finetuned the bert model again to classify things right

data_categories/Computers_and_Electronics.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8926ed9c6d555331be7f050a8074b9898260e6e9ec698ddf6a57b5954d2d7adb
-size 36145
+oid sha256:3bfb344e958c0625df92cecfd61ee937ad46f4ae3c1fe7b4a43d64bc66ea025b
+size 53312

data_categories/Final_Category_Data_With_Labels.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381bf850c184b58a8deea31f12421b126212f7c1702a8c73ed3e4176d2b56785
-size 1685102
+oid sha256:0e98ec1b4ff3e48cf46b76010bdb651b013e29b73a2ba8afde2691ff2c7ffd89
+size 1755664

data_categories/Food_and_Drink.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadb7c36f6a07a555ffc31e245efc6062af7a18c58d977eb6877c1807b4e9251
-size 47597
+oid sha256:6f93635d1d2a6cb1bcce6f246efe265a22a21f9b0f9e09ad64ff4f4135e9a873
+size 50513

data_categories/Pets_and_Animals.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88bc062d741826064efa5b0b2135f45abafe10aed9be7122f372769b780daba
-size 57220
+oid sha256:6f02553cb1d35b2874332bdc31f355f85f17bf22d93024ddbe3ed174897c5c60
+size 60136

data_categories/Real Estate.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98584873072b57c4b8629f8071ae0ffe4548f2c1a953260693659f2f740c43a6
-size 36020
+oid sha256:4d2c95f708a885aa30ff47132f588c8b1f69ea65587a9ff2dcdb9012e11754c3
+size 40030

data_categories/Reference.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d77e7335dab3965e50b81a91d2f4312e5408705847ad425b0261a0e45acd136
-size 55091
+oid sha256:f4f2e6a675d15a45ca557f267488141912d0898e231e890f40075b2dad1bf1ce
+size 57698

data_categories/Sensitive Subjects.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6851357c45f0aa9baad91b8263d4f85421ae16952682e44279b193e289e9ed32
-size 10172
+oid sha256:1a2594ab9518c2def44acaef1c8661194ae16c95755face04b58d255bac1b33f
+size 11256

data_categories/Shopping.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88fe8138d63bd43921db7982b432d2d78bbcf8c17d182cf55877c616e856675f
-size 46132
+oid sha256:dc8a3ba5ed07db6b06b247d33d1b91bded1647f55b9ebcb1d50b1072a51eeecf
+size 56890

data_test/keywords-2.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc87cd18c79ecaa87b16dca63019b9577f72073c987ac18c624b059252e32d0f
+size 8356

data_test/labelled_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f208650b882688e9a5cd9e0f2b3787dfd81ca7f5cb524a98c6d1e75d4aadfbf5
+size 19932

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "finetuned_entity_categorical_classification/checkpoint-3346",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -9,63 +9,63 @@
   "dropout": 0.1,
   "hidden_dim": 3072,
   "id2label": {
-    "0": "Beauty_and_Fitness",
-    "1": "People_and_Society",
-    "2": "Travel_and_Transportation",
-    "3": "Shopping",
-    "4": "Adult",
-    "5": "Sports",
-    "6": "Science",
-    "7": "Food_and_Drink",
-    "8": "News",
-    "9": "Sensitive Subjects",
-    "10": "Autos_and_Vehicles",
-    "11": "Law_and_Government",
-    "12": "Business_and_Industrial",
-    "13": "Health",
-    "14": "Real Estate",
-    "15": "Books_and_Literature",
-    "16": "Computers_and_Electronics",
-    "17": "Internet_and_Telecom",
-    "18": "Home_and_Garden",
-    "19": "Jobs_and_Education",
-    "20": "Online Communities",
-    "21": "Finance",
+    "0": "Hobbies_and_Leisure",
+    "1": "News",
+    "2": "Science",
+    "3": "Autos_and_Vehicles",
+    "4": "Health",
+    "5": "Pets_and_Animals",
+    "6": "Adult",
+    "7": "Computers_and_Electronics",
+    "8": "Online Communities",
+    "9": "Beauty_and_Fitness",
+    "10": "People_and_Society",
+    "11": "Business_and_Industrial",
+    "12": "Reference",
+    "13": "Shopping",
+    "14": "Travel_and_Transportation",
+    "15": "Food_and_Drink",
+    "16": "Law_and_Government",
+    "17": "Books_and_Literature",
+    "18": "Finance",
+    "19": "Games",
+    "20": "Home_and_Garden",
+    "21": "Jobs_and_Education",
     "22": "Arts_and_Entertainment",
-    "23": "Games",
-    "24": "Hobbies_and_Leisure",
-    "25": "Reference",
-    "26": "Pets_and_Animals"
+    "23": "Sensitive Subjects",
+    "24": "Real Estate",
+    "25": "Internet_and_Telecom",
+    "26": "Sports"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "Adult": 4,
+    "Adult": 6,
     "Arts_and_Entertainment": 22,
-    "Autos_and_Vehicles": 10,
-    "Beauty_and_Fitness": 0,
-    "Books_and_Literature": 15,
-    "Business_and_Industrial": 12,
-    "Computers_and_Electronics": 16,
-    "Finance": 21,
-    "Food_and_Drink": 7,
-    "Games": 23,
-    "Health": 13,
-    "Hobbies_and_Leisure": 24,
-    "Home_and_Garden": 18,
-    "Internet_and_Telecom": 17,
-    "Jobs_and_Education": 19,
-    "Law_and_Government": 11,
-    "News": 8,
-    "Online Communities": 20,
-    "People_and_Society": 1,
-    "Pets_and_Animals": 26,
-    "Real Estate": 14,
-    "Reference": 25,
-    "Science": 6,
-    "Sensitive Subjects": 9,
-    "Shopping": 3,
-    "Sports": 5,
-    "Travel_and_Transportation": 2
+    "Autos_and_Vehicles": 3,
+    "Beauty_and_Fitness": 9,
+    "Books_and_Literature": 17,
+    "Business_and_Industrial": 11,
+    "Computers_and_Electronics": 7,
+    "Finance": 18,
+    "Food_and_Drink": 15,
+    "Games": 19,
+    "Health": 4,
+    "Hobbies_and_Leisure": 0,
+    "Home_and_Garden": 20,
+    "Internet_and_Telecom": 25,
+    "Jobs_and_Education": 21,
+    "Law_and_Government": 16,
+    "News": 1,
+    "Online Communities": 8,
+    "People_and_Society": 10,
+    "Pets_and_Animals": 5,
+    "Real Estate": 24,
+    "Reference": 12,
+    "Science": 2,
+    "Sensitive Subjects": 23,
+    "Shopping": 13,
+    "Sports": 26,
+    "Travel_and_Transportation": 14
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e20e493b3480b24380280eb5e21c5fd12d4881adfb9cb57a5dd4559f3e85680
+oid sha256:7482411d85a2d5cf5f632c997d2e07449fe4217bcf4b1aad0b38f9138d1acd0a
 size 535881018

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732fd46b0cb9afaec1d14b6595994279ae8d82e40715c5b60b128db60718e69b
+oid sha256:f30aacfea59fa26f3b7edc0f510fe6d083c82c0a92e3118f80f0b13f375cb74e
 size 267932842

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774c81fc50874cca433d334a482dfa90f04ccfdc642ea608612d6233e8d60700
+oid sha256:9c77a82e248c93cca9760dd3358cd21c9eded35e9713e3141aaaa12789322001
 size 1064

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/trainer_state.json

@@ -1,46 +1,46 @@
 {
-  "best_metric": 0.2187376469373703,
-  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1576",
+  "best_metric": 0.10296357423067093,
+  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1681",
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1576,
+  "global_step": 1681,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.32,
-      "learning_rate": 1.957698815566836e-05,
-      "loss": 1.5567,
+      "epoch": 0.3,
+      "learning_rate": 1.7025580011897683e-05,
+      "loss": 0.1045,
       "step": 500
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 1.915397631133672e-05,
-      "loss": 0.3944,
+      "epoch": 0.59,
+      "learning_rate": 1.405116002379536e-05,
+      "loss": 0.1056,
       "step": 1000
     },
     {
-      "epoch": 0.95,
-      "learning_rate": 1.873096446700508e-05,
-      "loss": 0.2773,
+      "epoch": 0.89,
+      "learning_rate": 1.1076740035693041e-05,
+      "loss": 0.1041,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9374900840869427,
-      "eval_loss": 0.2187376469373703,
-      "eval_runtime": 2.2114,
-      "eval_samples_per_second": 2850.256,
-      "eval_steps_per_second": 178.169,
-      "step": 1576
+      "eval_accuracy": 0.9721850364420646,
+      "eval_loss": 0.10296357423067093,
+      "eval_runtime": 2.316,
+      "eval_samples_per_second": 2902.854,
+      "eval_steps_per_second": 181.779,
+      "step": 1681
     }
   ],
   "logging_steps": 500,
-  "max_steps": 23640,
-  "num_train_epochs": 15,
+  "max_steps": 3362,
+  "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 100414675899720.0,
+  "total_flos": 108413372385396.0,
   "trial_name": null,
   "trial_params": null
 }

finetuned_entity_categorical_classification/{checkpoint-1576 → checkpoint-1681}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665da3b0732e752c339d7e2fda57582d0f87bae18392c4edd4fe1327453b2e44
+oid sha256:2de83bc1893d1870cbe886f5287e02f718e1fe0be09dba843ccfc561aeb95ec6
 size 4600

finetuned_entity_categorical_classification/checkpoint-3346/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

finetuned_entity_categorical_classification/checkpoint-3346/config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "finetuned_entity_categorical_classification/checkpoint-3338",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Hobbies_and_Leisure",
+    "1": "News",
+    "2": "Science",
+    "3": "Autos_and_Vehicles",
+    "4": "Health",
+    "5": "Pets_and_Animals",
+    "6": "Adult",
+    "7": "Computers_and_Electronics",
+    "8": "Online Communities",
+    "9": "Beauty_and_Fitness",
+    "10": "People_and_Society",
+    "11": "Business_and_Industrial",
+    "12": "Reference",
+    "13": "Shopping",
+    "14": "Travel_and_Transportation",
+    "15": "Food_and_Drink",
+    "16": "Law_and_Government",
+    "17": "Books_and_Literature",
+    "18": "Finance",
+    "19": "Games",
+    "20": "Home_and_Garden",
+    "21": "Jobs_and_Education",
+    "22": "Arts_and_Entertainment",
+    "23": "Sensitive Subjects",
+    "24": "Real Estate",
+    "25": "Internet_and_Telecom",
+    "26": "Sports"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Adult": 6,
+    "Arts_and_Entertainment": 22,
+    "Autos_and_Vehicles": 3,
+    "Beauty_and_Fitness": 9,
+    "Books_and_Literature": 17,
+    "Business_and_Industrial": 11,
+    "Computers_and_Electronics": 7,
+    "Finance": 18,
+    "Food_and_Drink": 15,
+    "Games": 19,
+    "Health": 4,
+    "Hobbies_and_Leisure": 0,
+    "Home_and_Garden": 20,
+    "Internet_and_Telecom": 25,
+    "Jobs_and_Education": 21,
+    "Law_and_Government": 16,
+    "News": 1,
+    "Online Communities": 8,
+    "People_and_Society": 10,
+    "Pets_and_Animals": 5,
+    "Real Estate": 24,
+    "Reference": 12,
+    "Science": 2,
+    "Sensitive Subjects": 23,
+    "Shopping": 13,
+    "Sports": 26,
+    "Travel_and_Transportation": 14
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 30522
+}

finetuned_entity_categorical_classification/checkpoint-3346/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7fd88a2fd3f16fd9c954418fb3e47832af4a6e96026f465481de95dd8e4b99
+size 535881018

finetuned_entity_categorical_classification/checkpoint-3346/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0316f1198be89b32f1ee6ecde222febe6895b798b64d12f8e12b0f5bdaba754
+size 267932842

finetuned_entity_categorical_classification/checkpoint-3346/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836b9ae7a26190d3866515097d559222a1c62e5f96c298c8360e09e55b2cf8a4
+size 1064

finetuned_entity_categorical_classification/checkpoint-3346/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

finetuned_entity_categorical_classification/checkpoint-3346/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

finetuned_entity_categorical_classification/checkpoint-3346/trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.10625720769166946,
+  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1673",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3346,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7011356843992828e-05,
+      "loss": 0.1126,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4022713687985656e-05,
+      "loss": 0.1165,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1034070531978483e-05,
+      "loss": 0.117,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9715951562266407,
+      "eval_loss": 0.10625720769166946,
+      "eval_runtime": 2.3554,
+      "eval_samples_per_second": 2839.909,
+      "eval_steps_per_second": 177.892,
+      "step": 1673
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.04542737597131e-06,
+      "loss": 0.0894,
+      "step": 2000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.056784219964137e-06,
+      "loss": 0.0827,
+      "step": 2500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.068141063956964e-06,
+      "loss": 0.0755,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9706981611601136,
+      "eval_loss": 0.1135576069355011,
+      "eval_runtime": 2.4092,
+      "eval_samples_per_second": 2776.427,
+      "eval_steps_per_second": 173.916,
+      "step": 3346
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3346,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 209706294909150.0,
+  "trial_name": null,
+  "trial_params": null
+}

finetuned_entity_categorical_classification/checkpoint-3346/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7813e2902539bc577c8459ca958658172359e179c4ef494972d6db5de3ada53e
+size 4600

finetuned_entity_categorical_classification/checkpoint-3362/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

finetuned_entity_categorical_classification/checkpoint-3362/config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "finetuned_entity_categorical_classification/checkpoint-3346",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Hobbies_and_Leisure",
+    "1": "News",
+    "2": "Science",
+    "3": "Autos_and_Vehicles",
+    "4": "Health",
+    "5": "Pets_and_Animals",
+    "6": "Adult",
+    "7": "Computers_and_Electronics",
+    "8": "Online Communities",
+    "9": "Beauty_and_Fitness",
+    "10": "People_and_Society",
+    "11": "Business_and_Industrial",
+    "12": "Reference",
+    "13": "Shopping",
+    "14": "Travel_and_Transportation",
+    "15": "Food_and_Drink",
+    "16": "Law_and_Government",
+    "17": "Books_and_Literature",
+    "18": "Finance",
+    "19": "Games",
+    "20": "Home_and_Garden",
+    "21": "Jobs_and_Education",
+    "22": "Arts_and_Entertainment",
+    "23": "Sensitive Subjects",
+    "24": "Real Estate",
+    "25": "Internet_and_Telecom",
+    "26": "Sports"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Adult": 6,
+    "Arts_and_Entertainment": 22,
+    "Autos_and_Vehicles": 3,
+    "Beauty_and_Fitness": 9,
+    "Books_and_Literature": 17,
+    "Business_and_Industrial": 11,
+    "Computers_and_Electronics": 7,
+    "Finance": 18,
+    "Food_and_Drink": 15,
+    "Games": 19,
+    "Health": 4,
+    "Hobbies_and_Leisure": 0,
+    "Home_and_Garden": 20,
+    "Internet_and_Telecom": 25,
+    "Jobs_and_Education": 21,
+    "Law_and_Government": 16,
+    "News": 1,
+    "Online Communities": 8,
+    "People_and_Society": 10,
+    "Pets_and_Animals": 5,
+    "Real Estate": 24,
+    "Reference": 12,
+    "Science": 2,
+    "Sensitive Subjects": 23,
+    "Shopping": 13,
+    "Sports": 26,
+    "Travel_and_Transportation": 14
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 30522
+}

finetuned_entity_categorical_classification/checkpoint-3362/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d015879f29a2744736a3ba7748885a4ec943584a74c779bc00637389c2d90ccd
+size 535881018

finetuned_entity_categorical_classification/checkpoint-3362/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f9ac5b4263d73b4fe5715bd69766cb18cb5925f401945d0c67275a65364524
+size 267932842

finetuned_entity_categorical_classification/checkpoint-3362/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af53710b40243eb9329cc845f9ef3a957c0e1972618f070ad4cc3c95bc43973
+size 1064

finetuned_entity_categorical_classification/checkpoint-3362/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

finetuned_entity_categorical_classification/checkpoint-3362/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

finetuned_entity_categorical_classification/checkpoint-3362/trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.10296357423067093,
+  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1681",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3362,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7025580011897683e-05,
+      "loss": 0.1045,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.405116002379536e-05,
+      "loss": 0.1056,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1076740035693041e-05,
+      "loss": 0.1041,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9721850364420646,
+      "eval_loss": 0.10296357423067093,
+      "eval_runtime": 2.316,
+      "eval_samples_per_second": 2902.854,
+      "eval_steps_per_second": 181.779,
+      "step": 1681
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 8.10232004759072e-06,
+      "loss": 0.0776,
+      "step": 2000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.1279000594884e-06,
+      "loss": 0.0675,
+      "step": 2500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.1534800713860798e-06,
+      "loss": 0.0773,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9708463483563885,
+      "eval_loss": 0.11056160181760788,
+      "eval_runtime": 2.2742,
+      "eval_samples_per_second": 2956.182,
+      "eval_steps_per_second": 185.119,
+      "step": 3362
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3362,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 216609059710134.0,
+  "trial_name": null,
+  "trial_params": null
+}

finetuned_entity_categorical_classification/checkpoint-3362/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de83bc1893d1870cbe886f5287e02f718e1fe0be09dba843ccfc561aeb95ec6
+size 4600

research/08_organizing_entire_datacategories.ipynb

@@ -438,173 +438,173 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>920</th>\n",
-       "      <td>Virtual reality in therapy 2025</td>\n",
-       "      <td>Computers_and_Electronics</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>368</th>\n",
-       "      <td>Real estate networking tips</td>\n",
-       "      <td>Real Estate</td>\n",
-       "      <td>24</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>173</th>\n",
-       "      <td>Real estate market outlook</td>\n",
-       "      <td>Real Estate</td>\n",
-       "      <td>24</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1045</th>\n",
+       "      <th>1201</th>\n",
        "      <td>Plus-size clothing stores and shops</td>\n",
        "      <td>Shopping</td>\n",
        "      <td>13</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>910</th>\n",
-       "      <td>Canyoning trips</td>\n",
-       "      <td>Hobbies_and_Leisure</td>\n",
-       "      <td>0</td>\n",
+       "      <th>853</th>\n",
+       "      <td>Citation context extraction techniques</td>\n",
+       "      <td>Reference</td>\n",
+       "      <td>12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1098</th>\n",
-       "      <td>Food storage organization</td>\n",
-       "      <td>Food_and_Drink</td>\n",
-       "      <td>15</td>\n",
+       "      <th>1034</th>\n",
+       "      <td>Cat ear headphones with aux</td>\n",
+       "      <td>Computers_and_Electronics</td>\n",
+       "      <td>7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>788</th>\n",
-       "      <td>Political party systems</td>\n",
-       "      <td>Law_and_Government</td>\n",
-       "      <td>16</td>\n",
+       "      <th>632</th>\n",
+       "      <td>promote such behavior</td>\n",
+       "      <td>Sensitive Subjects</td>\n",
+       "      <td>23</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>999</th>\n",
-       "      <td>Voting systems security</td>\n",
+       "      <th>91</th>\n",
+       "      <td>Literature review references</td>\n",
+       "      <td>Reference</td>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>168</th>\n",
+       "      <td>Freedom of speech cases</td>\n",
        "      <td>Law_and_Government</td>\n",
        "      <td>16</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>547</th>\n",
-       "      <td>Cottage garden outdoor seating</td>\n",
+       "      <th>1111</th>\n",
+       "      <td>French country kitchen design inspiration DIY</td>\n",
        "      <td>Home_and_Garden</td>\n",
        "      <td>20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>210</th>\n",
-       "      <td>Sustainable fashion and ethical clothing networks</td>\n",
-       "      <td>Online Communities</td>\n",
-       "      <td>8</td>\n",
+       "      <th>492</th>\n",
+       "      <td>Credit score improvement techniques overview</td>\n",
+       "      <td>Finance</td>\n",
+       "      <td>18</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>466</th>\n",
-       "      <td>Medicaid</td>\n",
+       "      <th>657</th>\n",
+       "      <td>regulated by laws</td>\n",
+       "      <td>Sensitive Subjects</td>\n",
+       "      <td>23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1037</th>\n",
+       "      <td>Health Education for Seniors</td>\n",
        "      <td>Health</td>\n",
        "      <td>4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>908</th>\n",
-       "      <td>Shakespearean adaptations in historical contex...</td>\n",
-       "      <td>Books_and_Literature</td>\n",
-       "      <td>17</td>\n",
+       "      <th>109</th>\n",
+       "      <td>Quantum mechanics experiments</td>\n",
+       "      <td>Science</td>\n",
+       "      <td>2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>831</th>\n",
-       "      <td>Travel destinations and vacation planning advi...</td>\n",
-       "      <td>Online Communities</td>\n",
-       "      <td>8</td>\n",
+       "      <th>538</th>\n",
+       "      <td>Healthcare AI applications</td>\n",
+       "      <td>Science</td>\n",
+       "      <td>2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>746</th>\n",
-       "      <td>Social and political activism campaigns and ev...</td>\n",
-       "      <td>Online Communities</td>\n",
-       "      <td>8</td>\n",
+       "      <th>1386</th>\n",
+       "      <td>AirPods Pro Case</td>\n",
+       "      <td>Computers_and_Electronics</td>\n",
+       "      <td>7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>715</th>\n",
-       "      <td>Community development resources</td>\n",
-       "      <td>People_and_Society</td>\n",
-       "      <td>10</td>\n",
+       "      <th>844</th>\n",
+       "      <td>DIY home electrical repairs</td>\n",
+       "      <td>Home_and_Garden</td>\n",
+       "      <td>20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>639</th>\n",
-       "      <td>Scientific data analysis software</td>\n",
-       "      <td>Science</td>\n",
-       "      <td>2</td>\n",
+       "      <th>439</th>\n",
+       "      <td>tube sex</td>\n",
+       "      <td>Adult</td>\n",
+       "      <td>6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>830</th>\n",
-       "      <td>Real estate market reports and insights</td>\n",
+       "      <th>231</th>\n",
+       "      <td>Real estate sales tactics</td>\n",
        "      <td>Real Estate</td>\n",
        "      <td>24</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>978</th>\n",
-       "      <td>Reference citation context importance measurem...</td>\n",
-       "      <td>Reference</td>\n",
-       "      <td>12</td>\n",
+       "      <th>610</th>\n",
+       "      <td>Home solar panel cleaning and maintenance</td>\n",
+       "      <td>Home_and_Garden</td>\n",
+       "      <td>20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>938</th>\n",
-       "      <td>Industrial companies in Asia</td>\n",
-       "      <td>Business_and_Industrial</td>\n",
-       "      <td>11</td>\n",
+       "      <th>422</th>\n",
+       "      <td>Real estate legal issues</td>\n",
+       "      <td>Real Estate</td>\n",
+       "      <td>24</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>Legal system</td>\n",
-       "      <td>Law_and_Government</td>\n",
-       "      <td>16</td>\n",
+       "      <th>222</th>\n",
+       "      <td>Film industry news</td>\n",
+       "      <td>Arts_and_Entertainment</td>\n",
+       "      <td>22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1077</th>\n",
+       "      <td>Cat ear headphones for PS4</td>\n",
+       "      <td>Computers_and_Electronics</td>\n",
+       "      <td>7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "                                               category  \\\n",
-       "920                     Virtual reality in therapy 2025   \n",
-       "368                         Real estate networking tips   \n",
-       "173                          Real estate market outlook   \n",
-       "1045                Plus-size clothing stores and shops   \n",
-       "910                                     Canyoning trips   \n",
-       "1098                          Food storage organization   \n",
-       "788                             Political party systems   \n",
-       "999                             Voting systems security   \n",
-       "547                      Cottage garden outdoor seating   \n",
-       "210   Sustainable fashion and ethical clothing networks   \n",
-       "466                                            Medicaid   \n",
-       "908   Shakespearean adaptations in historical contex...   \n",
-       "831   Travel destinations and vacation planning advi...   \n",
-       "746   Social and political activism campaigns and ev...   \n",
-       "715                     Community development resources   \n",
-       "639                   Scientific data analysis software   \n",
-       "830             Real estate market reports and insights   \n",
-       "978   Reference citation context importance measurem...   \n",
-       "938                        Industrial companies in Asia   \n",
-       "8                                          Legal system   \n",
+       "                                           category  \\\n",
+       "1201            Plus-size clothing stores and shops   \n",
+       "853          Citation context extraction techniques   \n",
+       "1034                    Cat ear headphones with aux   \n",
+       "632                           promote such behavior   \n",
+       "91                     Literature review references   \n",
+       "168                         Freedom of speech cases   \n",
+       "1111  French country kitchen design inspiration DIY   \n",
+       "492    Credit score improvement techniques overview   \n",
+       "657                               regulated by laws   \n",
+       "1037                   Health Education for Seniors   \n",
+       "109                   Quantum mechanics experiments   \n",
+       "538                      Healthcare AI applications   \n",
+       "1386                               AirPods Pro Case   \n",
+       "844                     DIY home electrical repairs   \n",
+       "439                                        tube sex   \n",
+       "231                       Real estate sales tactics   \n",
+       "610       Home solar panel cleaning and maintenance   \n",
+       "422                        Real estate legal issues   \n",
+       "222                              Film industry news   \n",
+       "1077                     Cat ear headphones for PS4   \n",
        "\n",
        "                          label  label_id  \n",
-       "920   Computers_and_Electronics         7  \n",
-       "368                 Real Estate        24  \n",
-       "173                 Real Estate        24  \n",
-       "1045                   Shopping        13  \n",
-       "910         Hobbies_and_Leisure         0  \n",
-       "1098             Food_and_Drink        15  \n",
-       "788          Law_and_Government        16  \n",
-       "999          Law_and_Government        16  \n",
-       "547             Home_and_Garden        20  \n",
-       "210          Online Communities         8  \n",
-       "466                      Health         4  \n",
-       "908        Books_and_Literature        17  \n",
-       "831          Online Communities         8  \n",
-       "746          Online Communities         8  \n",
-       "715          People_and_Society        10  \n",
-       "639                     Science         2  \n",
-       "830                 Real Estate        24  \n",
-       "978                   Reference        12  \n",
-       "938     Business_and_Industrial        11  \n",
-       "8            Law_and_Government        16  "
+       "1201                   Shopping        13  \n",
+       "853                   Reference        12  \n",
+       "1034  Computers_and_Electronics         7  \n",
+       "632          Sensitive Subjects        23  \n",
+       "91                    Reference        12  \n",
+       "168          Law_and_Government        16  \n",
+       "1111            Home_and_Garden        20  \n",
+       "492                     Finance        18  \n",
+       "657          Sensitive Subjects        23  \n",
+       "1037                     Health         4  \n",
+       "109                     Science         2  \n",
+       "538                     Science         2  \n",
+       "1386  Computers_and_Electronics         7  \n",
+       "844             Home_and_Garden        20  \n",
+       "439                       Adult         6  \n",
+       "231                 Real Estate        24  \n",
+       "610             Home_and_Garden        20  \n",
+       "422                 Real Estate        24  \n",
+       "222      Arts_and_Entertainment        22  \n",
+       "1077  Computers_and_Electronics         7  "
       ]
      },
      "execution_count": 10,
@@ -625,21 +625,22 @@
      "data": {
       "text/plain": [
        "label\n",
-       "Food_and_Drink               1755\n",
-       "Shopping                     1505\n",
-       "Computers_and_Electronics    1432\n",
+       "Computers_and_Electronics    1959\n",
+       "Shopping                     1912\n",
+       "Food_and_Drink               1851\n",
+       "Reference                    1453\n",
        "Sports                       1399\n",
        "Online Communities           1396\n",
        "Travel_and_Transportation    1355\n",
        "Internet_and_Telecom         1353\n",
-       "Reference                    1315\n",
+       "Pets_and_Animals             1324\n",
        "Beauty_and_Fitness           1259\n",
        "People_and_Society           1250\n",
-       "Pets_and_Animals             1228\n",
        "Law_and_Government           1226\n",
        "Home_and_Garden              1200\n",
        "News                         1199\n",
        "Jobs_and_Education           1188\n",
+       "Real Estate                  1166\n",
        "Arts_and_Entertainment       1162\n",
        "Business_and_Industrial      1124\n",
        "Adult                        1100\n",
@@ -647,11 +648,10 @@
        "Autos_and_Vehicles           1072\n",
        "Science                      1055\n",
        "Hobbies_and_Leisure          1049\n",
-       "Finance                      1000\n",
-       "Real Estate                  1000\n",
        "Books_and_Literature         1000\n",
+       "Finance                      1000\n",
+       "Sensitive Subjects            762\n",
        "Games                         700\n",
-       "Sensitive Subjects            688\n",
        "Name: count, dtype: int64"
       ]
      },
@@ -698,121 +698,121 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>DIY woodworking projects</td>\n",
-       "      <td>Home_and_Garden</td>\n",
-       "      <td>20</td>\n",
+       "      <td>Internet usage monitoring</td>\n",
+       "      <td>Internet_and_Telecom</td>\n",
+       "      <td>25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>Music festivals lineup leaks</td>\n",
-       "      <td>Arts_and_Entertainment</td>\n",
-       "      <td>22</td>\n",
+       "      <td>Food safety guidelines and regulations</td>\n",
+       "      <td>Food_and_Drink</td>\n",
+       "      <td>15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>Sports Team Fan Love</td>\n",
-       "      <td>Sports</td>\n",
-       "      <td>26</td>\n",
+       "      <td>Internet protocols and edge computing in finance</td>\n",
+       "      <td>Internet_and_Telecom</td>\n",
+       "      <td>25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>Food portion control and portion control apps</td>\n",
+       "      <td>Online grocery shopping</td>\n",
        "      <td>Food_and_Drink</td>\n",
        "      <td>15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>Planting flower beds</td>\n",
-       "      <td>Home_and_Garden</td>\n",
-       "      <td>20</td>\n",
+       "      <td>Writing retreats for poets and novelists</td>\n",
+       "      <td>Books_and_Literature</td>\n",
+       "      <td>17</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
-       "      <td>News articles</td>\n",
-       "      <td>News</td>\n",
-       "      <td>1</td>\n",
+       "      <td>Unicorn cat ear headphones</td>\n",
+       "      <td>Computers_and_Electronics</td>\n",
+       "      <td>7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
-       "      <td>Organic makeup for natural look</td>\n",
-       "      <td>Beauty_and_Fitness</td>\n",
-       "      <td>9</td>\n",
+       "      <td>Reference citation context tagging techniques</td>\n",
+       "      <td>Reference</td>\n",
+       "      <td>12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
-       "      <td>Art history online courses in art therapy</td>\n",
-       "      <td>Arts_and_Entertainment</td>\n",
-       "      <td>22</td>\n",
+       "      <td>Motorcycle riding tips for beginners gear chec...</td>\n",
+       "      <td>Autos_and_Vehicles</td>\n",
+       "      <td>3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
-       "      <td>Citation context ranking algorithms</td>\n",
-       "      <td>Reference</td>\n",
-       "      <td>12</td>\n",
+       "      <td>Space agency missions</td>\n",
+       "      <td>Science</td>\n",
+       "      <td>2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
-       "      <td>Career assessment quizzes</td>\n",
-       "      <td>Jobs_and_Education</td>\n",
-       "      <td>21</td>\n",
+       "      <td>Game streaming self-promotion and growth tactics</td>\n",
+       "      <td>Games</td>\n",
+       "      <td>19</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>10</th>\n",
-       "      <td>Game streaming camera choice and setup tips</td>\n",
-       "      <td>Games</td>\n",
-       "      <td>19</td>\n",
+       "      <td>sex videos movies</td>\n",
+       "      <td>Adult</td>\n",
+       "      <td>6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>11</th>\n",
-       "      <td>Truck financing</td>\n",
-       "      <td>Autos_and_Vehicles</td>\n",
-       "      <td>3</td>\n",
+       "      <td>Citation context organization methods</td>\n",
+       "      <td>Reference</td>\n",
+       "      <td>12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>12</th>\n",
-       "      <td>Community engagement</td>\n",
-       "      <td>People_and_Society</td>\n",
-       "      <td>10</td>\n",
+       "      <td>Healthy office snacks</td>\n",
+       "      <td>Health</td>\n",
+       "      <td>4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>13</th>\n",
-       "      <td>Creative writing prompts</td>\n",
-       "      <td>Books_and_Literature</td>\n",
-       "      <td>17</td>\n",
+       "      <td>Indigenous rights advocacy</td>\n",
+       "      <td>People_and_Society</td>\n",
+       "      <td>10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>14</th>\n",
-       "      <td>Reference citation context exploration methods</td>\n",
-       "      <td>Reference</td>\n",
-       "      <td>12</td>\n",
+       "      <td>News talk shows</td>\n",
+       "      <td>News</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>15</th>\n",
-       "      <td>Online discussion boards</td>\n",
-       "      <td>Online Communities</td>\n",
-       "      <td>8</td>\n",
+       "      <td>Best facial cleansers</td>\n",
+       "      <td>Hobbies_and_Leisure</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>16</th>\n",
-       "      <td>Tarantula species care for advanced keepers an...</td>\n",
-       "      <td>Pets_and_Animals</td>\n",
-       "      <td>5</td>\n",
+       "      <td>Letter of recommendation</td>\n",
+       "      <td>Reference</td>\n",
+       "      <td>12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>17</th>\n",
-       "      <td>Cycling workouts</td>\n",
-       "      <td>Beauty_and_Fitness</td>\n",
-       "      <td>9</td>\n",
+       "      <td>Fossil preservation techniques</td>\n",
+       "      <td>Science</td>\n",
+       "      <td>2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>18</th>\n",
-       "      <td>Webcomics and graphic novels discussion groups</td>\n",
-       "      <td>Online Communities</td>\n",
-       "      <td>8</td>\n",
+       "      <td>Marriage equality</td>\n",
+       "      <td>People_and_Society</td>\n",
+       "      <td>10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>19</th>\n",
-       "      <td>eSports Game Content Creation</td>\n",
+       "      <td>eSports Game Esports Player Fan Engagement Ini...</td>\n",
        "      <td>Sports</td>\n",
        "      <td>26</td>\n",
        "    </tr>\n",
@@ -821,49 +821,49 @@
        "</div>"
       ],
       "text/plain": [
-       "                                             category                   label  \\\n",
-       "0                            DIY woodworking projects         Home_and_Garden   \n",
-       "1                        Music festivals lineup leaks  Arts_and_Entertainment   \n",
-       "2                                Sports Team Fan Love                  Sports   \n",
-       "3       Food portion control and portion control apps          Food_and_Drink   \n",
-       "4                                Planting flower beds         Home_and_Garden   \n",
-       "5                                       News articles                    News   \n",
-       "6                     Organic makeup for natural look      Beauty_and_Fitness   \n",
-       "7           Art history online courses in art therapy  Arts_and_Entertainment   \n",
-       "8                 Citation context ranking algorithms               Reference   \n",
-       "9                           Career assessment quizzes      Jobs_and_Education   \n",
-       "10        Game streaming camera choice and setup tips                   Games   \n",
-       "11                                    Truck financing      Autos_and_Vehicles   \n",
-       "12                               Community engagement      People_and_Society   \n",
-       "13                           Creative writing prompts    Books_and_Literature   \n",
-       "14     Reference citation context exploration methods               Reference   \n",
-       "15                           Online discussion boards      Online Communities   \n",
-       "16  Tarantula species care for advanced keepers an...        Pets_and_Animals   \n",
-       "17                                   Cycling workouts      Beauty_and_Fitness   \n",
-       "18     Webcomics and graphic novels discussion groups      Online Communities   \n",
-       "19                      eSports Game Content Creation                  Sports   \n",
+       "                                             category  \\\n",
+       "0                           Internet usage monitoring   \n",
+       "1              Food safety guidelines and regulations   \n",
+       "2    Internet protocols and edge computing in finance   \n",
+       "3                             Online grocery shopping   \n",
+       "4            Writing retreats for poets and novelists   \n",
+       "5                          Unicorn cat ear headphones   \n",
+       "6       Reference citation context tagging techniques   \n",
+       "7   Motorcycle riding tips for beginners gear chec...   \n",
+       "8                               Space agency missions   \n",
+       "9    Game streaming self-promotion and growth tactics   \n",
+       "10                                  sex videos movies   \n",
+       "11              Citation context organization methods   \n",
+       "12                              Healthy office snacks   \n",
+       "13                         Indigenous rights advocacy   \n",
+       "14                                    News talk shows   \n",
+       "15                              Best facial cleansers   \n",
+       "16                           Letter of recommendation   \n",
+       "17                     Fossil preservation techniques   \n",
+       "18                                  Marriage equality   \n",
+       "19  eSports Game Esports Player Fan Engagement Ini...   \n",
        "\n",
-       "    label_id  \n",
-       "0         20  \n",
-       "1         22  \n",
-       "2         26  \n",
-       "3         15  \n",
-       "4         20  \n",
-       "5          1  \n",
-       "6          9  \n",
-       "7         22  \n",
-       "8         12  \n",
-       "9         21  \n",
-       "10        19  \n",
-       "11         3  \n",
-       "12        10  \n",
-       "13        17  \n",
-       "14        12  \n",
-       "15         8  \n",
-       "16         5  \n",
-       "17         9  \n",
-       "18         8  \n",
-       "19        26  "
+       "                        label  label_id  \n",
+       "0        Internet_and_Telecom        25  \n",
+       "1              Food_and_Drink        15  \n",
+       "2        Internet_and_Telecom        25  \n",
+       "3              Food_and_Drink        15  \n",
+       "4        Books_and_Literature        17  \n",
+       "5   Computers_and_Electronics         7  \n",
+       "6                   Reference        12  \n",
+       "7          Autos_and_Vehicles         3  \n",
+       "8                     Science         2  \n",
+       "9                       Games        19  \n",
+       "10                      Adult         6  \n",
+       "11                  Reference        12  \n",
+       "12                     Health         4  \n",
+       "13         People_and_Society        10  \n",
+       "14                       News         1  \n",
+       "15        Hobbies_and_Leisure         0  \n",
+       "16                  Reference        12  \n",
+       "17                    Science         2  \n",
+       "18         People_and_Society        10  \n",
+       "19                     Sports        26  "
       ]
      },
      "execution_count": 12,