DEBUG

combination_embeddings.py

@@ -302,13 +302,11 @@ X_1_train = np.array(X_1_train)
 X_2_train = np.array(X_2_train)
 y_lat_train = np.array(y_lat_train)
 y_lon_train = np.array(y_lon_train)
-y_train = np.array(y_train)
 
 X_1_test = np.array(X_1_test)
 X_2_test = np.array(X_2_test)
 y_lat_test = np.array(y_lat_test)
 y_lon_test = np.array(y_lon_test)
-y_test = np.array(y_test)
 
 logging.info("Data prepared !")
 

combination_embeddingsv3.py

@@ -71,7 +71,7 @@ logging.basicConfig(
     level=logging.INFO  
     )
 
-args = ConfigurationReader("./parser_config/toponym_combination_embedding.json")\
+args = ConfigurationReader("./parser_config/toponym_combination_embedding_v2.json")\
     .parse_args()#("-w --wikipedia-cooc-fn subsetCoocALL.csv ../data/geonamesData/allCountries.txt ../data/geonamesData/hierarchy.txt".split())
 
 #

parser_config/toponym_combination_embedding.json

@@ -12,7 +12,7 @@
         {"long": "--adjacency-iteration", "type":"int","default":1},
         { "short": "-n", "long": "--ngram-size", "type": "int", "default": 2 },
         { "long": "--ngram-word2vec-iter", "type": "int", "default": 50 },
-        { "short": "-t", "long": "--tolerance-value", "type": "float", "default": 100 },
+        { "short": "-t", "long": "--tolerance-value", "type": "float", "default": 0.002 },
         { "short": "-e", "long": "--epochs", "type": "int", "default": 100 },
         { "short": "-d", "long": "--dimension", "type": "int", "default": 256 },
         {  "long": "--admin_code_1", "default": "None" }

parser_config/toponym_combination_embedding_v2.json

@@ -2,21 +2,19 @@
     "description": "Toponym Combination",
     "args": [
         { "short": "geoname_input", "help": "Filepath of the Geonames file you want to use." },
-        { "short": "ngram_index_fn", "help": "Filepath of the NgramIndex file you want to use." },
-        { "short": "embedding_fn", "help": "Filepath of the Embedding file you want to use." },
-        { "short": "-n", "long": "--ngram-size", "type": "int", "default": 4 },
-        { "short": "-d", "long": "--dimension", "type": "int", "default": 100 },
+        { "short": "geoname_hierachy_input", "help": "Filepath of the Geonames file you want to use." },
         { "short": "-v", "long": "--verbose", "action": "store_true" },
         { "short": "-i", "long": "--inclusion", "action": "store_true" },
         { "short": "-a", "long": "--adjacency", "action": "store_true" },
         { "short": "-w", "long": "--wikipedia-cooc", "action": "store_true" },
-        { "long": "--inclusion-fn","help":"Cooccurrence data filename"},
         { "long": "--wikipedia-cooc-fn","help":"Cooccurrence data filename"},
-        { "long": "--adjacency-fn","help":"Adjacency data filename"},
-        { "long": "--cooc-sample", "type": "int", "default": 3 },
-        {"long": "--adjacency-sample", "type":"int","default":1},
+        { "long": "--cooc-sample-size", "type": "int", "default": 1 },
+        {"long": "--adjacency-iteration", "type":"int","default":1},
+        { "short": "-n", "long": "--ngram-size", "type": "int", "default": 2 },
+        { "long": "--ngram-word2vec-iter", "type": "int", "default": 50 },
+        { "short": "-t", "long": "--tolerance-value", "type": "float", "default": 100 },
         { "short": "-e", "long": "--epochs", "type": "int", "default": 100 },
-        { "short": "-b", "long": "--batch-size", "type": "int", "default": 100 },
-        { "short": "-k", "long": "--k-value", "type": "float", "default": 100 ,"help":"Used for the accuracy@k metrics. Given in kilometers"}    
+        { "short": "-d", "long": "--dimension", "type": "int", "default": 256 },
+        {  "long": "--admin_code_1", "default": "None" }
     ]
 }
\ No newline at end of file