From b272413d47b83f1f71ec2b08918d1556edfd6916 Mon Sep 17 00:00:00 2001
From: Jacques Fize <jacques.fize@insa-lyon.fr>
Date: Wed, 9 Sep 2020 15:51:37 +0200
Subject: [PATCH] DEBUG
---
combination_embeddings.py | 2 --
combination_embeddingsv3.py | 2 +-
.../toponym_combination_embedding.json | 2 +-
.../toponym_combination_embedding_v2.json | 18 ++++++++----------
4 files changed, 10 insertions(+), 14 deletions(-)
diff --git a/combination_embeddings.py b/combination_embeddings.py
index 5255cdb..dd66e51 100644
--- a/combination_embeddings.py
+++ b/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 !")
diff --git a/combination_embeddingsv3.py b/combination_embeddingsv3.py
index ac5ceb6..86e4fcb 100644
--- a/combination_embeddingsv3.py
+++ b/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())
#
diff --git a/parser_config/toponym_combination_embedding.json b/parser_config/toponym_combination_embedding.json
index 9163e70..a7dc96c 100644
--- a/parser_config/toponym_combination_embedding.json
+++ b/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" }
diff --git a/parser_config/toponym_combination_embedding_v2.json b/parser_config/toponym_combination_embedding_v2.json
index f0fb1fd..9163e70 100644
--- a/parser_config/toponym_combination_embedding_v2.json
+++ b/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
--
GitLab