Merging recomm_sys

.devcontainer/devcontainer.json

@@ -1,7 +1,7 @@
 {
-  "name": "TM Graph Devcontainer",
+  "name": "TM Graph Recomm",
   "dockerComposeFile": "docker-compose.yml",
-  "service": "tm-graph-development",
+  "service": "tm-graph-recomm",
   "workspaceFolder": "/app",
   "forwardPorts": [],
   "postCreateCommand": "echo 'Devcontainer is ready'",

.devcontainer/docker-compose.yml

@@ -1,5 +1,5 @@
 services:
-  tm-graph-development:
+  tm-graph-recomm:
     build:
       context: ../
       dockerfile: .devcontainer/Dockerfile
@@ -9,4 +9,5 @@ services:
           devices:
             - driver: nvidia
               capabilities: [gpu]
-              count: 1 # Assign number of GPUs or use 'all' to assign all available GPUs
+              # count: 1 # Assign number of GPUs or use 'all' to assign all available GPUs
+              device_ids: ["6"]

.gitignore

@@ -1,3 +1,7 @@
+build/
+GraphTsetlinMachine.egg-info/
+/dist/
+
 .envrc
 
 # Byte-compiled / optimized / DLL files

examples/MNISTConvolutionDemo.py

@@ -61,18 +61,13 @@ def default_args(**kwargs):
     hypervector_bits=args.hypervector_bits,
     double_hashing = args.double_hashing
 )
-
 for graph_id in range(X_train.shape[0]):
     graphs_train.set_number_of_graph_nodes(graph_id, number_of_nodes)
-
 graphs_train.prepare_node_configuration()
-
 for graph_id in range(X_train.shape[0]):
     for node_id in range(graphs_train.number_of_graph_nodes[graph_id]):
         graphs_train.add_graph_node(graph_id, node_id, 0)
-
 graphs_train.prepare_edge_configuration()
-
 for graph_id in range(X_train.shape[0]):
     if graph_id % 1000 == 0:
         print(graph_id, X_train.shape[0])
@@ -88,23 +83,17 @@ def default_args(**kwargs):
 
                 graphs_train.add_graph_node_property(graph_id, node_id, "C:%d" % (q))
                 graphs_train.add_graph_node_property(graph_id, node_id, "R:%d" % (r))
-
 graphs_train.encode()
-
 print("Training data produced")
 
 graphs_test = Graphs(X_test.shape[0], init_with=graphs_train)
 for graph_id in range(X_test.shape[0]):
     graphs_test.set_number_of_graph_nodes(graph_id, number_of_nodes)
-
 graphs_test.prepare_node_configuration()
-
 for graph_id in range(X_test.shape[0]):
     for node_id in range(graphs_test.number_of_graph_nodes[graph_id]):
         graphs_test.add_graph_node(graph_id, node_id, 0)
-
 graphs_test.prepare_edge_configuration()
-
 for graph_id in range(X_test.shape[0]):
     if graph_id % 1000 == 0:
         print(graph_id, X_test.shape[0])
@@ -120,9 +109,7 @@ def default_args(**kwargs):
 
                 graphs_test.add_graph_node_property(graph_id, node_id, "C:%d" % (q))
                 graphs_test.add_graph_node_property(graph_id, node_id, "R:%d" % (r))
-
 graphs_test.encode()
-
 print("Testing data produced")
 
 tm = MultiClassGraphTsetlinMachine(

examples/MNISTVanillaDemo.py

@@ -4,7 +4,6 @@
 from GraphTsetlinMachine.tm import MultiClassGraphTsetlinMachine
 from time import time
 import argparse
-from skimage.util import view_as_windows
 from keras.datasets import mnist
 from numba import jit
 
@@ -53,51 +52,36 @@ def default_args(**kwargs):
     hypervector_bits=args.hypervector_bits,
     double_hashing = args.double_hashing
 )
-
 for graph_id in range(X_train.shape[0]):
     graphs_train.set_number_of_graph_nodes(graph_id, number_of_nodes)
-
 graphs_train.prepare_node_configuration()
-
 for graph_id in range(X_train.shape[0]):
     number_of_outgoing_edges = 0
     graphs_train.add_graph_node(graph_id, 'Image Node', number_of_outgoing_edges)
-
 graphs_train.prepare_edge_configuration()
-
 for graph_id in range(X_train.shape[0]):
-    if graph_id % 1000 == 0:
-        print(graph_id, X_train.shape[0])
-
+    # if graph_id % 1000 == 0:
+        # print(graph_id, X_train.shape[0])
     for k in X_train[graph_id].nonzero()[0]:
         graphs_train.add_graph_node_property(graph_id, 'Image Node', "W%d,%d" % (k // 28, k % 28))
-
 graphs_train.encode()
-
 print("Training data produced")
 
 graphs_test = Graphs(X_test.shape[0], init_with=graphs_train)
-
 for graph_id in range(X_test.shape[0]):
     graphs_test.set_number_of_graph_nodes(graph_id, number_of_nodes)
-
 graphs_test.prepare_node_configuration()
-
 for graph_id in range(X_test.shape[0]):
     number_of_outgoing_edges = 0
     graphs_test.add_graph_node(graph_id, 'Image Node', number_of_outgoing_edges)
-
 graphs_test.prepare_edge_configuration()
-
 for graph_id in range(X_test.shape[0]):
     if graph_id % 1000 == 0:
         print(graph_id, X_test.shape[0])
 
     for k in X_test[graph_id].nonzero()[0]:
         graphs_test.add_graph_node_property(graph_id, 'Image Node', "W%d,%d" % (k // 28, k % 28))
-
 graphs_test.encode()
-
 print("Testing data produced")
 
 tm = MultiClassGraphTsetlinMachine(
@@ -125,16 +109,16 @@ def default_args(**kwargs):
 
     print("%d %.2f %.2f %.2f %.2f" % (i, result_train, result_test, stop_training-start_training, stop_testing-start_testing))
 
-weights = tm.get_state()[1].reshape(2, -1)
-for i in range(tm.number_of_clauses):
-        print("Clause #%d Weights:(%d %d)" % (i, weights[0,i], weights[1,i]), end=' ')
-        l = []
-        for k in range(args.hypervector_size * 2):
-            if tm.ta_action(0, i, k):
-                if k < args.hypervector_size:
-                    l.append("x%d" % (k))
-                else:
-                    l.append("NOT x%d" % (k - args.hypervector_size))
-        print(" AND ".join(l))
-
-print(graphs_train.hypervectors)
+# weights = tm.get_state()[1].reshape(2, -1)
+# for i in range(tm.number_of_clauses):
+#         print("Clause #%d Weights:(%d %d)" % (i, weights[0,i], weights[1,i]), end=' ')
+#         l = []
+#         for k in range(args.hypervector_size * 2):
+#             if tm.ta_action(0, i, k):
+#                 if k < args.hypervector_size:
+#                     l.append("x%d" % (k))
+#                 else:
+#                     l.append("NOT x%d" % (k - args.hypervector_size))
+#         print(" AND ".join(l))
+
+# print(graphs_train.hypervectors)

examples/NoisyXORDemo.py

@@ -34,31 +34,24 @@ def default_args(**kwargs):
 print("Creating training data")
 
 # Create train data
-
 graphs_train = Graphs(
     args.number_of_examples,
     symbols=['A', 'B'],
     hypervector_size=args.hypervector_size,
     hypervector_bits=args.hypervector_bits,
 )
-
 for graph_id in range(args.number_of_examples):
     graphs_train.set_number_of_graph_nodes(graph_id, 2)
-
 graphs_train.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     number_of_outgoing_edges = 1
     graphs_train.add_graph_node(graph_id, 'Node 1', number_of_outgoing_edges)
     graphs_train.add_graph_node(graph_id, 'Node 2', number_of_outgoing_edges)
-
-graphs_train.prepare_edge_configuration()
-
+graphs_train.prepar_eedge_configuration()
 for graph_id in range(args.number_of_examples):
     edge_type = "Plain"
     graphs_train.add_graph_node_edge(graph_id, 'Node 1', 'Node 2', edge_type)
     graphs_train.add_graph_node_edge(graph_id, 'Node 2', 'Node 1', edge_type)
-
 Y_train = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     x1 = random.choice(['A', 'B'])
@@ -74,32 +67,23 @@ def default_args(**kwargs):
 
     if np.random.rand() <= args.noise:
         Y_train[graph_id] = 1 - Y_train[graph_id]
-
 graphs_train.encode()
 
-# Create test data
-
+# Create test data 
 print("Creating testing data")
-
 graphs_test = Graphs(args.number_of_examples, init_with=graphs_train)
-
 for graph_id in range(args.number_of_examples):
     graphs_test.set_number_of_graph_nodes(graph_id, 2)
-
 graphs_test.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     number_of_outgoing_edges = 1
     graphs_test.add_graph_node(graph_id, 'Node 1', number_of_outgoing_edges)
     graphs_test.add_graph_node(graph_id, 'Node 2', number_of_outgoing_edges)
-
 graphs_test.prepare_edge_configuration()
-
 for graph_id in range(args.number_of_examples):
     edge_type = "Plain"
     graphs_test.add_graph_node_edge(graph_id, 'Node 1', 'Node 2', edge_type)
     graphs_test.add_graph_node_edge(graph_id, 'Node 2', 'Node 1', edge_type)
-
 Y_test = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     x1 = random.choice(['A', 'B'])
@@ -112,7 +96,6 @@ def default_args(**kwargs):
         Y_test[graph_id] = 0
     else:
         Y_test[graph_id] = 1
-
 graphs_test.encode()
 
 tm = MultiClassGraphTsetlinMachine(

examples/NoisyXORMNISTDemo.py

@@ -54,24 +54,18 @@ def default_args(**kwargs):
     hypervector_size=args.hypervector_size,
     hypervector_bits=args.hypervector_bits,
 )
-
 for graph_id in range(args.number_of_examples):
     graphs_train.set_number_of_graph_nodes(graph_id, 2)
-
 graphs_train.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     number_of_outgoing_edges = 1
     graphs_train.add_graph_node(graph_id, 'Node 1', number_of_outgoing_edges)
     graphs_train.add_graph_node(graph_id, 'Node 2', number_of_outgoing_edges)
-
 graphs_train.prepare_edge_configuration()
-
 for graph_id in range(args.number_of_examples):
     edge_type = "Plain"
     graphs_train.add_graph_node_edge(graph_id, 'Node 1', 'Node 2', edge_type)
     graphs_train.add_graph_node_edge(graph_id, 'Node 2', 'Node 1', edge_type)
-
 Y_train = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     x1 = random.choice([0, 1])
@@ -91,32 +85,23 @@ def default_args(**kwargs):
 
     if np.random.rand() <= args.noise:
         Y_train[graph_id] = 1 - Y_train[graph_id]
-
 graphs_train.encode()
 
 # Create test data
-
 print("Creating testing data")
-
 graphs_test = Graphs(args.number_of_examples, init_with=graphs_train)
-
 for graph_id in range(args.number_of_examples):
     graphs_test.set_number_of_graph_nodes(graph_id, 2)
-
 graphs_test.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     number_of_outgoing_edges = 1
     graphs_test.add_graph_node(graph_id, 'Node 1', number_of_outgoing_edges)
     graphs_test.add_graph_node(graph_id, 'Node 2', number_of_outgoing_edges)
-
 graphs_test.prepare_edge_configuration()
-
 for graph_id in range(args.number_of_examples):
     edge_type = "Plain"
     graphs_test.add_graph_node_edge(graph_id, 'Node 1', 'Node 2', edge_type)
     graphs_test.add_graph_node_edge(graph_id, 'Node 2', 'Node 1', edge_type)
-
 Y_test = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     x1 = random.choice([0, 1])
@@ -133,7 +118,6 @@ def default_args(**kwargs):
         Y_test[graph_id] = 0
     else:
         Y_test[graph_id] = 1
-
 graphs_test.encode()
 
 tm = MultiClassGraphTsetlinMachine(

examples/SequenceClassificationDemo.py

@@ -35,27 +35,21 @@ def default_args(**kwargs):
 print("Creating training data")
 
 # Create train data
-
 graphs_train = Graphs(
     args.number_of_examples,
     symbols=['A'],
     hypervector_size=args.hypervector_size,
     hypervector_bits=args.hypervector_bits,
     double_hashing = args.double_hashing
 )
-
 for graph_id in range(args.number_of_examples):
     graphs_train.set_number_of_graph_nodes(graph_id, np.random.randint(args.number_of_classes, args.max_sequence_length+1))
-
 graphs_train.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     for node_id in range(graphs_train.number_of_graph_nodes[graph_id]):
         number_of_edges = 2 if node_id > 0 and node_id < graphs_train.number_of_graph_nodes[graph_id]-1 else 1
         graphs_train.add_graph_node(graph_id, node_id, number_of_edges)
-
 graphs_train.prepare_edge_configuration()
-
 Y_train = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     for node_id in range(graphs_train.number_of_graph_nodes[graph_id]):
@@ -76,26 +70,19 @@ def default_args(**kwargs):
 
     if np.random.rand() <= args.noise:
         Y_train[graph_id] = np.random.choice(np.setdiff1d(np.arange(args.number_of_classes), [Y_train[graph_id]]))
-
 graphs_train.encode()
 
 # Create test data
-
 print("Creating testing data")
-
 graphs_test = Graphs(args.number_of_examples, init_with=graphs_train)
 for graph_id in range(args.number_of_examples):
     graphs_test.set_number_of_graph_nodes(graph_id, np.random.randint(args.number_of_classes, args.max_sequence_length+1))
-
 graphs_test.prepare_node_configuration()
-
 for graph_id in range(args.number_of_examples):
     for node_id in range(graphs_test.number_of_graph_nodes[graph_id]):
         number_of_edges = 2 if node_id > 0 and node_id < graphs_test.number_of_graph_nodes[graph_id]-1 else 1
         graphs_test.add_graph_node(graph_id, node_id, number_of_edges)
-
 graphs_test.prepare_edge_configuration()
-
 Y_test = np.empty(args.number_of_examples, dtype=np.uint32)
 for graph_id in range(args.number_of_examples):
     for node_id in range(graphs_test.number_of_graph_nodes[graph_id]):
@@ -113,7 +100,6 @@ def default_args(**kwargs):
     node_id = np.random.randint(Y_test[graph_id], graphs_test.number_of_graph_nodes[graph_id])
     for node_pos in range(Y_test[graph_id] + 1):
         graphs_test.add_graph_node_property(graph_id, node_id - node_pos, 'A')
-
 graphs_test.encode()
 
 tm = MultiClassGraphTsetlinMachine(

examples/recomm_system/README.md

@@ -0,0 +1,2 @@
+cd examples/recomm_system/
+bash main.sh