add region predictor class

get_region.py

@@ -0,0 +1,82 @@
+__copyright__ = "Copyright (C) 2023 Ali Mustapha"
+__license__ = "GPL-3.0-or-later"
+
+import pandas as pd
+import numpy as np
+import tensorflow as tf
+import pickle
+
+class RegionPredictor:
+    def __init__(self, models_directory):
+        self.models_directory = models_directory
+        
+    def load_model(self, path):
+        model = tf.keras.models.load_model(path+"bestmodel.tf")
+        #compile and train the model
+        model.compile(
+            loss = tf.keras.losses.categorical_crossentropy, 
+            optimizer=tf.keras.optimizers.Adam(),
+            metrics=['accuracy'])
+        with open(self.models_directory+'label_encoder.pkl', 'rb') as file:
+            label_encoder = pickle.load(file)
+        with open(self.models_directory+'optimal_thresholds_f1.pkl', 'rb') as file:
+            optF1 = pickle.load(file)
+        with open(self.models_directory+'optimal_thresholds_ROC.pkl', 'rb') as file:
+            optROC = pickle.load(file)
+        return model,label_encoder,optF1,optROC
+
+
+    def model_prediction(self, dataset,model,label_encoder,optF1=None,optROC=None):
+        input_Full_name=np.asarray(dataset['Full_Name']).astype('str')
+        input_offset=np.asarray(dataset['offset']).astype('float')
+        predictions_proba = model.predict({
+            "input_text": input_Full_name,
+            "input_offset": input_offset
+        })  
+        # predictions = np.argmax(predictions_proba,axis=1)
+        y_pred_F1=[]
+        y_pred_ROC=[]
+        
+        if optF1 is not None:
+            y_pred_F1 = (predictions_proba >= optF1).astype(int)
+            y_pred_F1=np.argmax(y_pred_F1,axis=1)
+            y_pred_F1 = label_encoder.inverse_transform(y_pred_F1)
+            
+        if optROC is not None:
+            y_pred_ROC = (predictions_proba >= optROC).astype(int)
+            y_pred_ROC=np.argmax(y_pred_ROC,axis=1)
+            
+            y_pred_ROC = label_encoder.inverse_transform(y_pred_ROC)
+        
+        return y_pred_F1,y_pred_ROC
+    
+    def get_region(self,dataset):
+        model,label_encoder,optF1,optROC=self.loadModel(self.models_directory+"/region/files/")
+        y_pred,_=self.model_prediction(dataset,model,label_encoder,optF1,optROC)
+        dataset["region-prediction"]=y_pred
+        Europe=dataset[dataset["region-prediction"]=="Europe"]
+        Africa=dataset[dataset["region-prediction"]=="Africa"]
+        Asia=dataset[dataset["region-prediction"]=="Asia"]
+        Americas=dataset[dataset["region-prediction"]=="Americas"]
+        Oceania=dataset[dataset["region-prediction"]=="Oceania"]
+        
+        model,label_encoder,optF1,optROC=self.loadModel(self.models_directory+"/Europe/files/")
+        y_pred,_=self.model_prediction(Europe,model,label_encoder,optF1,optROC)
+        Europe["sub-region-prediction"]=y_pred
+        model,label_encoder,optF1,optROC=self.loadModel(self.models_directory+"/Asia/files/")
+        y_pred,_=self.model_prediction(Asia,model,label_encoder,optF1,optROC)
+        Asia["sub-region-prediction"]=y_pred
+        model,label_encoder,optF1,optROC=self.loadModel(self.models_directory+"/Americas/files/")
+        y_pred=self.model_prediction(Americas,model,label_encoder,optF1,optROC)
+        Americas["sub-region-prediction"]=y_pred
+        Oceania["sub-region-prediction"]="Australia and New Zealand"
+        Africa["sub-region-prediction"]="Africa"
+        data=pd.concat([Europe,Asia,Oceania,Americas,Africa])
+        return data
+
+        
+        
+        
+        
+        
+