diff --git a/.gitattributes b/.gitattributes
old mode 100644
new mode 100755
diff --git a/.gitignore b/.gitignore
old mode 100644
new mode 100755
diff --git a/README.md b/README.md
old mode 100644
new mode 100755
diff --git a/combination_embeddings.py b/combination_embeddings.py
old mode 100644
new mode 100755
index d2d13a5979294b0e5a0ef063839be6a584baeb2c..ab4a251956e774cd6f7d7a53ad24268711661af0
--- a/combination_embeddings.py
+++ b/combination_embeddings.py
@@ -73,21 +73,41 @@ def get_new_ids(cooc_data,id_first_value):
topo_id[id_]=interlink
return topo_id
-def accuracy_at_k(y_true, y_pred):
- """
- Metrics use to measure the accuracy of the coordinate prediction. But in comparison to the normal accuracy metrics, we add a tolerance threshold due to the (quasi) impossible
- task for neural network to obtain the exact coordinate.
-
- Parameters
- ----------
- y_true : tf.Tensor
- truth data
- y_pred : tf.Tensor
- predicted output
- """
- diff = tf.abs(y_true - y_pred)
- fit = tf.where(tf.less(diff,ACCURACY_TOLERANCE))
- return K.size(fit[:,0])/K.size(y_pred),K.size(fit[:,1])/K.size(y_pred)
+def lat_accuracy(LAT_TOL =1/180.):
+ def accuracy_at_k_lat(y_true, y_pred):
+ """
+ Metrics use to measure the accuracy of the coordinate prediction. But in comparison to the normal accuracy metrics, we add a tolerance threshold due to the (quasi) impossible
+ task for neural network to obtain the exact coordinate.
+
+ Parameters
+ ----------
+ y_true : tf.Tensor
+ truth data
+ y_pred : tf.Tensor
+ predicted output
+ """
+ diff = tf.abs(y_true - y_pred)
+ fit = tf.dtypes.cast(tf.less(diff,LAT_TOL),tf.int64)
+ return tf.reduce_sum(fit)/tf.size(y_pred,out_type=tf.dtypes.int64)
+ return accuracy_at_k_lat
+
+def lon_accuracy(LON_TOL=1/360.):
+ def accuracy_at_k_lon(y_true, y_pred):
+ """
+ Metrics use to measure the accuracy of the coordinate prediction. But in comparison to the normal accuracy metrics, we add a tolerance threshold due to the (quasi) impossible
+ task for neural network to obtain the exact coordinate.
+
+ Parameters
+ ----------
+ y_true : tf.Tensor
+ truth data
+ y_pred : tf.Tensor
+ predicted output
+ """
+ diff = tf.abs(y_true - y_pred)
+ fit = tf.dtypes.cast(tf.less(diff,LON_TOL),tf.int64)
+ return tf.reduce_sum(fit)/tf.size(y_pred,out_type=tf.dtypes.int64)
+ return accuracy_at_k_lon
# LOGGING CONF
logging.basicConfig(
@@ -98,7 +118,7 @@ logging.basicConfig(
chrono = Chronometer()
args = ConfigurationReader("./parser_config/toponym_combination_embedding.json")\
- .parse_args()#("-n 4 -t 0.002 -e 20 -a -w -i data/geonamesData/FR.txt data/geonamesData/hierarchy.txt".split())
+ .parse_args("-n 4 -t 0.002 -e 20 -i data/geonamesData/FR.txt data/geonamesData/hierarchy.txt".split())
# Initialisee CONSTANTS
GEONAME_FN = args.geoname_input
@@ -108,6 +128,7 @@ ACCURACY_TOLERANCE = args.tolerance_value
EPOCHS = args.epochs
ITER_ADJACENCY = args.adjacency_iteration
COOC_SAMPLING_NUMBER = 3
+WORDVEC_ITER = 50
# check for output dir
if not os.path.exists("outputs/"):
@@ -296,7 +317,7 @@ index.save("outputs/"+name+"_index")
# NGRAM EMBDEDDING
logging.info("Generating N-GRAM Embedding...")
-embedding_weights = index.get_embedding_layer(geoname2encodedname.values(),dim= embedding_dim,iter=50)
+embedding_weights = index.get_embedding_layer(geoname2encodedname.values(),dim= embedding_dim,iter=WORDVEC_ITER)
logging.info("Embedding generated !")
# DEEP MODEL
@@ -326,7 +347,7 @@ output_lat = Dense(1,activation="sigmoid",name="Output_LAT")(x2)
model = Model(inputs = [input_1,input_2], outputs = [output_lon,output_lat])#input_3
-model.compile(loss=['mean_squared_error','mean_squared_error'], optimizer='adam',metrics=[accuracy_at_k])
+model.compile(loss=['mean_squared_error','mean_squared_error'], optimizer='adam',metrics={"Output_LON":lon_accuracy(),"Output_LAT":lat_accuracy()})
history = model.fit(x=[X_1_train,X_2_train],
y=[y_lon_train,y_lat_train],
verbose=True, batch_size=100,
diff --git a/documentation/imgs/first_approach.png b/documentation/imgs/first_approach.png
old mode 100644
new mode 100755
index 297c1a5025d993acfae6e501d88acac24dfc7e59..4b83d1184fc92e154510c934ecea41b4e80455ce
Binary files a/documentation/imgs/first_approach.png and b/documentation/imgs/first_approach.png differ
diff --git a/documentation/imgs/second_approach.png b/documentation/imgs/second_approach.png
old mode 100644
new mode 100755
index e5e693fbaf11113de2673b366d4bf603047239c2..bdff5964c3796980e518eb0f9aa724bd836e0ca6
Binary files a/documentation/imgs/second_approach.png and b/documentation/imgs/second_approach.png differ
diff --git a/documentation/imgs/third_approach.png b/documentation/imgs/third_approach.png
old mode 100644
new mode 100755
index d96596ad9ee35b8ada81b0a68535e593ed8e1a0e..ea8e6aaa02e19084a61e346ebacff25139cc63cb
Binary files a/documentation/imgs/third_approach.png and b/documentation/imgs/third_approach.png differ
diff --git a/embeddings_lat_lon_type.py b/embeddings_lat_lon_type.py
old mode 100644
new mode 100755
diff --git a/extractDataFromWikidata.py b/extractDataFromWikidata.py
old mode 100644
new mode 100755
diff --git a/extractLearningDataset.py b/extractLearningDataset.py
old mode 100644
new mode 100755
diff --git a/geonames_embedding.py b/geonames_embedding.py
old mode 100644
new mode 100755
diff --git a/helpers.py b/helpers.py
old mode 100644
new mode 100755
diff --git a/models.py b/models.py
old mode 100644
new mode 100755
diff --git a/parser_config/embeddings_lat_lon.json b/parser_config/embeddings_lat_lon.json
old mode 100644
new mode 100755
diff --git a/parser_config/toponym_combination_embedding.json b/parser_config/toponym_combination_embedding.json
old mode 100644
new mode 100755
diff --git a/predict_toponym_coordinates.py b/predict_toponym_coordinates.py
old mode 100644
new mode 100755
diff --git a/requirements.txt b/requirements.txt
old mode 100644
new mode 100755
index 798a0142faf7dba8870eb329f0d2d6731c39784a..4eb9e43ed0fb7aefddd5bdfe87ddf049a489394c
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,6 @@
-pyroutelib3
+#pyroutelib3
node2vec
-osrm
+#osrm
geopandas
pandas
numpy
@@ -18,3 +18,4 @@ sqlitedict
nltk
folium
flask
+numba
diff --git a/scripts/classificationEmbeddings.py b/scripts/classificationEmbeddings.py
old mode 100644
new mode 100755
diff --git a/scripts/evalgeonamesembeddings.py b/scripts/evalgeonamesembeddings.py
old mode 100644
new mode 100755
diff --git a/scripts/evaluation-dbpedia-types.py b/scripts/evaluation-dbpedia-types.py
old mode 100644
new mode 100755
diff --git a/scripts/evaluation-geonames.py b/scripts/evaluation-geonames.py
old mode 100644
new mode 100755
diff --git a/scripts/extractWikidataClasseName.py b/scripts/extractWikidataClasseName.py
old mode 100644
new mode 100755
diff --git a/scripts/filterDataWithtopNclasse.py b/scripts/filterDataWithtopNclasse.py
old mode 100644
new mode 100755
diff --git a/scripts/getEmbeddingGeonamesPlacenames.py b/scripts/getEmbeddingGeonamesPlacenames.py
old mode 100644
new mode 100755
diff --git a/scripts/getWikidataTypesNames.py b/scripts/getWikidataTypesNames.py
old mode 100644
new mode 100755
diff --git a/templates/cover.css b/templates/cover.css
new file mode 100755
index 0000000000000000000000000000000000000000..7c6d33cdd58d82b8936fd0209c691184883d5e67
--- /dev/null
+++ b/templates/cover.css
@@ -0,0 +1,106 @@
+/*
+ * Globals
+ */
+
+/* Links */
+a,
+a:focus,
+a:hover {
+ color: #fff;
+}
+
+/* Custom default button */
+.btn-secondary,
+.btn-secondary:hover,
+.btn-secondary:focus {
+ color: #333;
+ text-shadow: none; /* Prevent inheritance from `body` */
+ background-color: #fff;
+ border: .05rem solid #fff;
+}
+
+
+/*
+ * Base structure
+ */
+
+html,
+body {
+ height: 100%;
+ background-color: #333;
+}
+
+body {
+ display: -ms-flexbox;
+ display: flex;
+ color: #fff;
+ text-shadow: 0 .05rem .1rem rgba(0, 0, 0, .5);
+ box-shadow: inset 0 0 5rem rgba(0, 0, 0, .5);
+}
+
+.cover-container {
+ max-width: 42em;
+}
+
+
+/*
+ * Header
+ */
+.masthead {
+ margin-bottom: 2rem;
+}
+
+.masthead-brand {
+ margin-bottom: 0;
+}
+
+.nav-masthead .nav-link {
+ padding: .25rem 0;
+ font-weight: 700;
+ color: rgba(255, 255, 255, .5);
+ background-color: transparent;
+ border-bottom: .25rem solid transparent;
+}
+
+.nav-masthead .nav-link:hover,
+.nav-masthead .nav-link:focus {
+ border-bottom-color: rgba(255, 255, 255, .25);
+}
+
+.nav-masthead .nav-link + .nav-link {
+ margin-left: 1rem;
+}
+
+.nav-masthead .active {
+ color: #fff;
+ border-bottom-color: #fff;
+}
+
+@media (min-width: 48em) {
+ .masthead-brand {
+ float: left;
+ }
+ .nav-masthead {
+ float: right;
+ }
+}
+
+
+/*
+ * Cover
+ */
+.cover {
+ padding: 0 1.5rem;
+}
+.cover .btn-lg {
+ padding: .75rem 1.25rem;
+ font-weight: 700;
+}
+
+
+/*
+ * Footer
+ */
+.mastfoot {
+ color: rgba(255, 255, 255, .5);
+}
diff --git a/templates/skeleton.html b/templates/skeleton.html
old mode 100644
new mode 100755
diff --git a/train_test_split_cooccurrence_data.py b/train_test_split_cooccurrence_data.py
old mode 100644
new mode 100755
diff --git a/train_test_split_geonames.py b/train_test_split_geonames.py
old mode 100644
new mode 100755
diff --git a/utils.py b/utils.py
old mode 100644
new mode 100755
index bd767edd0f9024730e9b4dc322929b590d26e5d2..db250b77474f8e1a135a373b76461dad485f88c1
--- a/utils.py
+++ b/utils.py
@@ -524,7 +524,6 @@ class Grid(object):
for c1 in range(len(self.inter_cells)):
if self.inter_cells[c1].contains(a[1],a[2]):
self.inter_cells[c1].add_object(*a)
- break
def get_adjacent_relationships(self,random_iteration=10):
"""