add new_version of train script

combination_embeddingsv3.py

+# Base module 
+import os
+
+# Structure
+import pandas as pd
+import numpy as np
+
+# DEEPL module
+from keras.layers import Dense, Input, Embedding,concatenate,Bidirectional,LSTM,Dropout,GRU
+from keras.models import Model
+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 *
+
+# Custom module
+from lib.ngram_index import NgramIndex
+from lib.utils import ConfigurationReader, MetaDataSerializer,LabelEncoder
+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
+import logging
+
+logging.getLogger('gensim').setLevel(logging.WARNING)
+
+from helpers import EpochTimer
+
+# LOGGING CONF
+logging.basicConfig(
+    format='[%(asctime)s][%(levelname)s] %(message)s ', 
+    datefmt='%m/%d/%Y %I:%M:%S %p',
+    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())
+
+#
+#################################################
+############# MODEL TRAINING PARAMETER ##########
+#################################################
+NGRAM_SIZE = args.ngram_size
+ACCURACY_TOLERANCE = args.k_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
+#################################################
+########## 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
+
+PREFIX_OUTPUT_FN = "{0}_{1}_{2}_{3}".format(
+    GEONAME_FN.split("/")[-1],
+    EPOCHS,
+    NGRAM_SIZE,
+    ACCURACY_TOLERANCE)
+
+REL_CODE=""
+if args.adjacency:
+    PREFIX_OUTPUT_FN += "_A"
+    REL_CODE+= "A"
+if args.inclusion:
+    PREFIX_OUTPUT_FN += "_I"
+    REL_CODE+= "I"
+if args.wikipedia_cooc:
+    PREFIX_OUTPUT_FN += "_C"
+    REL_CODE+= "C"
+
+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)
+
+
+meta_data = MetaDataSerializer(
+    DATASET_NAME,
+    REL_CODE,
+    COOC_SAMPLING,
+    ADJACENCY_SAMPLING,
+    NGRAM_SIZE,
+    ACCURACY_TOLERANCE,
+    EPOCHS,
+    EMBEDDING_DIM,
+    WORDVEC_ITER,
+    INDEX_FN,
+    MODEL_OUTPUT_FN,
+    HISTORY_FN
+)
+meta_data.save("outputs/{0}.json".format(PREFIX_OUTPUT_FN))
+
+
+### PUT DATASRC + GENERATOR
+
+index = NgramIndex.load(args.ngram_index_fn)
+
+train_src = []
+test_src = []
+
+class_encoder = LabelEncoder()
+
+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 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)
+
+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
+
+print("Number of classes:",class_encoder.get_num_classes())
+
+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)  
+
+#############################################################################################
+################################# NGRAM EMBEDDINGS ##########################################
+#############################################################################################
+
+embedding_weights = load_embedding(args.embedding_fn) 
+EMBEDDING_DIM = len(embedding_weights[0])
+
+#############################################################################################
+################################# 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)
+
+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)
+
+x = concatenate([x1,x2])#,x3])
+
+x1 = Dense(500,activation="relu")(x)
+x1 = Dropout(0.3)(x1)
+x1 = Dense(500,activation="relu")(x1)
+x1 = Dropout(0.3)(x1)
+
+x2 = Dense(500,activation="relu")(x)
+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)
+
+output_lon = Dense(1,activation="sigmoid")(x1)
+output_lat = Dense(1,activation="sigmoid")(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()
+#############################################################################################
+################################# TRAINING LAUNCH ###########################################
+#############################################################################################
+
+checkpoint = ModelCheckpoint(MODEL_OUTPUT_FN + ".part", monitor='loss', verbose=1,
+    save_best_only=True, mode='auto', period=1)
+
+epoch_timer = EpochTimer("outputs/"+PREFIX_OUTPUT_FN+"_epoch_timer_output.csv")
+
+
+history = model.fit_generator(generator=d_train,
+    validation_data=d_test,
+    verbose=True,
+    epochs=EPOCHS,
+    callbacks=[checkpoint,epoch_timer])
+
+
+hist_df = pd.DataFrame(history.history)
+hist_df.to_csv(HISTORY_FN)
+
+model.save(MODEL_OUTPUT_FN)
+
+# Erase Model Checkpoint file
+if os.path.exists(MODEL_OUTPUT_FN + ".part"):
+    os.remove(MODEL_OUTPUT_FN + ".part")
\ No newline at end of file

train_test_split_cooccurrence_data.py

@@ -14,7 +14,7 @@ logging.basicConfig(
 from sklearn.model_selection import train_test_split
 from shapely.geometry import Point
 
-from lib.geo import Grid,latlon2healpix
+from lib.geo import latlon2healpix
 
 from tqdm import tqdm 
 
@@ -27,33 +27,10 @@ args = parser.parse_args()#("data/wikipedia/cooccurrence_FR.txt".split())#("data
 # LOAD DATAgeopandas
 COOC_FN = args.cooccurrence_file
 
-
-
 logging.info("Load Cooc DATA data...")
 cooc_data = pd.read_csv(COOC_FN,sep="\t").fillna("")
-# cooc_data["geometry"] = cooc_data["longitude latitude".split()].apply(lambda x: Point(x.longitude,x.latitude),axis=1)
-# cooc_data = gpd.GeoDataFrame(cooc_data)
 logging.info("Cooc data loaded!")
 
-# # World Shape bounds
-# world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))
-# world["nn"] = 1
-# dissolved = world.dissolve(by="nn").iloc[0].geometry
-
-# #Creating Grid
-# logging.info("Initializing Grid (360,180)...")
-# g = Grid(*dissolved.bounds,[360,180])
-# logging.info("Fit Data to the Grid...")
-# g.fit_data(cooc_data)
-# logging.info("Placing place into the grid...")
-# [g+(row.title,row.latitude,row.longitude) for ix,row in tqdm(cooc_data.iterrows(),total=len(cooc_data))]
-
-# #ASSOCIATE CELL NUMBER TO EACH PLACE IN THE GEONAME DATAFRAME
-# logging.info("Associate a cell number to each place in the Geoname Dataframe")
-# def foo(g,id_):
-#     for ix,cell in enumerate(g.cells):
-#         if id_ in cell.list_object:
-#             return ix
 
 cooc_data["cat"] = cooc_data.apply(lambda x:latlon2healpix(x.latitude,x.longitude,64),axis=1)
 
@@ -79,12 +56,9 @@ for i in np.unique(cooc_data.cat.values):
     except Exception as e:
         print(e) #print("Error",len(filtered[filtered.cat == i]))
 
-# del X_train["geometry"]
-# del X_train["nn"]
 del X_train["cat"]
 del X_test["cat"]
-# del X_test["geometry"]
-# del X_test["nn"]
+
 # SAVING THE DATA
 logging.info("Saving Output !")
 suffix =""