DEBUG Acc@k

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,

requirements.txt

-pyroutelib3
+#pyroutelib3
 node2vec
-osrm
+#osrm
 geopandas
 pandas
 numpy
@@ -18,3 +18,4 @@ sqlitedict
 nltk
 folium
 flask
+numba