add new version of the model. NEW : loss is based on heversine distance

combination_embeddings.py

@@ -25,6 +25,8 @@ from lib.geo import Grid,zero_one_encoding, get_adjacency_rels, get_geonames_inc
 from lib.ngram_index import NgramIndex
 from lib.utils import ConfigurationReader
 from lib.metrics import lat_accuracy,lon_accuracy
+from lib.geo import haversine_tf,accuracy_k,haversine_tf_1circle
+
 
 # Logging
 from tqdm import tqdm
@@ -300,11 +302,13 @@ 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 !")
 
@@ -354,6 +358,8 @@ x2 = Dense(500,activation="relu")(x2)
 output_lon = Dense(1,activation="sigmoid",name="Output_LON")(x1)
 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={"Output_LON":lon_accuracy(),"Output_LAT":lat_accuracy()})

combination_embeddingsv3.py

 # Base module 
+import re
 import os
+import json
 
 # Structure
 import pandas as pd
 import numpy as np
+import geopandas as gpd
 
 # DEEPL module
-from keras.layers import Dense, Input, Embedding,concatenate,Bidirectional,LSTM,Dropout,GRU
+from keras.layers import Dense, Input, Embedding,concatenate,Bidirectional,LSTM, Dropout
 from keras.models import Model
+from keras import backend as K
 from keras.callbacks import ModelCheckpoint
-from tensorflow.keras.layers import Lambda
-import keras.backend as K 
-import tensorflow as tf 
-from lib.custom_layer import *
+
+import tensorflow as tf
+
+# Geometry
+from shapely.geometry import Point
 
 # Custom module
+from helpers import read_geonames
+from lib.geo import Grid,zero_one_encoding, get_adjacency_rels, get_geonames_inclusion_rel,get_bounds
 from lib.ngram_index import NgramIndex
-from lib.utils import ConfigurationReader, MetaDataSerializer,LabelEncoder
+from lib.utils import ConfigurationReader
 from lib.metrics import lat_accuracy,lon_accuracy
-from lib.data_generator import DataGenerator,CoOccurrences,load_embedding,Inclusion,Adjacency
 from lib.geo import haversine_tf,accuracy_k,haversine_tf_1circle
 
+
 # Logging
+from tqdm import tqdm
 import logging
+from helpers import parse_title_wiki,EpochTimer
 
 logging.getLogger('gensim').setLevel(logging.WARNING)
 
-from helpers import EpochTimer
+def get_new_ids(cooc_data,id_first_value):
+    """
+    Return new ids from cooccurrence data
+    
+    Parameters
+    ----------
+    cooc_data : pd.DataFrame
+        cooccurrence da
+    id_first_value : int
+        id beginning value
+    
+    Returns
+    -------
+    dict
+        new ids for each toponyms 
+    """
+    topo_id = {}
+    id_ = id_first_value
+    for title in cooc_data.title.values:
+        if not title in topo_id:
+            id_+=1
+            topo_id[id_]=title
+    for interlinks in cooc_data.interlinks.values:
+        for interlink in interlinks.split("|"):
+            if not interlink in topo_id:
+                id_+=1
+                topo_id[id_]=interlink
+    return topo_id
 
 # LOGGING CONF
 logging.basicConfig(
@@ -35,41 +71,40 @@ logging.basicConfig(
     level=logging.INFO  
     )
 
-args = ConfigurationReader("./parser_config/toponym_combination_embedding_v2.json")\
-    .parse_args()#("-i --inclusion-fn ../data/geonamesData/hierarchy.txt ../data/geonamesData/allCountries.txt ../data/embeddings/word2vec4gram/4gramWiki+geonames_index.json ../data/embeddings/word2vec4gram/embedding4gramWiki+Geonames.bin".split())
-
-#.parse_args("-w  --wikipedia-cooc-fn  subsetCoocALLv2.csv ../data/geonamesData/allCountries.txt ../data/embeddings/word2vec4gram/4gramWiki+geonames_index.json ../data/embeddings/word2vec4gram/embedding4gramWiki+Geonames.bin".split())
+args = ConfigurationReader("./parser_config/toponym_combination_embedding.json")\
+    .parse_args()#("-w --wikipedia-cooc-fn subsetCoocALL.csv ../data/geonamesData/allCountries.txt ../data/geonamesData/hierarchy.txt".split())
 
 #
 #################################################
 ############# MODEL TRAINING PARAMETER ##########
 #################################################
+MODEL_NAME = "Bi-LSTM_NGRAM"
 NGRAM_SIZE = args.ngram_size
-ACCURACY_TOLERANCE = args.k_value
+ACCURACY_TOLERANCE = args.tolerance_value
 EPOCHS = args.epochs
-ADJACENCY_SAMPLING = args.adjacency_sample
-COOC_SAMPLING = args.cooc_sample
-WORDVEC_ITER = 50
-EMBEDDING_DIM = args.dimension
-BATCH_SIZE = args.batch_size
+ITER_ADJACENCY = args.adjacency_iteration
+COOC_SAMPLING_NUMBER = args.cooc_sample_size
+WORDVEC_ITER = args.ngram_word2vec_iter
+EMBEDDING_DIM = 256
 #################################################
 ########## FILENAME VARIABLE ####################
 #################################################
-# check for output dir
-if not os.path.exists("outputs/"):
-    os.makedirs("outputs/")
-
 GEONAME_FN = args.geoname_input
 DATASET_NAME = args.geoname_input.split("/")[-1]
-GEONAMES_HIERARCHY_FN = args.inclusion_fn
-ADJACENCY_REL_FILENAME = args.adjacency_fn
-COOC_FN = args.wikipedia_cooc_fn
+GEONAMES_HIERARCHY_FN = args.geoname_hierachy_input
+REGION_SUFFIX_FN = "" if args.admin_code_1 == "None" else "_" + args.admin_code_1
+ADJACENCY_REL_FILENAME = "{0}_{1}{2}adjacency.json".format(
+        GEONAME_FN,
+        ITER_ADJACENCY,
+        REGION_SUFFIX_FN)
 
-PREFIX_OUTPUT_FN = "{0}_{1}_{2}_{3}".format(
+COOC_FN = args.wikipedia_cooc_fn
+PREFIX_OUTPUT_FN = "{0}_{1}_{2}_{3}_{4}".format(
     GEONAME_FN.split("/")[-1],
     EPOCHS,
     NGRAM_SIZE,
-    ACCURACY_TOLERANCE)
+    ACCURACY_TOLERANCE,
+    REGION_SUFFIX_FN)
 
 REL_CODE=""
 if args.adjacency:
@@ -86,12 +121,14 @@ MODEL_OUTPUT_FN = "outputs/{0}.h5".format(PREFIX_OUTPUT_FN)
 INDEX_FN = "outputs/{0}_index".format(PREFIX_OUTPUT_FN)
 HISTORY_FN = "outputs/{0}.csv".format(PREFIX_OUTPUT_FN)
 
+from lib.utils import MetaDataSerializer
 
 meta_data = MetaDataSerializer(
+    MODEL_NAME,
     DATASET_NAME,
     REL_CODE,
-    COOC_SAMPLING,
-    ADJACENCY_SAMPLING,
+    COOC_SAMPLING_NUMBER,
+    ITER_ADJACENCY,
     NGRAM_SIZE,
     ACCURACY_TOLERANCE,
     EPOCHS,
@@ -103,92 +140,238 @@ meta_data = MetaDataSerializer(
 )
 meta_data.save("outputs/{0}.json".format(PREFIX_OUTPUT_FN))
 
+#############################################################################################
+################################# LOAD DATA #################################################
+#############################################################################################
 
-### PUT DATASRC + GENERATOR
+# LOAD  Geonames DATA
+logging.info("Load Geonames data...")
+geoname_data = read_geonames(GEONAME_FN).fillna("")
 
-index = NgramIndex.load(args.ngram_index_fn)
+train_indices = set(pd.read_csv(GEONAME_FN+"_train.csv").geonameid.values)
+test_indices = set(pd.read_csv(GEONAME_FN+"_test.csv").geonameid.values)
 
-train_src = []
-test_src = []
+logging.info("Geonames data loaded!")
 
-class_encoder = LabelEncoder()
+# SELECT ENTRY with class == to A and P (Areas and Populated Places)
+filtered = geoname_data[geoname_data.feature_class.isin("A P".split())].copy() # Only take area and populated places
+#CLEAR RAM
+del geoname_data
 
-if args.wikipedia_cooc:
-    train_src.append(CoOccurrences(COOC_FN + "_train.csv",class_encoder,sampling=4,use_healpix=False))
-    test_src.append(CoOccurrences(COOC_FN + "_test.csv",class_encoder,sampling=4,use_healpix=False))
 
+# IF REGION
+if args.admin_code_1 != "None":
+    filtered = filtered[filtered.admin1_code == args.admin_code_1].copy()
+
+# GET BOUNDS AND REDUCE DATA AVAILABLE FIELDS
+filtered = filtered["geonameid name longitude latitude".split()] # KEEP ONLY ID LABEL AND COORD
+
+
+
+#############################################################################################
+################################# RETRIEVE RELATIONSHIPS ####################################
+#############################################################################################
+
+
+# INITIALIZE RELATION STORE
+rel_store = []
+
+# Retrieve adjacency relationships
 if args.adjacency:
-    a_train = Adjacency(ADJACENCY_REL_FILENAME + "_train.csv",GEONAME_FN,sampling=ADJACENCY_SAMPLING,gzip=False)
-    a_test = Adjacency(ADJACENCY_REL_FILENAME + "_test.csv",GEONAME_FN,sampling=ADJACENCY_SAMPLING,gzip=False)
-    train_src.append(a_train)
-    test_src.append(a_test)
+    logging.info("Retrieve adjacency relationships ! ")
+
+    if not os.path.exists(ADJACENCY_REL_FILENAME):
+        bounds = get_bounds(filtered) # Required to get adjacency relationships
+        rel_store.extend(get_adjacency_rels(filtered,bounds,[360,180],ITER_ADJACENCY))
+        json.dump(rel_store,open(ADJACENCY_REL_FILENAME,'w'))
+    else:
+        logging.info("Open and load data from previous computation!")
+        rel_store=json.load(open(ADJACENCY_REL_FILENAME))
 
+    logging.info("{0} adjacency relationships retrieved ! ".format(len(rel_store)))
+
+# Retrieve inclusion relationships
 if args.inclusion:
-    i_train = Inclusion(GEONAME_FN,GEONAMES_HIERARCHY_FN+"_train.csv")
-    i_test = Inclusion(GEONAME_FN,GEONAMES_HIERARCHY_FN+"_test.csv")
-    train_src.append(i_train)
-    test_src.append(i_test)
-#Adjacency
+    logging.info("Retrieve inclusion relationships ! ")
+
+    cpt_rel = len(rel_store)
+    rel_store.extend(get_geonames_inclusion_rel(filtered,GEONAMES_HIERARCHY_FN))
 
-print("Number of classes:",class_encoder.get_num_classes())
+    logging.info("{0} inclusion relationships retrieved ! ".format(len(rel_store)-cpt_rel))
 
-d_train = DataGenerator(train_src,index,class_encoder,batch_size=BATCH_SIZE) 
-d_test = DataGenerator(test_src,index,class_encoder,batch_size=BATCH_SIZE) 
 
-num_words = len(index.index_ngram)  
+
+if args.wikipedia_cooc:
+    logging.info("Load Wikipedia Cooccurrence data and merge with geonames")
+    
+    cooc_data = pd.read_csv(COOC_FN,sep="\t")
+    cooc_data["title"] = cooc_data.title.apply(parse_title_wiki)
+    cooc_data["interlinks"] = cooc_data.interlinks.apply(parse_title_wiki)
+    id_wikipediatitle = get_new_ids(cooc_data,filtered.geonameid.max())
+    wikipediatitle_id = {v:k for k,v in id_wikipediatitle.items()}
+    title_coord = {row.title: (row.longitude,row.latitude) for _,row in tqdm(cooc_data.iterrows(),total=len(cooc_data))}
+    cooc_data["geonameid"] = cooc_data.title.apply(lambda x: wikipediatitle_id[x])
+    filtered = pd.concat((filtered,cooc_data["geonameid title longitude latitude".split()].rename(columns={"title":"name"}).copy()))
+    train_cooc_indices,test_cooc_indices = pd.read_csv(COOC_FN+"_train.csv",sep="\t"), pd.read_csv(COOC_FN+"_test.csv",sep="\t")
+    if not "title" in train_cooc_indices:
+        train_cooc_indices,test_cooc_indices = pd.read_csv(COOC_FN+"_train.csv"), pd.read_csv(COOC_FN+"_test.csv")
+    train_indices = train_indices.union(set(train_cooc_indices.title.apply(lambda x: wikipediatitle_id[parse_title_wiki(x)]).values))
+    test_indices = test_indices.union(set(test_cooc_indices.title.apply(lambda x: wikipediatitle_id[parse_title_wiki(x)]).values))
+
+    logging.info("Merged with Geonames data !")
+
+    # EXTRACT rel
+    logging.info("Extracting cooccurrence relationships")
+    cpt=0
+    for ix, row in tqdm(cooc_data.iterrows(),total=len(cooc_data),desc="Extracting Wikipedia Cooccurrence"):
+        for inter in np.random.choice(row.interlinks.split("|"),COOC_SAMPLING_NUMBER):
+            cpt+=1
+            rel_store.extend([[row.geonameid,wikipediatitle_id[inter]]])
+    logging.info("Extract {0} cooccurrence relationships !".format(cpt))
+
+
+# STORE ID to name
+geoname2name = dict(filtered["geonameid name".split()].values)
+
+# ENCODING NAME USING N-GRAM SPLITTING
+logging.info("Encoding toponyms to ngram...")
+index = NgramIndex(NGRAM_SIZE)
+
+ # Identify all ngram available
+filtered.name.apply(lambda x : index.split_and_add(x))
+if args.wikipedia_cooc:[index.split_and_add(k) for k in wikipediatitle_id]
+
+geoname2encodedname = {row.geonameid : index.encode(row.name) for row in filtered.itertuples()} #init a dict with the 'geonameid' --> 'encoded toponym' association
+
+if args.wikipedia_cooc:
+    geoname2encodedname.update({v:index.encode(k) for k,v in wikipediatitle_id.items()})
+
+# SAVE THE INDEX TO REUSE THE MODEL
+index.save(INDEX_FN)
+
+logging.info("Done !")
+
+
+#############################################################################################
+################################# ENCODE COORDINATES ########################################
+#############################################################################################
+
+
+
+# Encode each geonames entry coordinates
+geoname_vec = {row.geonameid : zero_one_encoding(row.longitude,row.latitude) for row in filtered.itertuples()}
+# CLEAR RAM
+del filtered
+
+
+EMBEDDING_DIM = 256
+num_words = len(index.index_ngram) # necessary for the embedding matrix 
+
+logging.info("Preparing Input and Output data...")
+
+
+#############################################################################################
+################################# BUILD TRAIN/TEST DATASETS #################################
+#############################################################################################
+
+X_1_train,X_2_train,y_lat_train,y_lon_train=[],[],[],[]
+X_1_test,X_2_test,y_lat_test,y_lon_test=[],[],[],[]
+y_train,y_test = [],[]
+
+for couple in rel_store:
+    geonameId_1,geonameId_2 = couple[0],couple[1]
+    if not geonameId_1 in geoname2encodedname:
+        continue
+    top1,top2 = geoname2encodedname[geonameId_1],geoname2encodedname[geonameId_2]
+    if geonameId_1 in train_indices: #and geonameId_2 in train_indices:
+        
+        X_1_train.append(top1)
+        X_2_train.append(top2)
+
+        y_train.append([geoname_vec[geonameId_1][0],geoname_vec[geonameId_1][1]])
+        #y_lon_train.append(geoname_vec[geonameId_1][0])
+        #y_lat_train.append(geoname_vec[geonameId_1][1])
+    
+    else:
+        X_1_test.append(top1)
+        X_2_test.append(top2)
+
+        y_test.append([geoname_vec[geonameId_1][0],geoname_vec[geonameId_1][1]])
+        #y_lon_test.append(geoname_vec[geonameId_1][0])
+        #y_lat_test.append(geoname_vec[geonameId_1][1])
+
+# NUMPYZE inputs and output lists
+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 !")
+
+
+# check for output dir
+if not os.path.exists("outputs/"):
+    os.makedirs("outputs/")
 
 #############################################################################################
 ################################# NGRAM EMBEDDINGS ##########################################
 #############################################################################################
 
-embedding_weights = load_embedding(args.embedding_fn) 
-EMBEDDING_DIM = len(embedding_weights[0])
+
+logging.info("Generating N-GRAM Embedding...")
+embedding_weights = index.get_embedding_layer(geoname2encodedname.values(),dim= EMBEDDING_DIM,iter=WORDVEC_ITER)
+logging.info("Embedding generated !")
 
 #############################################################################################
 ################################# MODEL DEFINITION ##########################################
 #############################################################################################
 
-from keras import regularizers
-####
 
 input_1 = Input(shape=(index.max_len,))
 input_2 = Input(shape=(index.max_len,))
 
-embedding_layer = Embedding(num_words, EMBEDDING_DIM,input_length=index.max_len,trainable=False)#, trainable=True)
+embedding_layer = Embedding(num_words, EMBEDDING_DIM,input_length=index.max_len,weights=[embedding_weights],trainable=False)#, trainable=True)
 
 x1 = embedding_layer(input_1)
 x2 = embedding_layer(input_2)
 
 # Each LSTM learn on a permutation of the input toponyms
-biLSTM = Bidirectional(GRU(128,activation="pentanh", recurrent_activation="pentanh"))
-x1 = biLSTM(x1)
-x2 = biLSTM(x2)
+x1 = Bidirectional(LSTM(98))(x1)
+x2 = Bidirectional(LSTM(98))(x2)
 
 x = concatenate([x1,x2])#,x3])
 
 x1 = Dense(500,activation="relu")(x)
-x1 = Dropout(0.3)(x1)
+# x1 = Dropout(0.3)(x1)
 x1 = Dense(500,activation="relu")(x1)
-x1 = Dropout(0.3)(x1)
+# x1 = Dropout(0.3)(x1)
 
 x2 = Dense(500,activation="relu")(x)
-x2 = Dropout(0.3)(x2)
+# x2 = Dropout(0.3)(x2)
 x2 = Dense(500,activation="relu")(x2)
-x2 = Dropout(0.3)(x2)
-
-#aux_layer = Dense(class_encoder.get_num_classes(),activation="softmax",name="aux_layer")(D)
+# x2 = Dropout(0.3)(x2)
 
-output_lon = Dense(1,activation="sigmoid")(x1)
-output_lat = Dense(1,activation="sigmoid")(x2)
+output_lon = Dense(1,activation="sigmoid",name="Output_LON")(x1)
+output_lat = Dense(1,activation="sigmoid",name="Output_LAT")(x2)
 
 output_coord = concatenate([output_lon,output_lat],name="output_coord")
 
-#####
 model = Model(inputs = [input_1,input_2], outputs = output_coord)#input_3
 
 model.compile(loss={"output_coord":haversine_tf_1circle}, optimizer='adam',metrics={"output_coord":accuracy_k(ACCURACY_TOLERANCE)})
 
-model.summary()
+# 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={"Output_LON":lon_accuracy(),"Output_LAT":lat_accuracy()})
+
+
 #############################################################################################
 ################################# TRAINING LAUNCH ###########################################
 #############################################################################################
@@ -199,10 +382,11 @@ checkpoint = ModelCheckpoint(MODEL_OUTPUT_FN + ".part", monitor='loss', verbose=
 epoch_timer = EpochTimer("outputs/"+PREFIX_OUTPUT_FN+"_epoch_timer_output.csv")
 
 
-history = model.fit_generator(generator=d_train,
-    validation_data=d_test,
-    verbose=True,
+history = model.fit(x=[X_1_train,X_2_train],
+    y=y_train,#[y_lon_train,y_lat_train],
+    verbose=True, batch_size=100,
     epochs=EPOCHS,
+    validation_data=([X_1_test,X_2_test],y_test),#[y_lon_test,y_lat_test]),
     callbacks=[checkpoint,epoch_timer])
 
 
@@ -213,4 +397,5 @@ model.save(MODEL_OUTPUT_FN)
 
 # Erase Model Checkpoint file
 if os.path.exists(MODEL_OUTPUT_FN + ".part"):
-    os.remove(MODEL_OUTPUT_FN + ".part")
+    import shutil
\ No newline at end of file
+    shutil.rmtree(MODEL_OUTPUT_FN + ".part")
\ No newline at end of file

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": 0.002 },
+        { "short": "-t", "long": "--tolerance-value", "type": "float", "default": 100 },
         { "short": "-e", "long": "--epochs", "type": "int", "default": 100 },
         { "short": "-d", "long": "--dimension", "type": "int", "default": 256 },
         {  "long": "--admin_code_1", "default": "None" }