Normalize solution.csv tag name, Fix typo

+vid_id,seg1,seg2,seg3,seg4,seg5
+Ndaa,Sports car:0.202,Shower:0.200,Racing:0.200,Greeting card:0.200,Car:0.199
+Dvaa,Tractor:0.363,Motorsport:0.323,Dance:0.145,Flour:0.092,Cappuccino:0.076
+gEaa,Cooking:0.246,Food:0.243,Dish (food):0.224,Vegetable:0.167,:0.120
+Pwaa,Dance:0.633,Wing Chun:0.095,Pencil:0.095,Eye shadow:0.095,Rubber band:0.083
+jgaa,Concert:0.332,Motorsport:0.209,Motorcycling:0.194,Motorcycle:0.159,Bicycle:0.106
+1Yaa,Concert:0.249,Dance:0.191,Tuna:0.188,Airplane:0.187,Association football:0.185
+yVaa,Weight training:0.372,Sport utility vehicle:0.241,Barbell:0.147,Luxury yacht:0.123,Icing (food):0.117
+BCaa,Mobile phone:0.397,Smartphone:0.395,Dance:0.090,Samsung Galaxy:0.073,Alpine skiing:0.046
+38aa,Food:0.269,Gold:0.211,Raven (comics):0.208,Car:0.171,Marching band:0.141
+AFaa,Car:0.386,Sports car:0.276,Motorsport:0.202,Volkswagen:0.078,Food:0.058
+Ajaa,Concert:0.355,Soldier:0.289,Cello:0.146,Drum kit:0.114,Arena:0.096
+2Faa,Orchestra:0.424,Disc jockey:0.288,Inflatable boat:0.115,Vegetarian cuisine:0.096,Concert:0.077
+ujaa,Mobile phone:0.273,Smartphone:0.215,IPhone 5S:0.199,Acoustic guitar:0.170,Door:0.143
+e2aa,Food:0.319,Cooking:0.313,Dish (food):0.285,Pikachu:0.048,Headset (audio):0.036
+UTaa,Pet:0.376,Wig:0.172,Mobile phone:0.170,Easter egg:0.156,Food:0.126
+12aa,Railroad car:0.342,Train:0.300,Muffler:0.142,Car:0.115,BMW 3 Series:0.101
+Duaa,Jaguar Cars:0.379,MacBook Air:0.189,Ferrari F430:0.168,Coupon:0.137,Hang gliding:0.126
+cpab,Car:0.408,Sports car:0.254,Motorsport:0.139,Sedan (automobile):0.139,Racing:0.060
+4rab,Food:0.310,Cooking:0.286,Dish (food):0.265,Meat:0.100,Bee:0.040
+Vtab,Choir:0.228,Handball:0.201,Hot air balloon:0.200,Fishing:0.199,Sedan (automobile):0.172
+gkab,Pet:0.374,Mercedes-Benz C-Class:0.285,Cat:0.162,Belle (Disney):0.111,Electric car:0.068
+RJab,Beer:0.317,Electric car:0.268,Acoustic guitar:0.169,Eye shadow:0.162,Vending machine:0.084
+utab,Concert:0.303,Booster pack:0.279,Fishing:0.159,Culinary art:0.138,Hair coloring:0.121
+Aeab,Samurai:0.278,Fishing:0.240,Association football:0.167,Chevrolet Corvette:0.167,Slam dunk:0.148
+t4ab,Association football:0.520,Barbell:0.166,Teacher:0.105,Biceps curl:0.105,Parachute:0.104
+53ab,Food:0.315,Cooking:0.269,Dish (food):0.257,Concealer:0.113,Bowling ball:0.046
+kaab,Necktie:0.257,Primary school:0.209,Turbine:0.187,Guitar amplifier:0.184,Dance:0.163
+Kdab,Cooking:0.306,Food:0.217,Train:0.175,Acoustic guitar:0.166,Tram:0.137
+Smab,Association football:0.292,Airbus A320 family:0.210,Racing:0.167,Vampire:0.165,Robot:0.165
+rAab,Association football:0.559,Pool (cue sports):0.170,Full moon:0.111,Fishing bait:0.091,Eye liner:0.070
+U3ab,Bride:0.414,Mobile phone:0.267,Smartphone:0.133,Mercedes-Benz C-Class:0.106,Loudspeaker:0.080
+mBab,Food:0.281,Cooking:0.261,Dish (food):0.260,:0.144,Vegetable:0.054
+18ab,Cooking:0.243,Dish (food):0.241,Food:0.239,Vegetable:0.166,:0.112
+NKab,Apartment:0.309,Piano:0.201,Association football:0.179,Table (furniture):0.176,Television set:0.134

+import pandas as pd
+from gensim.models import Word2Vec
+
+
+def vectorization_video():
+    print('[0.1 0.2]')
+
+
+if __name__ == '__main__':
+    tag_vectors = Word2Vec.load("esot3ria/tags_word2vec.model").wv
+    video_vectors = Word2Vec().wv   # Empty model
+
+    # Load video recommendation tags.
+    video_tags = pd.read_csv('esot3ria/video_recommendation_tags.csv')
+    for i, row in video_tags.iterrows():
+        video_id = row[0]
+
+

@@ -14,7 +14,7 @@ for i in range(vocab['Name'].__len__()):
     if isinstance(name, str) and name.find(" (") != -1:
     if isinstance(name, str) and name.find(" (") != -1:
         vocab['Name'][i] = name[:name.find(" (")]
         vocab['Name'][i] = name[:name.find(" (")]
 
 
-# Combine separated names.(mobile phone -> mobile_phone)
+# Combine separated names.(mobile phone -> mobile-phone)
 for name in vocab['Name']:
 for name in vocab['Name']:
     if isinstance(name, str) and name.find(" ") != -1:
     if isinstance(name, str) and name.find(" ") != -1:
         combined_name = name.replace(" ", "-")
         combined_name = name.replace(" ", "-")

@@ -185,6 +185,17 @@ def get_segments(batch_video_mtx, batch_num_frames, segment_size):
   }
   }
 
 
 
 
+def normalize_tag(tag):
+    if isinstance(tag, str):
+        new_tag = tag.lower().replace('[^a-zA-Z]', ' ')
+        if new_tag.find(" (") != -1:
+            new_tag = new_tag[:new_tag.find(" (")]
+        new_tag = new_tag.replace(" ", "-")
+        return new_tag
+    else:
+        return tag
+
+
 def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
 def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
               top_k):
               top_k):
   """Inference function."""
   """Inference function."""
@@ -366,12 +377,16 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
           demoninator = float(temp[0][1] + temp[1][1] + temp[2][1] + temp[3][1] + temp[4][1])
           demoninator = float(temp[0][1] + temp[1][1] + temp[2][1] + temp[3][1] + temp[4][1])
           #for item in temp: 
           #for item in temp: 
           for itemIndex in range(0, top_k):
           for itemIndex in range(0, top_k):
-            result_string = result_string + str(voca_dict[str(temp[itemIndex][0])]) + ":" + format(temp[itemIndex][1]/demoninator,".3f") + ","
+            # 20.05.31 Esot3riA
+            # Normalize tag name
+            segment_tag = str(voca_dict[str(temp[itemIndex][0])])
+            normalized_tag = normalize_tag(segment_tag)
+            result_string = result_string + normalized_tag + ":" + format(temp[itemIndex][1]/demoninator,".3f") + ","
           
           
           cls_result_arr.append(result_string[:-1])
           cls_result_arr.append(result_string[:-1])
           logging.info(segs + " : " + result_string[:-1])
           logging.info(segs + " : " + result_string[:-1])
         #=======================================
         #=======================================
-        final_out_file.write("vid_id,seg_classes\n")
+        final_out_file.write("vid_id,segment1,segment2,segment3,segment4,segment5\n")
         for seg_id, class_indcies in zip(segment_id_list, cls_result_arr):
         for seg_id, class_indcies in zip(segment_id_list, cls_result_arr):
           final_out_file.write("%s,%s\n" %(seg_id, str(class_indcies)))
           final_out_file.write("%s,%s\n" %(seg_id, str(class_indcies)))
         final_out_file.close()
         final_out_file.close()