances
+
+
                 row_sums = invdistance.sum(axis=1)
                 weights = invdistance / row_sums[:, np.newaxis]
 
@@ -536,9 +567,16 @@ def sequential_imputer(
                     # global_nb = cluster_idx[missing_idx[nb]]
                     bldg_idx = bldg_inde_subset[missing_idx[nb]]
 
-                    surrounding_building_sample = np.random.choice(
-                        building_ids[nb, :], size=1, replace=True, p=weights[nb, :]
-                    )
+                    try:
+                        surrounding_building_sample = np.random.choice(
+                            building_ids[nb, :], size=1, replace=True, p=weights[nb, :]
+                        )
+                    except Exception as e:
+                        print(weights[nb, :])
+                        print(row_sums[nb, np.newaxis])
+                        print(invdistance[nb, :])
+                        exit(-1)
+
                     closet_building = building_ids[nb, np.argmin(weights[nb, :])]
 
                     imputed_index_sample = mytrainY[surrounding_building_sample]

brails/inferers/__init__.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2024 The Regents of the University of California
+#
+# This file is part of BRAILS++.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# 1. Redistributions of source code must retain the above copyright notice,
+# this list of conditions and the following disclaimer.
+#
+# 2. Redistributions in binary form must reproduce the above copyright notice,
+# this list of conditions and the following disclaimer in the documentation
+# and/or other materials provided with the distribution.
+#
+# 3. Neither the name of the copyright holder nor the names of its contributors
+# may be used to endorse or promote products derived from this software without
+# specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+#
+# You should have received a copy of the BSD 3-Clause License along with
+# BRAILS. If not, see <http://www.opensource.org/licenses/>.

brails/inferers/hazus_inferer/__init__.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2024 The Regents of the University of California
+#
+# This file is part of BRAILS++.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# 1. Redistributions of source code must retain the above copyright notice,
+# this list of conditions and the following disclaimer.
+#
+# 2. Redistributions in binary form must reproduce the above copyright notice,
+# this list of conditions and the following disclaimer in the documentation
+# and/or other materials provided with the distribution.
+#
+# 3. Neither the name of the copyright holder nor the names of its contributors
+# may be used to endorse or promote products derived from this software without
+# specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+#
+# You should have received a copy of the BSD 3-Clause License along with
+# BRAILS. If not, see <http://www.opensource.org/licenses/>.