added Azure NER

data/wolf_cut_labelled.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809d5432ceb512c742171eaefe4862dcc283674b8eab13eacf17ff15595fc16a
+size 278211

data/wolf_cut_temp.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a72974667af5a81b8012edba66f761f6c6784d03658413c37db06b0e94f0fb
+size 52781

data_intent/intent_data.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24091e2e977d444be178138ac717fa57b8d16534dcf5e66d4084cf3f77e6f6ce
-size 39551
+oid sha256:2ee34445e32b84ac258ad523d7c6b1c6babf326a6932ae05f4a9aeae01ae4366
+size 72303

data_intent/temp.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c89381303aa0fec070d7141d2e3ad2699daf9d0fb0c2a99eec7625c41977b62
+size 632216

finetuned_entity_categorical_classification/checkpoint-1681/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7482411d85a2d5cf5f632c997d2e07449fe4217bcf4b1aad0b38f9138d1acd0a
+oid sha256:7ddb82ef6b7ce9d69183007173cd0480840f0e859a1284293e8d83debea834d5
 size 535881018

finetuned_entity_categorical_classification/checkpoint-1681/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30aacfea59fa26f3b7edc0f510fe6d083c82c0a92e3118f80f0b13f375cb74e
+oid sha256:1026e1cb049c206c60d220d76f2ad9cccabbb8a8e435bf46049bfcbb6b973a7f
 size 267932842

finetuned_entity_categorical_classification/checkpoint-1681/trainer_state.json

@@ -1,5 +1,5 @@
 {
- "best_metric": 0.10296357423067093,
+ "best_metric": 0.07765195518732071,
  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1681",
  "epoch": 1.0,
  "eval_steps": 500,
@@ -11,28 +11,28 @@
  {
  "epoch": 0.3,
  "learning_rate": 1.7025580011897683e-05,
- "loss": 0.1045,
+ "loss": 0.1008,
  "step": 500
  },
  {
  "epoch": 0.59,
  "learning_rate": 1.405116002379536e-05,
- "loss": 0.1056,
+ "loss": 0.1133,
  "step": 1000
  },
  {
  "epoch": 0.89,
  "learning_rate": 1.1076740035693041e-05,
- "loss": 0.1041,
+ "loss": 0.1023,
  "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,
+ "eval_accuracy": 0.9753086419753086,
+ "eval_loss": 0.07765195518732071,
+ "eval_runtime": 2.2887,
+ "eval_samples_per_second": 2937.427,
+ "eval_steps_per_second": 183.944,
  "step": 1681
  }
  ],
@@ -40,7 +40,7 @@
  "max_steps": 3362,
  "num_train_epochs": 2,
  "save_steps": 500,
- "total_flos": 108413372385396.0,
+ "total_flos": 106434534943386.0,
  "trial_name": null,
  "trial_params": null
 }

finetuned_entity_categorical_classification/checkpoint-1681/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de83bc1893d1870cbe886f5287e02f718e1fe0be09dba843ccfc561aeb95ec6
+oid sha256:38ca296b683b24f6f80d4f29a9a0c986a837732910bd0a31303095257578ddfb
 size 4600

finetuned_entity_categorical_classification/checkpoint-3362/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d015879f29a2744736a3ba7748885a4ec943584a74c779bc00637389c2d90ccd
+oid sha256:167b28137ba8f1cd7b5e16c91eb0e53bf3273a77a9f450b8f88896a8fc0333a5
 size 535881018

finetuned_entity_categorical_classification/checkpoint-3362/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f9ac5b4263d73b4fe5715bd69766cb18cb5925f401945d0c67275a65364524
+oid sha256:c4394c17645f6749fa890492765494e6f6dcf094a971ee68dff1d187d6339a1d
 size 267932842

finetuned_entity_categorical_classification/checkpoint-3362/trainer_state.json

@@ -1,5 +1,5 @@
 {
- "best_metric": 0.10296357423067093,
+ "best_metric": 0.07765195518732071,
  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1681",
  "epoch": 2.0,
  "eval_steps": 500,
@@ -11,55 +11,55 @@
  {
  "epoch": 0.3,
  "learning_rate": 1.7025580011897683e-05,
- "loss": 0.1045,
+ "loss": 0.1008,
  "step": 500
  },
  {
  "epoch": 0.59,
  "learning_rate": 1.405116002379536e-05,
- "loss": 0.1056,
+ "loss": 0.1133,
  "step": 1000
  },
  {
  "epoch": 0.89,
  "learning_rate": 1.1076740035693041e-05,
- "loss": 0.1041,
+ "loss": 0.1023,
  "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,
+ "eval_accuracy": 0.9753086419753086,
+ "eval_loss": 0.07765195518732071,
+ "eval_runtime": 2.2887,
+ "eval_samples_per_second": 2937.427,
+ "eval_steps_per_second": 183.944,
  "step": 1681
  },
  {
  "epoch": 1.19,
  "learning_rate": 8.10232004759072e-06,
- "loss": 0.0776,
+ "loss": 0.0827,
  "step": 2000
  },
  {
  "epoch": 1.49,
  "learning_rate": 5.1279000594884e-06,
- "loss": 0.0675,
+ "loss": 0.0702,
  "step": 2500
  },
  {
  "epoch": 1.78,
  "learning_rate": 2.1534800713860798e-06,
- "loss": 0.0773,
+ "loss": 0.0834,
  "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,
+ "eval_accuracy": 0.9747136694927859,
+ "eval_loss": 0.08629146963357925,
+ "eval_runtime": 2.3024,
+ "eval_samples_per_second": 2919.969,
+ "eval_steps_per_second": 182.851,
  "step": 3362
  }
  ],
@@ -67,7 +67,7 @@
  "max_steps": 3362,
  "num_train_epochs": 2,
  "save_steps": 500,
- "total_flos": 216609059710134.0,
+ "total_flos": 213673546900476.0,
  "trial_name": null,
  "trial_params": null
 }

finetuned_entity_categorical_classification/checkpoint-3362/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de83bc1893d1870cbe886f5287e02f718e1fe0be09dba843ccfc561aeb95ec6
+oid sha256:38ca296b683b24f6f80d4f29a9a0c986a837732910bd0a31303095257578ddfb
 size 4600

intent_classification_model/{checkpoint-324 → checkpoint-1216}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50f88f7a9097ecddb2b3c7e3d38747deec4ca3a386132fac9e0e4efaa82ae0e
+oid sha256:97791790fb47e0d2262cfd6c379f3e36d956e7ef05ddcfcd905abba63c990209
 size 535745722

intent_classification_model/{checkpoint-324 → checkpoint-1216}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b339df5c0d892e025a1749d085ab010e551f4b249eb497812a1a3bd7ebd5fd99
+oid sha256:3d83acd64be6fc794a8e6c94f48eb095fd23679e7c612bd83712b5738588b1b8
 size 267865194

intent_classification_model/{checkpoint-324 → checkpoint-1216}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f74582c189fe624f606122980ccb279125588a1db45b4052dc704fa2b51184
+oid sha256:a94db5976ef19e649b033b8c416b03f555990a66e540f81cc5eccc167168f1bc
 size 1064

intent_classification_model/checkpoint-1216/trainer_state.json

@@ -0,0 +1,175 @@
+{
+ "best_metric": 0.06275933235883713,
+ "best_model_checkpoint": "intent_classification_model/checkpoint-152",
+ "epoch": 16.0,
+ "eval_steps": 500,
+ "global_step": 1216,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.9867549668874173,
+ "eval_loss": 0.20886486768722534,
+ "eval_runtime": 0.1475,
+ "eval_samples_per_second": 2048.099,
+ "eval_steps_per_second": 128.854,
+ "step": 76
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.9834437086092715,
+ "eval_loss": 0.06275933235883713,
+ "eval_runtime": 0.1586,
+ "eval_samples_per_second": 1904.103,
+ "eval_steps_per_second": 119.795,
+ "step": 152
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.9867549668874173,
+ "eval_loss": 0.06509935110807419,
+ "eval_runtime": 0.1445,
+ "eval_samples_per_second": 2090.586,
+ "eval_steps_per_second": 131.527,
+ "step": 228
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.9768211920529801,
+ "eval_loss": 0.08112386614084244,
+ "eval_runtime": 0.1335,
+ "eval_samples_per_second": 2262.833,
+ "eval_steps_per_second": 142.364,
+ "step": 304
+ },
+ {
+ "epoch": 5.0,
+ "eval_accuracy": 0.9701986754966887,
+ "eval_loss": 0.11257749050855637,
+ "eval_runtime": 0.134,
+ "eval_samples_per_second": 2253.71,
+ "eval_steps_per_second": 141.79,
+ "step": 380
+ },
+ {
+ "epoch": 6.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.11174333095550537,
+ "eval_runtime": 0.1339,
+ "eval_samples_per_second": 2255.512,
+ "eval_steps_per_second": 141.903,
+ "step": 456
+ },
+ {
+ "epoch": 6.58,
+ "learning_rate": 1.1776315789473684e-05,
+ "loss": 0.1883,
+ "step": 500
+ },
+ {
+ "epoch": 7.0,
+ "eval_accuracy": 0.9768211920529801,
+ "eval_loss": 0.10020075738430023,
+ "eval_runtime": 0.145,
+ "eval_samples_per_second": 2083.04,
+ "eval_steps_per_second": 131.052,
+ "step": 532
+ },
+ {
+ "epoch": 8.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.116866335272789,
+ "eval_runtime": 0.1348,
+ "eval_samples_per_second": 2240.912,
+ "eval_steps_per_second": 140.985,
+ "step": 608
+ },
+ {
+ "epoch": 9.0,
+ "eval_accuracy": 0.9701986754966887,
+ "eval_loss": 0.14152054488658905,
+ "eval_runtime": 0.1308,
+ "eval_samples_per_second": 2309.736,
+ "eval_steps_per_second": 145.314,
+ "step": 684
+ },
+ {
+ "epoch": 10.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.1344088315963745,
+ "eval_runtime": 0.1195,
+ "eval_samples_per_second": 2526.256,
+ "eval_steps_per_second": 158.937,
+ "step": 760
+ },
+ {
+ "epoch": 11.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.13409321010112762,
+ "eval_runtime": 0.1399,
+ "eval_samples_per_second": 2159.267,
+ "eval_steps_per_second": 135.848,
+ "step": 836
+ },
+ {
+ "epoch": 12.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.12705937027931213,
+ "eval_runtime": 0.1366,
+ "eval_samples_per_second": 2210.321,
+ "eval_steps_per_second": 139.06,
+ "step": 912
+ },
+ {
+ "epoch": 13.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.13874845206737518,
+ "eval_runtime": 0.1374,
+ "eval_samples_per_second": 2197.254,
+ "eval_steps_per_second": 138.238,
+ "step": 988
+ },
+ {
+ "epoch": 13.16,
+ "learning_rate": 3.5526315789473687e-06,
+ "loss": 0.018,
+ "step": 1000
+ },
+ {
+ "epoch": 14.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.13716736435890198,
+ "eval_runtime": 0.1193,
+ "eval_samples_per_second": 2530.546,
+ "eval_steps_per_second": 159.207,
+ "step": 1064
+ },
+ {
+ "epoch": 15.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.13588877022266388,
+ "eval_runtime": 0.1396,
+ "eval_samples_per_second": 2163.789,
+ "eval_steps_per_second": 136.132,
+ "step": 1140
+ },
+ {
+ "epoch": 16.0,
+ "eval_accuracy": 0.9735099337748344,
+ "eval_loss": 0.13579562306404114,
+ "eval_runtime": 0.1288,
+ "eval_samples_per_second": 2345.226,
+ "eval_steps_per_second": 147.547,
+ "step": 1216
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 1216,
+ "num_train_epochs": 16,
+ "save_steps": 500,
+ "total_flos": 62384098266840.0,
+ "trial_name": null,
+ "trial_params": null
+}

intent_classification_model/{checkpoint-324 → checkpoint-1216}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27308f0087e544f12e1806abafb33d65745a5791fb1559d9e521f3670215df9
+oid sha256:40b975e2b309584fec6c9097bbbfc4736c3bbe492681259866398911daf0ae0c
 size 4536

intent_classification_model/checkpoint-1376/added_tokens.json

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

intent_classification_model/checkpoint-1376/config.json

@@ -0,0 +1,39 @@
+{
+ "_name_or_path": "distilbert-base-uncased",
+ "activation": "gelu",
+ "architectures": [
+ "DistilBertForSequenceClassification"
+ ],
+ "attention_dropout": 0.1,
+ "dim": 768,
+ "dropout": 0.1,
+ "hidden_dim": 3072,
+ "id2label": {
+ "0": "Commercial",
+ "1": "Informational",
+ "2": "Navigational",
+ "3": "Local",
+ "4": "Transactional"
+ },
+ "initializer_range": 0.02,
+ "label2id": {
+ "Commercial": 0,
+ "Informational": 1,
+ "Local": 3,
+ "Navigational": 2,
+ "Transactional": 4
+ },
+ "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
+}

intent_classification_model/checkpoint-1376/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2ed586c32f48dd2cece37baf89590cc951fda221ec175eadd3034e996abe25
+size 535745722

intent_classification_model/checkpoint-1376/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153cb325de818e493f8a0a7aa1fbcc5cf3d8fa27d07339fbfd1d8e238d8cb38b
+size 267865194

intent_classification_model/checkpoint-1376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c80c9f7b843dea09bd3b8739eafa7b84f67f346b13150be7548d804af238e2c
+size 1064

intent_classification_model/checkpoint-1376/special_tokens_map.json

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

intent_classification_model/checkpoint-1376/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]"
+}

intent_classification_model/checkpoint-1376/trainer_state.json

@@ -0,0 +1,175 @@
+{
+ "best_metric": 0.10133440792560577,
+ "best_model_checkpoint": "intent_classification_model/checkpoint-344",
+ "epoch": 16.0,
+ "eval_steps": 500,
+ "global_step": 1376,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.956140350877193,
+ "eval_loss": 0.24781915545463562,
+ "eval_runtime": 0.1669,
+ "eval_samples_per_second": 2049.176,
+ "eval_steps_per_second": 131.818,
+ "step": 86
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.9766081871345029,
+ "eval_loss": 0.10303749144077301,
+ "eval_runtime": 0.2792,
+ "eval_samples_per_second": 1224.804,
+ "eval_steps_per_second": 78.789,
+ "step": 172
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.12486349791288376,
+ "eval_runtime": 0.1527,
+ "eval_samples_per_second": 2239.207,
+ "eval_steps_per_second": 144.043,
+ "step": 258
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.9766081871345029,
+ "eval_loss": 0.10133440792560577,
+ "eval_runtime": 0.1513,
+ "eval_samples_per_second": 2260.581,
+ "eval_steps_per_second": 145.418,
+ "step": 344
+ },
+ {
+ "epoch": 5.0,
+ "eval_accuracy": 0.9766081871345029,
+ "eval_loss": 0.11906354874372482,
+ "eval_runtime": 0.1397,
+ "eval_samples_per_second": 2448.535,
+ "eval_steps_per_second": 157.508,
+ "step": 430
+ },
+ {
+ "epoch": 5.81,
+ "learning_rate": 1.2732558139534886e-05,
+ "loss": 0.1903,
+ "step": 500
+ },
+ {
+ "epoch": 6.0,
+ "eval_accuracy": 0.9678362573099415,
+ "eval_loss": 0.14922283589839935,
+ "eval_runtime": 0.1511,
+ "eval_samples_per_second": 2264.082,
+ "eval_steps_per_second": 145.643,
+ "step": 516
+ },
+ {
+ "epoch": 7.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.10685376077890396,
+ "eval_runtime": 0.1562,
+ "eval_samples_per_second": 2189.014,
+ "eval_steps_per_second": 140.814,
+ "step": 602
+ },
+ {
+ "epoch": 8.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.12596090137958527,
+ "eval_runtime": 0.1543,
+ "eval_samples_per_second": 2216.873,
+ "eval_steps_per_second": 142.606,
+ "step": 688
+ },
+ {
+ "epoch": 9.0,
+ "eval_accuracy": 0.9707602339181286,
+ "eval_loss": 0.129041388630867,
+ "eval_runtime": 0.1334,
+ "eval_samples_per_second": 2563.696,
+ "eval_steps_per_second": 164.916,
+ "step": 774
+ },
+ {
+ "epoch": 10.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.12375017255544662,
+ "eval_runtime": 0.1513,
+ "eval_samples_per_second": 2261.041,
+ "eval_steps_per_second": 145.447,
+ "step": 860
+ },
+ {
+ "epoch": 11.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.12813875079154968,
+ "eval_runtime": 0.1546,
+ "eval_samples_per_second": 2212.042,
+ "eval_steps_per_second": 142.295,
+ "step": 946
+ },
+ {
+ "epoch": 11.63,
+ "learning_rate": 5.465116279069767e-06,
+ "loss": 0.0258,
+ "step": 1000
+ },
+ {
+ "epoch": 12.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.13388033211231232,
+ "eval_runtime": 0.1607,
+ "eval_samples_per_second": 2128.444,
+ "eval_steps_per_second": 136.917,
+ "step": 1032
+ },
+ {
+ "epoch": 13.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.1308409869670868,
+ "eval_runtime": 0.1401,
+ "eval_samples_per_second": 2441.546,
+ "eval_steps_per_second": 157.058,
+ "step": 1118
+ },
+ {
+ "epoch": 14.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.13211463391780853,
+ "eval_runtime": 0.1539,
+ "eval_samples_per_second": 2222.296,
+ "eval_steps_per_second": 142.955,
+ "step": 1204
+ },
+ {
+ "epoch": 15.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.13366281986236572,
+ "eval_runtime": 0.1507,
+ "eval_samples_per_second": 2269.433,
+ "eval_steps_per_second": 145.987,
+ "step": 1290
+ },
+ {
+ "epoch": 16.0,
+ "eval_accuracy": 0.9736842105263158,
+ "eval_loss": 0.13524049520492554,
+ "eval_runtime": 0.1603,
+ "eval_samples_per_second": 2133.42,
+ "eval_steps_per_second": 137.238,
+ "step": 1376
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 1376,
+ "num_train_epochs": 16,
+ "save_steps": 500,
+ "total_flos": 70181981180580.0,
+ "trial_name": null,
+ "trial_params": null
+}

intent_classification_model/checkpoint-1376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b92fcfbb60dcd18505e69a8641e67a12b1dbb1bb4cf8cf1817bb473e3ed0dc
+size 4536

intent_classification_model/checkpoint-324/trainer_state.json

@@ -1,73 +0,0 @@
-{
- "best_metric": 0.16397738456726074,
- "best_model_checkpoint": "intent_classification_model/checkpoint-270",
- "epoch": 6.0,
- "eval_steps": 500,
- "global_step": 324,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "epoch": 1.0,
- "eval_accuracy": 0.9488372093023256,
- "eval_loss": 0.4676927328109741,
- "eval_runtime": 0.1185,
- "eval_samples_per_second": 1814.083,
- "eval_steps_per_second": 118.126,
- "step": 54
- },
- {
- "epoch": 2.0,
- "eval_accuracy": 0.9534883720930233,
- "eval_loss": 0.20428764820098877,
- "eval_runtime": 0.0972,
- "eval_samples_per_second": 2210.83,
- "eval_steps_per_second": 143.961,
- "step": 108
- },
- {
- "epoch": 3.0,
- "eval_accuracy": 0.9674418604651163,
- "eval_loss": 0.16401757299900055,
- "eval_runtime": 0.1015,
- "eval_samples_per_second": 2118.828,
- "eval_steps_per_second": 137.97,
- "step": 162
- },
- {
- "epoch": 4.0,
- "eval_accuracy": 0.9674418604651163,
- "eval_loss": 0.16496841609477997,
- "eval_runtime": 0.0941,
- "eval_samples_per_second": 2284.398,
- "eval_steps_per_second": 148.752,
- "step": 216
- },
- {
- "epoch": 5.0,
- "eval_accuracy": 0.9674418604651163,
- "eval_loss": 0.16397738456726074,
- "eval_runtime": 0.0975,
- "eval_samples_per_second": 2204.851,
- "eval_steps_per_second": 143.572,
- "step": 270
- },
- {
- "epoch": 6.0,
- "eval_accuracy": 0.9674418604651163,
- "eval_loss": 0.16553252935409546,
- "eval_runtime": 0.0947,
- "eval_samples_per_second": 2271.063,
- "eval_steps_per_second": 147.883,
- "step": 324
- }
- ],
- "logging_steps": 500,
- "max_steps": 324,
- "num_train_epochs": 6,
- "save_steps": 500,
- "total_flos": 13032177536640.0,
- "trial_name": null,
- "trial_params": null
-}

research/09_fine_tuning_for_datacategories.ipynb

@@ -62,93 +62,93 @@
  " </thead>\n",
  " <tbody>\n",
  " <tr>\n",
- " <th>22910</th>\n",
- " <td>Retirement income streams explanation</td>\n",
- " <td>Finance</td>\n",
- " <td>18</td>\n",
+ " <th>3982</th>\n",
+ " <td>Citation context relevance assessment platforms</td>\n",
+ " <td>Reference</td>\n",
+ " <td>12</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>3202</th>\n",
- " <td>Social justice strategies</td>\n",
- " <td>People_and_Society</td>\n",
- " <td>10</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>23191</th>\n",
- " <td>Nanomaterials engineering</td>\n",
+ " <th>24651</th>\n",
+ " <td>Geology fieldwork</td>\n",
  " <td>Science</td>\n",
  " <td>2</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>25025</th>\n",
- " <td>Acrylic nails</td>\n",
- " <td>Beauty_and_Fitness</td>\n",
- " <td>9</td>\n",
+ " <th>28113</th>\n",
+ " <td>Password management for individuals</td>\n",
+ " <td>Computers_and_Electronics</td>\n",
+ " <td>7</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>14018</th>\n",
- " <td>Substance abuse recovery strategies</td>\n",
- " <td>People_and_Society</td>\n",
- " <td>10</td>\n",
+ " <th>10999</th>\n",
+ " <td>Real estate market statistics</td>\n",
+ " <td>Real Estate</td>\n",
+ " <td>24</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>30887</th>\n",
- " <td>Facebook privacy</td>\n",
- " <td>Online Communities</td>\n",
- " <td>8</td>\n",
+ " <th>17096</th>\n",
+ " <td>Running gear for women</td>\n",
+ " <td>Beauty_and_Fitness</td>\n",
+ " <td>9</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>5716</th>\n",
- " <td>disability</td>\n",
- " <td>Sensitive Subjects</td>\n",
- " <td>23</td>\n",
+ " <th>2374</th>\n",
+ " <td>Sports Team Fan Pride</td>\n",
+ " <td>Sports</td>\n",
+ " <td>26</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>25854</th>\n",
- " <td>Zumba dance fitness</td>\n",
- " <td>Beauty_and_Fitness</td>\n",
- " <td>9</td>\n",
+ " <th>9932</th>\n",
+ " <td>Wine and food events</td>\n",
+ " <td>Food_and_Drink</td>\n",
+ " <td>15</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>25032</th>\n",
- " <td>Enjoy dick porn</td>\n",
- " <td>Adult</td>\n",
- " <td>6</td>\n",
+ " <th>2953</th>\n",
+ " <td>College admissions for aspiring dancers</td>\n",
+ " <td>Jobs_and_Education</td>\n",
+ " <td>21</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>2008</th>\n",
- " <td>iPhone Face ID</td>\n",
- " <td>Computers_and_Electronics</td>\n",
- " <td>7</td>\n",
+ " <th>25038</th>\n",
+ " <td>Software development best practices forums</td>\n",
+ " <td>Online Communities</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29703</th>\n",
+ " <td>Quantum physics theories</td>\n",
+ " <td>Science</td>\n",
+ " <td>2</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table>\n",
  "</div>"
  ],
  "text/plain": [
- " category label \\\n",
- "22910 Retirement income streams explanation Finance \n",
- "3202 Social justice strategies People_and_Society \n",
- "23191 Nanomaterials engineering Science \n",
- "25025 Acrylic nails Beauty_and_Fitness \n",
- "14018 Substance abuse recovery strategies People_and_Society \n",
- "30887 Facebook privacy Online Communities \n",
- "5716 disability Sensitive Subjects \n",
- "25854 Zumba dance fitness Beauty_and_Fitness \n",
- "25032 Enjoy dick porn Adult \n",
- "2008 iPhone Face ID Computers_and_Electronics \n",
+ " category \\\n",
+ "3982 Citation context relevance assessment platforms \n",
+ "24651 Geology fieldwork \n",
+ "28113 Password management for individuals \n",
+ "10999 Real estate market statistics \n",
+ "17096 Running gear for women \n",
+ "2374 Sports Team Fan Pride \n",
+ "9932 Wine and food events \n",
+ "2953 College admissions for aspiring dancers \n",
+ "25038 Software development best practices forums \n",
+ "29703 Quantum physics theories \n",
  "\n",
- " label_id \n",
- "22910 18 \n",
- "3202 10 \n",
- "23191 2 \n",
- "25025 9 \n",
- "14018 10 \n",
- "30887 8 \n",
- "5716 23 \n",
- "25854 9 \n",
- "25032 6 \n",
- "2008 7 "
+ " label label_id \n",
+ "3982 Reference 12 \n",
+ "24651 Science 2 \n",
+ "28113 Computers_and_Electronics 7 \n",
+ "10999 Real Estate 24 \n",
+ "17096 Beauty_and_Fitness 9 \n",
+ "2374 Sports 26 \n",
+ "9932 Food_and_Drink 15 \n",
+ "2953 Jobs_and_Education 21 \n",
+ "25038 Online Communities 8 \n",
+ "29703 Science 2 "
  ]
  },
  "execution_count": 3,
@@ -273,7 +273,7 @@
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "/tmp/ipykernel_129502/984288843.py:1: SettingWithCopyWarning: \n",
+ "/tmp/ipykernel_139501/984288843.py:1: SettingWithCopyWarning: \n",
  "A value is trying to be set on a copy of a slice from a DataFrame\n",
  "\n",
  "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@@ -307,71 +307,71 @@
  " </thead>\n",
  " <tbody>\n",
  " <tr>\n",
- " <th>7152</th>\n",
- " <td>Social justice strategies</td>\n",
- " <td>10</td>\n",
+ " <th>2925</th>\n",
+ " <td>Kids' toy stores online</td>\n",
+ " <td>13</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>31780</th>\n",
- " <td>LinkedIn job search for food writing organizat...</td>\n",
- " <td>21</td>\n",
+ " <th>31108</th>\n",
+ " <td>Birdwatching apps for bird behavior</td>\n",
+ " <td>5</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>20244</th>\n",
- " <td>Nobel Prize in Literature news</td>\n",
+ " <th>6817</th>\n",
+ " <td>Legal developments</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>16634</th>\n",
- " <td>Job search for people with public health impai...</td>\n",
- " <td>21</td>\n",
+ " <th>20037</th>\n",
+ " <td>Citation context relevance assessment tools</td>\n",
+ " <td>12</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>8603</th>\n",
- " <td>Car insurance for luxury cars</td>\n",
- " <td>3</td>\n",
+ " <th>18928</th>\n",
+ " <td>Orchid care guide</td>\n",
+ " <td>20</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>30042</th>\n",
- " <td>Personal development and self-help techniques ...</td>\n",
- " <td>8</td>\n",
+ " <th>33358</th>\n",
+ " <td>Scientific publications and journals</td>\n",
+ " <td>2</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>9345</th>\n",
- " <td>Smartwatch features</td>\n",
- " <td>7</td>\n",
+ " <th>16499</th>\n",
+ " <td>Service dog etiquette</td>\n",
+ " <td>5</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>19660</th>\n",
- " <td>Travel deals for beachfront chalets</td>\n",
- " <td>14</td>\n",
+ " <th>26484</th>\n",
+ " <td>Social media trends analysis</td>\n",
+ " <td>25</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>27349</th>\n",
- " <td>Choosing energy-efficient HVAC</td>\n",
- " <td>20</td>\n",
+ " <th>15543</th>\n",
+ " <td>Troubleshooting computer issues</td>\n",
+ " <td>7</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>12660</th>\n",
- " <td>Advocacy for native land rights</td>\n",
- " <td>10</td>\n",
+ " <th>15854</th>\n",
+ " <td>large</td>\n",
+ " <td>23</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table>\n",
  "</div>"
  ],
  "text/plain": [
- " text label\n",
- "7152 Social justice strategies 10\n",
- "31780 LinkedIn job search for food writing organizat... 21\n",
- "20244 Nobel Prize in Literature news 1\n",
- "16634 Job search for people with public health impai... 21\n",
- "8603 Car insurance for luxury cars 3\n",
- "30042 Personal development and self-help techniques ... 8\n",
- "9345 Smartwatch features 7\n",
- "19660 Travel deals for beachfront chalets 14\n",
- "27349 Choosing energy-efficient HVAC 20\n",
- "12660 Advocacy for native land rights 10"
+ " text label\n",
+ "2925 Kids' toy stores online 13\n",
+ "31108 Birdwatching apps for bird behavior 5\n",
+ "6817 Legal developments 1\n",
+ "20037 Citation context relevance assessment tools 12\n",
+ "18928 Orchid care guide 20\n",
+ "33358 Scientific publications and journals 2\n",
+ "16499 Service dog etiquette 5\n",
+ "26484 Social media trends analysis 25\n",
+ "15543 Troubleshooting computer issues 7\n",
+ "15854 large 23"
  ]
  },
  "execution_count": 6,
@@ -483,8 +483,15 @@
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "Map: 100%|██████████| 26889/26889 [00:00<00:00, 33262.24 examples/s]\n",
- "Map: 100%|██████████| 6723/6723 [00:00<00:00, 42992.17 examples/s]\n"
+ "Map: 48%|████▊ | 13000/26889 [00:00<00:00, 32226.42 examples/s]"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Map: 100%|██████████| 26889/26889 [00:00<00:00, 34388.34 examples/s]\n",
+ "Map: 100%|██████████| 6723/6723 [00:00<00:00, 41978.69 examples/s]\n"
  ]
  }
  ],
@@ -501,9 +508,9 @@
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "2023-10-12 11:59:02.472987: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+ "2023-10-13 10:29:49.212220: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
  "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2023-10-12 11:59:03.211664: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
+ "2023-10-13 10:29:50.573292: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
  ]
  }
  ],
@@ -686,7 +693,7 @@
  " <div>\n",
  " \n",
  " <progress value='3362' max='3362' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
- " [3362/3362 01:46, Epoch 2/2]\n",
+ " [3362/3362 01:52, Epoch 2/2]\n",
  " </div>\n",
  " <table border=\"1\" class=\"dataframe\">\n",
  " <thead>\n",
@@ -700,15 +707,15 @@
  " <tbody>\n",
  " <tr>\n",
  " <td>1</td>\n",
- " <td>0.104100</td>\n",
- " <td>0.102964</td>\n",
- " <td>0.972185</td>\n",
+ " <td>0.102300</td>\n",
+ " <td>0.077652</td>\n",
+ " <td>0.975309</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>2</td>\n",
- " <td>0.077300</td>\n",
- " <td>0.110562</td>\n",
- " <td>0.970846</td>\n",
+ " <td>0.083400</td>\n",
+ " <td>0.086291</td>\n",
+ " <td>0.974714</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table><p>"
@@ -723,7 +730,7 @@
  {
  "data": {
  "text/plain": [
- "TrainOutput(global_step=3362, training_loss=0.08810693149691462, metrics={'train_runtime': 106.8757, 'train_samples_per_second': 503.183, 'train_steps_per_second': 31.457, 'total_flos': 216609059710134.0, 'train_loss': 0.08810693149691462, 'epoch': 2.0})"
+ "TrainOutput(global_step=3362, training_loss=0.08880683540376008, metrics={'train_runtime': 113.5357, 'train_samples_per_second': 473.666, 'train_steps_per_second': 29.612, 'total_flos': 213673546900476.0, 'train_loss': 0.08880683540376008, 'epoch': 2.0})"
  ]
  },
  "execution_count": 19,

research/11_evaluation.ipynb

@@ -13,7 +13,17 @@
  "cell_type": "code",
  "execution_count": 2,
  "metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/home/ubuntu/SentenceStructureComparision/venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+ " from .autonotebook import tqdm as notebook_tqdm\n",
+ "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
+ ]
+ }
+ ],
  "source": [
  "from utils.get_intent import get_top_intent"
  ]
@@ -26,11 +36,11 @@
  {
  "data": {
  "text/plain": [
- "[('Commercial', 0.969),\n",
- " ('Transactional', 0.673),\n",
- " ('Informational', 0.237),\n",
- " ('Navigational', 0.215),\n",
- " ('Local', 0.155)]"
+ "[('Commercial', 0.997),\n",
+ " ('Transactional', 0.199),\n",
+ " ('Local', 0.132),\n",
+ " ('Navigational', 0.099),\n",
+ " ('Informational', 0.088)]"
  ]
  },
  "execution_count": 3,
@@ -50,11 +60,11 @@
  {
  "data": {
  "text/plain": [
- "[('Transactional', 0.987),\n",
- " ('Navigational', 0.317),\n",
- " ('Commercial', 0.27),\n",
- " ('Informational', 0.249),\n",
- " ('Local', 0.229)]"
+ "[('Transactional', 0.996),\n",
+ " ('Commercial', 0.315),\n",
+ " ('Navigational', 0.149),\n",
+ " ('Local', 0.146),\n",
+ " ('Informational', 0.133)]"
  ]
  },
  "execution_count": 4,
@@ -74,11 +84,11 @@
  {
  "data": {
  "text/plain": [
- "[('Informational', 0.984),\n",
- " ('Local', 0.244),\n",
- " ('Commercial', 0.237),\n",
- " ('Transactional', 0.212),\n",
- " ('Navigational', 0.194)]"
+ "[('Informational', 0.999),\n",
+ " ('Transactional', 0.116),\n",
+ " ('Local', 0.094),\n",
+ " ('Commercial', 0.075),\n",
+ " ('Navigational', 0.075)]"
  ]
  },
  "execution_count": 5,
@@ -98,11 +108,11 @@
  {
  "data": {
  "text/plain": [
- "[('Local', 0.988),\n",
- " ('Informational', 0.3),\n",
- " ('Commercial', 0.278),\n",
- " ('Navigational', 0.273),\n",
- " ('Transactional', 0.234)]"
+ "[('Local', 0.997),\n",
+ " ('Commercial', 0.134),\n",
+ " ('Informational', 0.122),\n",
+ " ('Navigational', 0.121),\n",
+ " ('Transactional', 0.12)]"
  ]
  },
  "execution_count": 6,
@@ -122,11 +132,11 @@
  {
  "data": {
  "text/plain": [
- "[('Informational', 0.763),\n",
- " ('Navigational', 0.638),\n",
- " ('Transactional', 0.433),\n",
- " ('Commercial', 0.286),\n",
- " ('Local', 0.236)]"
+ "[('Informational', 0.892),\n",
+ " ('Transactional', 0.685),\n",
+ " ('Navigational', 0.533),\n",
+ " ('Commercial', 0.123),\n",
+ " ('Local', 0.072)]"
  ]
  },
  "execution_count": 7,
@@ -146,11 +156,11 @@
  {
  "data": {
  "text/plain": [
- "[('Navigational', 0.861),\n",
- " ('Transactional', 0.725),\n",
- " ('Local', 0.422),\n",
- " ('Commercial', 0.287),\n",
- " ('Informational', 0.202)]"
+ "[('Informational', 0.993),\n",
+ " ('Commercial', 0.183),\n",
+ " ('Transactional', 0.173),\n",
+ " ('Local', 0.123),\n",
+ " ('Navigational', 0.082)]"
  ]
  },
  "execution_count": 8,
@@ -170,11 +180,11 @@
  {
  "data": {
  "text/plain": [
- "[('Navigational', 0.983),\n",
- " ('Transactional', 0.27),\n",
- " ('Local', 0.23),\n",
- " ('Informational', 0.209),\n",
- " ('Commercial', 0.192)]"
+ "[('Navigational', 0.998),\n",
+ " ('Transactional', 0.271),\n",
+ " ('Local', 0.164),\n",
+ " ('Commercial', 0.134),\n",
+ " ('Informational', 0.129)]"
  ]
  },
  "execution_count": 9,
@@ -194,11 +204,11 @@
  {
  "data": {
  "text/plain": [
- "[('Navigational', 0.983),\n",
+ "[('Navigational', 0.998),\n",
  " ('Transactional', 0.256),\n",
- " ('Informational', 0.241),\n",
- " ('Local', 0.214),\n",
- " ('Commercial', 0.184)]"
+ " ('Local', 0.171),\n",
+ " ('Informational', 0.151),\n",
+ " ('Commercial', 0.127)]"
  ]
  },
  "execution_count": 10,
@@ -218,11 +228,11 @@
  {
  "data": {
  "text/plain": [
- "[('Local', 0.988),\n",
- " ('Informational', 0.294),\n",
- " ('Navigational', 0.284),\n",
- " ('Commercial', 0.252),\n",
- " ('Transactional', 0.235)]"
+ "[('Local', 0.997),\n",
+ " ('Commercial', 0.136),\n",
+ " ('Transactional', 0.124),\n",
+ " ('Informational', 0.119),\n",
+ " ('Navigational', 0.118)]"
  ]
  },
  "execution_count": 11,
@@ -242,11 +252,11 @@
  {
  "data": {
  "text/plain": [
- "[('Informational', 0.984),\n",
- " ('Local', 0.245),\n",
- " ('Commercial', 0.242),\n",
- " ('Transactional', 0.226),\n",
- " ('Navigational', 0.189)]"
+ "[('Informational', 0.999),\n",
+ " ('Transactional', 0.131),\n",
+ " ('Local', 0.09),\n",
+ " ('Commercial', 0.072),\n",
+ " ('Navigational', 0.069)]"
  ]
  },
  "execution_count": 12,
@@ -258,6 +268,204 @@
  "get_top_intent(\"how to wear headphones\")"
  ]
  },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Navigational', 0.997),\n",
+ " ('Transactional', 0.452),\n",
+ " ('Local', 0.127),\n",
+ " ('Informational', 0.126),\n",
+ " ('Commercial', 0.12)]"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent(\"receiptify\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Transactional', 0.995),\n",
+ " ('Commercial', 0.27),\n",
+ " ('Informational', 0.181),\n",
+ " ('Local', 0.162),\n",
+ " ('Navigational', 0.133)]"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent(\"cat ear headphones\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Transactional', 0.977),\n",
+ " ('Navigational', 0.808),\n",
+ " ('Commercial', 0.254),\n",
+ " ('Informational', 0.107),\n",
+ " ('Local', 0.081)]"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent(\"sony headphones guide\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Navigational', 0.949),\n",
+ " ('Transactional', 0.89),\n",
+ " ('Informational', 0.328),\n",
+ " ('Commercial', 0.113),\n",
+ " ('Local', 0.069)]"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent(\"wolf cut\") # informational"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Transactional', 0.996),\n",
+ " ('Commercial', 0.217),\n",
+ " ('Informational', 0.199),\n",
+ " ('Navigational', 0.17),\n",
+ " ('Local', 0.136)]"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent(\"help plumbing supply\") # informational"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Informational', 0.969),\n",
+ " ('Commercial', 0.677),\n",
+ " ('Transactional', 0.276),\n",
+ " ('Local', 0.071),\n",
+ " ('Navigational', 0.035)]"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_intent('yoga purpose') # informational"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os; os.chdir('..')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from utils.get_category import get_top_labels"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('Computers_and_Electronics', 1.0), ('Shopping', 0.182)]"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_top_labels(\n",
+ " \"best cat ear headphones\"\n",
+ ")"
+ ]
+ },
  {
  "cell_type": "code",
  "execution_count": null,

research/11_intent_classification_using_distilbert.ipynb

@@ -20,7 +20,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 3,
+ "execution_count": 10,
  "metadata": {},
  "outputs": [
  {
@@ -87,7 +87,7 @@
  "4 tech crunch Navigational"
  ]
  },
- "execution_count": 3,
+ "execution_count": 10,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -99,7 +99,59 @@
  },
  {
  "cell_type": "code",
- "execution_count": 4,
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "False 1506\n",
+ "True 202\n",
+ "Name: count, dtype: int64"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "original_df.duplicated().value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "original_df.drop_duplicates(inplace=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "False 1506\n",
+ "Name: count, dtype: int64"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "original_df.duplicated().value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -108,7 +160,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 5,
+ "execution_count": 20,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -121,7 +173,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 6,
+ "execution_count": 21,
  "metadata": {},
  "outputs": [
  {
@@ -134,7 +186,7 @@
  " 4: 'Transactional'}"
  ]
  },
- "execution_count": 6,
+ "execution_count": 21,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -145,7 +197,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 7,
+ "execution_count": 22,
  "metadata": {},
  "outputs": [
  {
@@ -158,7 +210,7 @@
  " 'Transactional': 4}"
  ]
  },
- "execution_count": 7,
+ "execution_count": 22,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -169,7 +221,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 8,
+ "execution_count": 23,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -179,7 +231,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 9,
+ "execution_count": 24,
  "metadata": {},
  "outputs": [
  {
@@ -246,58 +298,58 @@
  " <td>...</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1066</th>\n",
- " <td>How to make a paper flower?</td>\n",
+ " <th>1703</th>\n",
+ " <td>How to make homemade pet accessories from recy...</td>\n",
  " <td>Informational</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1067</th>\n",
- " <td>Why do some animals camouflage?</td>\n",
+ " <th>1704</th>\n",
+ " <td>Top 10 science fiction book series that take r...</td>\n",
  " <td>Informational</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1068</th>\n",
- " <td>What is the history of ancient civilizations?</td>\n",
+ " <th>1705</th>\n",
+ " <td>How to start a car restoration and customizati...</td>\n",
  " <td>Informational</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1069</th>\n",
- " <td>How to make a simple machine?</td>\n",
+ " <th>1706</th>\n",
+ " <td>Ancient Mesopotamian architecture and its infl...</td>\n",
  " <td>Informational</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1070</th>\n",
- " <td>Why do we see the phases of the moon?</td>\n",
+ " <th>1707</th>\n",
+ " <td>Benefits of a flexitarian diet for those seeki...</td>\n",
  " <td>Informational</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table>\n",
- "<p>1071 rows × 3 columns</p>\n",
+ "<p>1506 rows × 3 columns</p>\n",
  "</div>"
  ],
  "text/plain": [
- " keyword intent id\n",
- "0 citalopram vs prozac Commercial 0\n",
- "1 who is the oldest football player Informational 1\n",
- "2 t mobile town east Navigational 2\n",
- "3 starbucks Navigational 2\n",
- "4 tech crunch Navigational 2\n",
- "... ... ... ..\n",
- "1066 How to make a paper flower? Informational 1\n",
- "1067 Why do some animals camouflage? Informational 1\n",
- "1068 What is the history of ancient civilizations? Informational 1\n",
- "1069 How to make a simple machine? Informational 1\n",
- "1070 Why do we see the phases of the moon? Informational 1\n",
+ " keyword intent id\n",
+ "0 citalopram vs prozac Commercial 0\n",
+ "1 who is the oldest football player Informational 1\n",
+ "2 t mobile town east Navigational 2\n",
+ "3 starbucks Navigational 2\n",
+ "4 tech crunch Navigational 2\n",
+ "... ... ... ..\n",
+ "1703 How to make homemade pet accessories from recy... Informational 1\n",
+ "1704 Top 10 science fiction book series that take r... Informational 1\n",
+ "1705 How to start a car restoration and customizati... Informational 1\n",
+ "1706 Ancient Mesopotamian architecture and its infl... Informational 1\n",
+ "1707 Benefits of a flexitarian diet for those seeki... Informational 1\n",
  "\n",
- "[1071 rows x 3 columns]"
+ "[1506 rows x 3 columns]"
  ]
  },
- "execution_count": 9,
+ "execution_count": 24,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -309,7 +361,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 10,
+ "execution_count": 25,
  "metadata": {},
  "outputs": [
  {
@@ -369,53 +421,53 @@
  " <td>...</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1066</th>\n",
- " <td>How to make a paper flower?</td>\n",
+ " <th>1703</th>\n",
+ " <td>How to make homemade pet accessories from recy...</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1067</th>\n",
- " <td>Why do some animals camouflage?</td>\n",
+ " <th>1704</th>\n",
+ " <td>Top 10 science fiction book series that take r...</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1068</th>\n",
- " <td>What is the history of ancient civilizations?</td>\n",
+ " <th>1705</th>\n",
+ " <td>How to start a car restoration and customizati...</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1069</th>\n",
- " <td>How to make a simple machine?</td>\n",
+ " <th>1706</th>\n",
+ " <td>Ancient Mesopotamian architecture and its infl...</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>1070</th>\n",
- " <td>Why do we see the phases of the moon?</td>\n",
+ " <th>1707</th>\n",
+ " <td>Benefits of a flexitarian diet for those seeki...</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table>\n",
- "<p>1071 rows × 2 columns</p>\n",
+ "<p>1506 rows × 2 columns</p>\n",
  "</div>"
  ],
  "text/plain": [
- " keyword id\n",
- "0 citalopram vs prozac 0\n",
- "1 who is the oldest football player 1\n",
- "2 t mobile town east 2\n",
- "3 starbucks 2\n",
- "4 tech crunch 2\n",
- "... ... ..\n",
- "1066 How to make a paper flower? 1\n",
- "1067 Why do some animals camouflage? 1\n",
- "1068 What is the history of ancient civilizations? 1\n",
- "1069 How to make a simple machine? 1\n",
- "1070 Why do we see the phases of the moon? 1\n",
+ " keyword id\n",
+ "0 citalopram vs prozac 0\n",
+ "1 who is the oldest football player 1\n",
+ "2 t mobile town east 2\n",
+ "3 starbucks 2\n",
+ "4 tech crunch 2\n",
+ "... ... ..\n",
+ "1703 How to make homemade pet accessories from recy... 1\n",
+ "1704 Top 10 science fiction book series that take r... 1\n",
+ "1705 How to start a car restoration and customizati... 1\n",
+ "1706 Ancient Mesopotamian architecture and its infl... 1\n",
+ "1707 Benefits of a flexitarian diet for those seeki... 1\n",
  "\n",
- "[1071 rows x 2 columns]"
+ "[1506 rows x 2 columns]"
  ]
  },
- "execution_count": 10,
+ "execution_count": 25,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -427,7 +479,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 11,
+ "execution_count": 26,
  "metadata": {},
  "outputs": [
  {
@@ -445,14 +497,14 @@
  },
  {
  "cell_type": "code",
- "execution_count": 12,
+ "execution_count": 27,
  "metadata": {},
  "outputs": [
  {
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "/tmp/ipykernel_138160/1635098052.py:1: SettingWithCopyWarning: \n",
+ "/tmp/ipykernel_140238/1635098052.py:1: SettingWithCopyWarning: \n",
  "A value is trying to be set on a copy of a slice from a DataFrame\n",
  "\n",
  "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@@ -486,74 +538,74 @@
  " </thead>\n",
  " <tbody>\n",
  " <tr>\n",
- " <th>706</th>\n",
- " <td>Purchase DJ equipment</td>\n",
+ " <th>26</th>\n",
+ " <td>Iphone 13 prices</td>\n",
  " <td>4</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>24</th>\n",
- " <td>best headphones quora</td>\n",
- " <td>2</td>\n",
+ " <th>1604</th>\n",
+ " <td>Basics of string theory and its applications</td>\n",
+ " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>727</th>\n",
- " <td>Purchase fitness tracker</td>\n",
+ " <th>622</th>\n",
+ " <td>Purchase air purifier</td>\n",
  " <td>4</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>17</th>\n",
- " <td>facebook</td>\n",
- " <td>2</td>\n",
+ " <th>841</th>\n",
+ " <td>Art studios in Asheville</td>\n",
+ " <td>3</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>808</th>\n",
- " <td>Outdoor activities in Lake Tahoe</td>\n",
- " <td>3</td>\n",
+ " <th>1504</th>\n",
+ " <td>What is epigenetic inheritance?</td>\n",
+ " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>946</th>\n",
- " <td>Wine bars in Napa Valley</td>\n",
- " <td>3</td>\n",
+ " <th>311</th>\n",
+ " <td>Target Business login</td>\n",
+ " <td>2</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>944</th>\n",
- " <td>Art installations in Chicago</td>\n",
- " <td>3</td>\n",
+ " <th>61</th>\n",
+ " <td>How to get Spotify Premium</td>\n",
+ " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>899</th>\n",
- " <td>Snowboarding parks in Utah</td>\n",
- " <td>3</td>\n",
+ " <th>980</th>\n",
+ " <td>How to meditate?</td>\n",
+ " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>36</th>\n",
- " <td>Mission Immpossible</td>\n",
+ " <th>1428</th>\n",
+ " <td>Basics of black holes</td>\n",
  " <td>1</td>\n",
  " </tr>\n",
  " <tr>\n",
- " <th>129</th>\n",
- " <td>Instagram</td>\n",
- " <td>2</td>\n",
+ " <th>1266</th>\n",
+ " <td>Ancient Chinese dynasties</td>\n",
+ " <td>1</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table>\n",
  "</div>"
  ],
  "text/plain": [
- " text label\n",
- "706 Purchase DJ equipment 4\n",
- "24 best headphones quora 2\n",
- "727 Purchase fitness tracker 4\n",
- "17 facebook 2\n",
- "808 Outdoor activities in Lake Tahoe 3\n",
- "946 Wine bars in Napa Valley 3\n",
- "944 Art installations in Chicago 3\n",
- "899 Snowboarding parks in Utah 3\n",
- "36 Mission Immpossible 1\n",
- "129 Instagram 2"
+ " text label\n",
+ "26 Iphone 13 prices 4\n",
+ "1604 Basics of string theory and its applications 1\n",
+ "622 Purchase air purifier 4\n",
+ "841 Art studios in Asheville 3\n",
+ "1504 What is epigenetic inheritance? 1\n",
+ "311 Target Business login 2\n",
+ "61 How to get Spotify Premium 1\n",
+ "980 How to meditate? 1\n",
+ "1428 Basics of black holes 1\n",
+ "1266 Ancient Chinese dynasties 1"
  ]
  },
- "execution_count": 12,
+ "execution_count": 27,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -571,7 +623,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 13,
+ "execution_count": 28,
  "metadata": {},
  "outputs": [
  {
@@ -586,12 +638,12 @@
  "data": {
  "text/plain": [
  "Dataset({\n",
- " features: ['text', 'label'],\n",
- " num_rows: 1071\n",
+ " features: ['text', 'label', '__index_level_0__'],\n",
+ " num_rows: 1506\n",
  "})"
  ]
  },
- "execution_count": 13,
+ "execution_count": 28,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -603,7 +655,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 14,
+ "execution_count": 29,
  "metadata": {},
  "outputs": [
  {
@@ -611,17 +663,17 @@
  "text/plain": [
  "DatasetDict({\n",
  " train: Dataset({\n",
- " features: ['text', 'label'],\n",
- " num_rows: 856\n",
+ " features: ['text', 'label', '__index_level_0__'],\n",
+ " num_rows: 1204\n",
  " })\n",
  " test: Dataset({\n",
- " features: ['text', 'label'],\n",
- " num_rows: 215\n",
+ " features: ['text', 'label', '__index_level_0__'],\n",
+ " num_rows: 302\n",
  " })\n",
  "})"
  ]
  },
- "execution_count": 14,
+ "execution_count": 29,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -633,7 +685,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 15,
+ "execution_count": 30,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -644,7 +696,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 16,
+ "execution_count": 31,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -654,15 +706,15 @@
  },
  {
  "cell_type": "code",
- "execution_count": 17,
+ "execution_count": 32,
  "metadata": {},
  "outputs": [
  {
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "Map: 100%|██████████| 856/856 [00:00<00:00, 18779.12 examples/s]\n",
- "Map: 100%|██████████| 215/215 [00:00<00:00, 27520.84 examples/s]\n"
+ "Map: 100%|██████████| 1204/1204 [00:00<00:00, 14009.91 examples/s]\n",
+ "Map: 100%|██████████| 302/302 [00:00<00:00, 24935.62 examples/s]\n"
  ]
  }
  ],
@@ -672,16 +724,16 @@
  },
  {
  "cell_type": "code",
- "execution_count": 18,
+ "execution_count": 33,
  "metadata": {},
  "outputs": [
  {
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "2023-10-13 09:10:00.122326: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+ "2023-10-13 10:49:11.199157: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
  "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2023-10-13 09:10:01.611782: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
+ "2023-10-13 10:49:12.962522: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
  ]
  }
  ],
@@ -700,7 +752,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 19,
+ "execution_count": 34,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -711,7 +763,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 20,
+ "execution_count": 35,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -726,14 +778,14 @@
  },
  {
  "cell_type": "code",
- "execution_count": 21,
+ "execution_count": 36,
  "metadata": {},
  "outputs": [
  {
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
+ "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.bias', 'pre_classifier.weight', 'classifier.weight', 'pre_classifier.bias']\n",
  "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
  ]
  }
@@ -748,7 +800,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 22,
+ "execution_count": 37,
  "metadata": {},
  "outputs": [
  {
@@ -764,8 +816,8 @@
  "\n",
  " <div>\n",
  " \n",
- " <progress value='324' max='324' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
- " [324/324 00:39, Epoch 6/6]\n",
+ " <progress value='1216' max='1216' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [1216/1216 02:51, Epoch 16/16]\n",
  " </div>\n",
  " <table border=\"1\" class=\"dataframe\">\n",
  " <thead>\n",
@@ -780,38 +832,98 @@
  " <tr>\n",
  " <td>1</td>\n",
  " <td>No log</td>\n",
- " <td>0.467693</td>\n",
- " <td>0.948837</td>\n",
+ " <td>0.208865</td>\n",
+ " <td>0.986755</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>2</td>\n",
  " <td>No log</td>\n",
- " <td>0.204288</td>\n",
- " <td>0.953488</td>\n",
+ " <td>0.062759</td>\n",
+ " <td>0.983444</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>3</td>\n",
  " <td>No log</td>\n",
- " <td>0.164018</td>\n",
- " <td>0.967442</td>\n",
+ " <td>0.065099</td>\n",
+ " <td>0.986755</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>4</td>\n",
  " <td>No log</td>\n",
- " <td>0.164968</td>\n",
- " <td>0.967442</td>\n",
+ " <td>0.081124</td>\n",
+ " <td>0.976821</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>5</td>\n",
  " <td>No log</td>\n",
- " <td>0.163977</td>\n",
- " <td>0.967442</td>\n",
+ " <td>0.112577</td>\n",
+ " <td>0.970199</td>\n",
  " </tr>\n",
  " <tr>\n",
  " <td>6</td>\n",
  " <td>No log</td>\n",
- " <td>0.165533</td>\n",
- " <td>0.967442</td>\n",
+ " <td>0.111743</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>7</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.100201</td>\n",
+ " <td>0.976821</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>8</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.116866</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>9</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.141521</td>\n",
+ " <td>0.970199</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>10</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.134409</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>11</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.134093</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>12</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.127059</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>13</td>\n",
+ " <td>0.188300</td>\n",
+ " <td>0.138748</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>14</td>\n",
+ " <td>0.018000</td>\n",
+ " <td>0.137167</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>15</td>\n",
+ " <td>0.018000</td>\n",
+ " <td>0.135889</td>\n",
+ " <td>0.973510</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>16</td>\n",
+ " <td>0.018000</td>\n",
+ " <td>0.135796</td>\n",
+ " <td>0.973510</td>\n",
  " </tr>\n",
  " </tbody>\n",
  "</table><p>"
@@ -826,10 +938,10 @@
  {
  "data": {
  "text/plain": [
- "TrainOutput(global_step=324, training_loss=0.2842947171058184, metrics={'train_runtime': 40.8212, 'train_samples_per_second': 125.817, 'train_steps_per_second': 7.937, 'total_flos': 13032177536640.0, 'train_loss': 0.2842947171058184, 'epoch': 6.0})"
+ "TrainOutput(global_step=1216, training_loss=0.08689324734242339, metrics={'train_runtime': 172.7465, 'train_samples_per_second': 111.516, 'train_steps_per_second': 7.039, 'total_flos': 62384098266840.0, 'train_loss': 0.08689324734242339, 'epoch': 16.0})"
  ]
  },
- "execution_count": 22,
+ "execution_count": 37,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -840,7 +952,7 @@
  " learning_rate=2e-5,\n",
  " per_device_train_batch_size=16,\n",
  " per_device_eval_batch_size=16,\n",
- " num_train_epochs=6,\n",
+ " num_train_epochs=16,\n",
  " weight_decay=0.01,\n",
  " evaluation_strategy=\"epoch\",\n",
  " save_strategy=\"epoch\",\n",

research/12_text_analytics_using_azure.ipynb

@@ -0,0 +1,407 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ! pip install --upgrade azure-ai-textanalytics"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "key = \"198414c4d7e54bde91ec77bf776d5211\"\n",
+ "endpoint = \"https://new-entity.cognitiveservices.azure.com/\"\n",
+ "# endpoint = \"https://eastus.api.cognitive.microsoft.com/\"\n",
+ "\n",
+ "from azure.ai.textanalytics import TextAnalyticsClient\n",
+ "from azure.core.credentials import AzureKeyCredential\n",
+ "\n",
+ "# Authenticate the client using your key and endpoint \n",
+ "def authenticate_client():\n",
+ " ta_credential = AzureKeyCredential(key)\n",
+ " text_analytics_client = TextAnalyticsClient(\n",
+ " endpoint=endpoint, \n",
+ " credential=ta_credential)\n",
+ " return text_analytics_client\n",
+ "\n",
+ "client = authenticate_client()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Named Entities:\n",
+ "\n",
+ "\tText: \t razor kraken \tCategory: \t Organization \tSubCategory: \t None \n",
+ "\tConfidence Score: \t 0.54 \tLength: \t 12 \tOffset: \t 0 \n",
+ "\n",
+ "\tText: \t headphones \tCategory: \t Product \tSubCategory: \t None \n",
+ "\tConfidence Score: \t 0.5 \tLength: \t 10 \tOffset: \t 13 \n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "key = \"2fd114e7967a4da58854be231fd766a3\"\n",
+ "endpoint = \"https://entity-collection.cognitiveservices.azure.com/\"\n",
+ "# endpoint = \"https://eastus.api.cognitive.microsoft.com/\"\n",
+ "\n",
+ "from azure.ai.textanalytics import TextAnalyticsClient\n",
+ "from azure.core.credentials import AzureKeyCredential\n",
+ "\n",
+ "# Authenticate the client using your key and endpoint \n",
+ "def authenticate_client():\n",
+ " ta_credential = AzureKeyCredential(key)\n",
+ " text_analytics_client = TextAnalyticsClient(\n",
+ " endpoint=endpoint, \n",
+ " credential=ta_credential)\n",
+ " return text_analytics_client\n",
+ "\n",
+ "client = authenticate_client()\n",
+ "\n",
+ "# Example function for recognizing entities from text\n",
+ "def entity_recognition_example(client):\n",
+ "\n",
+ " try:\n",
+ " documents = [\"razor kraken headphones\"]\n",
+ " result = client.recognize_entities(documents = documents)[0]\n",
+ "\n",
+ " print(\"Named Entities:\\n\")\n",
+ " for entity in result.entities:\n",
+ " print(\"\\tText: \\t\", entity.text, \"\\tCategory: \\t\", entity.category, \"\\tSubCategory: \\t\", entity.subcategory,\n",
+ " \"\\n\\tConfidence Score: \\t\", round(entity.confidence_score, 2), \"\\tLength: \\t\", entity.length, \"\\tOffset: \\t\", entity.offset, \"\\n\")\n",
+ "\n",
+ " except Exception as err:\n",
+ " print(\"Encountered exception. {}\".format(err))\n",
+ "entity_recognition_example(client)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def replace_original_text(original_text:str):\n",
+ " try:\n",
+ " result = client.recognize_entities(documents = [original_text])[0]\n",
+ "\n",
+ " for entity in result.entities:\n",
+ " # print(\"\\tText: \\t\", entity.text, \"\\tCategory: \\t\", entity.category, \"\\tSubCategory: \\t\", entity.subcategory,\n",
+ " # \"\\n\\tConfidence Score: \\t\", round(entity.confidence_score, 2), \"\\tLength: \\t\", entity.length, \"\\tOffset: \\t\", entity.offset, \"\\n\")\n",
+ " original_text= original_text.replace(\n",
+ " entity.text, \n",
+ " entity.text+ f' ({entity.category}) '\n",
+ " )\n",
+ " return original_text\n",
+ "\n",
+ " except Exception as err:\n",
+ " \n",
+ " print(\"Encountered exception. {}\".format(err))\n",
+ " return original_text\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'best cat ear headphones (Product) '"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "replace_original_text(original_text=\"best cat ear headphones\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'Barack Obama (Person) in the White House (Location) '"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "replace_original_text(\n",
+ " 'Barack Obama in the White House'\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from azure.core.credentials import AzureKeyCredential\n",
+ "from azure.ai.textanalytics import TextAnalyticsClient\n",
+ "\n",
+ "credential = AzureKeyCredential(\"c8b849064d6649ea87cbd8fbbd39f708\")\n",
+ "text_analytics_client = TextAnalyticsClient(endpoint=\"https://entity-retrieval.cognitiveservices.azure.com/\", credential=credential)\n",
+ "# text_analytics_client = TextAnalyticsClient(endpoint=\"https://ktitji5.eastus.cognitiveservices.azure.com/\", credential=credential)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Get the endpoint for the Language service resource\n",
+ "# ! az cognitiveservices account show --name \"resource-name\" --resource-group \"resource-group-name\" --query \"properties.endpoint\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "documents = [\n",
+ " {\"id\": \"1\", \"language\": \"en\", \"text\": \"I hated the movie. It was so slow!\"},\n",
+ " {\"id\": \"2\", \"language\": \"en\", \"text\": \"The movie made it into my top ten favorites. What a great movie!\"},\n",
+ "]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ClientAuthenticationError",
+ "evalue": "(401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m Traceback (most recent call last)",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_text_analytics_client.py:991\u001b[0m, in \u001b[0;36mTextAnalyticsClient.analyze_sentiment\u001b[0;34m(self, documents, **kwargs)\u001b[0m\n\u001b[1;32m 988\u001b[0m models \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_client\u001b[39m.\u001b[39mmodels(api_version\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_api_version)\n\u001b[1;32m 989\u001b[0m \u001b[39mreturn\u001b[39;00m cast(\n\u001b[1;32m 990\u001b[0m List[Union[AnalyzeSentimentResult, DocumentError]],\n\u001b[0;32m--> 991\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_client\u001b[39m.\u001b[39;49manalyze_text(\n\u001b[1;32m 992\u001b[0m body\u001b[39m=\u001b[39;49mmodels\u001b[39m.\u001b[39;49mAnalyzeTextSentimentAnalysisInput(\n\u001b[1;32m 993\u001b[0m analysis_input\u001b[39m=\u001b[39;49m{\u001b[39m\"\u001b[39;49m\u001b[39mdocuments\u001b[39;49m\u001b[39m\"\u001b[39;49m: docs},\n\u001b[1;32m 994\u001b[0m parameters\u001b[39m=\u001b[39;49mmodels\u001b[39m.\u001b[39;49mSentimentAnalysisTaskParameters(\n\u001b[1;32m 995\u001b[0m logging_opt_out\u001b[39m=\u001b[39;49mdisable_service_logs,\n\u001b[1;32m 996\u001b[0m model_version\u001b[39m=\u001b[39;49mmodel_version,\n\u001b[1;32m 997\u001b[0m string_index_type\u001b[39m=\u001b[39;49mstring_index_type_compatibility(string_index_type),\n\u001b[1;32m 998\u001b[0m opinion_mining\u001b[39m=\u001b[39;49mshow_opinion_mining,\n\u001b[1;32m 999\u001b[0m )\n\u001b[1;32m 1000\u001b[0m ),\n\u001b[1;32m 1001\u001b[0m show_stats\u001b[39m=\u001b[39;49mshow_stats,\n\u001b[1;32m 1002\u001b[0m \u001b[39mcls\u001b[39;49m\u001b[39m=\u001b[39;49mkwargs\u001b[39m.\u001b[39;49mpop(\u001b[39m\"\u001b[39;49m\u001b[39mcls\u001b[39;49m\u001b[39m\"\u001b[39;49m, sentiment_result),\n\u001b[1;32m 1003\u001b[0m \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs\n\u001b[1;32m 1004\u001b[0m )\n\u001b[1;32m 1005\u001b[0m )\n\u001b[1;32m 1007\u001b[0m \u001b[39m# api_versions 3.0, 3.1\u001b[39;00m\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_generated/_operations_mixin.py:109\u001b[0m, in \u001b[0;36mTextAnalyticsClientOperationsMixin.analyze_text\u001b[0;34m(self, body, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 108\u001b[0m mixin_instance\u001b[39m.\u001b[39m_deserialize \u001b[39m=\u001b[39m Deserializer(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_models_dict(api_version))\n\u001b[0;32m--> 109\u001b[0m \u001b[39mreturn\u001b[39;00m mixin_instance\u001b[39m.\u001b[39;49manalyze_text(body, show_stats, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/tracing/decorator.py:78\u001b[0m, in \u001b[0;36mdistributed_trace.<locals>.decorator.<locals>.wrapper_use_tracer\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 77\u001b[0m \u001b[39mif\u001b[39;00m span_impl_type \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m---> 78\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 80\u001b[0m \u001b[39m# Merge span is parameter is set, but only if no explicit parent are passed\u001b[39;00m\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_generated/v2022_05_01/operations/_text_analytics_client_operations.py:299\u001b[0m, in \u001b[0;36mTextAnalyticsClientOperationsMixin.analyze_text\u001b[0;34m(self, body, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 298\u001b[0m \u001b[39mif\u001b[39;00m response\u001b[39m.\u001b[39mstatus_code \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m [\u001b[39m200\u001b[39m]:\n\u001b[0;32m--> 299\u001b[0m map_error(status_code\u001b[39m=\u001b[39;49mresponse\u001b[39m.\u001b[39;49mstatus_code, response\u001b[39m=\u001b[39;49mresponse, error_map\u001b[39m=\u001b[39;49merror_map)\n\u001b[1;32m 300\u001b[0m error \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_deserialize\u001b[39m.\u001b[39mfailsafe_deserialize(_models\u001b[39m.\u001b[39mErrorResponse, pipeline_response)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/exceptions.py:165\u001b[0m, in \u001b[0;36mmap_error\u001b[0;34m(status_code, response, error_map)\u001b[0m\n\u001b[1;32m 164\u001b[0m error \u001b[39m=\u001b[39m error_type(response\u001b[39m=\u001b[39mresponse)\n\u001b[0;32m--> 165\u001b[0m \u001b[39mraise\u001b[39;00m error\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m: (401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.",
+ "\nThe above exception was the direct cause of the following exception:\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb Cell 12\u001b[0m line \u001b[0;36m1\n\u001b[0;32m----> <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=0'>1</a>\u001b[0m response \u001b[39m=\u001b[39m text_analytics_client\u001b[39m.\u001b[39;49manalyze_sentiment(documents)\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=1'>2</a>\u001b[0m successful_responses \u001b[39m=\u001b[39m [doc \u001b[39mfor\u001b[39;00m doc \u001b[39min\u001b[39;00m response \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m doc\u001b[39m.\u001b[39mis_error]\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/tracing/decorator.py:78\u001b[0m, in \u001b[0;36mdistributed_trace.<locals>.decorator.<locals>.wrapper_use_tracer\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 76\u001b[0m span_impl_type \u001b[39m=\u001b[39m settings\u001b[39m.\u001b[39mtracing_implementation()\n\u001b[1;32m 77\u001b[0m \u001b[39mif\u001b[39;00m span_impl_type \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m---> 78\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 80\u001b[0m \u001b[39m# Merge span is parameter is set, but only if no explicit parent are passed\u001b[39;00m\n\u001b[1;32m 81\u001b[0m \u001b[39mif\u001b[39;00m merge_span \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m passed_in_parent:\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_validate.py:74\u001b[0m, in \u001b[0;36mvalidate_multiapi_args.<locals>.decorator.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 72\u001b[0m \u001b[39m# the latest version is selected, we assume all features supported\u001b[39;00m\n\u001b[1;32m 73\u001b[0m \u001b[39mif\u001b[39;00m selected_api_version \u001b[39m==\u001b[39m VERSIONS_SUPPORTED[\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m]:\n\u001b[0;32m---> 74\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 76\u001b[0m \u001b[39mif\u001b[39;00m version_method_added \u001b[39mand\u001b[39;00m version_method_added \u001b[39m!=\u001b[39m selected_api_version \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m 77\u001b[0m VERSIONS_SUPPORTED\u001b[39m.\u001b[39mindex(selected_api_version) \u001b[39m<\u001b[39m VERSIONS_SUPPORTED\u001b[39m.\u001b[39mindex(version_method_added):\n\u001b[1;32m 78\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m 79\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m'\u001b[39m\u001b[39m{\u001b[39;00mclient\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m{\u001b[39;00mfunc\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m'\u001b[39m\u001b[39m is not available in API version \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 80\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mselected_api_version\u001b[39m}\u001b[39;00m\u001b[39m. Use service API version \u001b[39m\u001b[39m{\u001b[39;00mversion_method_added\u001b[39m}\u001b[39;00m\u001b[39m or newer.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 81\u001b[0m )\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_text_analytics_client.py:1022\u001b[0m, in \u001b[0;36mTextAnalyticsClient.analyze_sentiment\u001b[0;34m(self, documents, **kwargs)\u001b[0m\n\u001b[1;32m 1008\u001b[0m \u001b[39mreturn\u001b[39;00m cast(\n\u001b[1;32m 1009\u001b[0m List[Union[AnalyzeSentimentResult, DocumentError]],\n\u001b[1;32m 1010\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_client\u001b[39m.\u001b[39msentiment(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1019\u001b[0m )\n\u001b[1;32m 1020\u001b[0m )\n\u001b[1;32m 1021\u001b[0m \u001b[39mexcept\u001b[39;00m HttpResponseError \u001b[39mas\u001b[39;00m error:\n\u001b[0;32m-> 1022\u001b[0m \u001b[39mreturn\u001b[39;00m process_http_response_error(error)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_response_handlers.py:60\u001b[0m, in \u001b[0;36mprocess_http_response_error\u001b[0;34m(error)\u001b[0m\n\u001b[1;32m 58\u001b[0m \u001b[39mif\u001b[39;00m error\u001b[39m.\u001b[39mstatus_code \u001b[39m==\u001b[39m \u001b[39m404\u001b[39m:\n\u001b[1;32m 59\u001b[0m raise_error \u001b[39m=\u001b[39m ResourceNotFoundError\n\u001b[0;32m---> 60\u001b[0m \u001b[39mraise\u001b[39;00m raise_error(response\u001b[39m=\u001b[39merror\u001b[39m.\u001b[39mresponse, error_format\u001b[39m=\u001b[39mCSODataV4Format) \u001b[39mfrom\u001b[39;00m \u001b[39merror\u001b[39;00m\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m: (401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource."
+ ]
+ }
+ ],
+ "source": [
+ "response = text_analytics_client.analyze_sentiment(documents)\n",
+ "successful_responses = [doc for doc in response if not doc.is_error]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "In this sample, we want to find the articles that mention Microsoft to read.\n"
+ ]
+ },
+ {
+ "ename": "ClientAuthenticationError",
+ "evalue": "(401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m Traceback (most recent call last)",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_text_analytics_client.py:900\u001b[0m, in \u001b[0;36mTextAnalyticsClient.extract_key_phrases\u001b[0;34m(self, documents, disable_service_logs, language, model_version, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 897\u001b[0m models \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_client\u001b[39m.\u001b[39mmodels(api_version\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_api_version)\n\u001b[1;32m 898\u001b[0m \u001b[39mreturn\u001b[39;00m cast(\n\u001b[1;32m 899\u001b[0m List[Union[ExtractKeyPhrasesResult, DocumentError]],\n\u001b[0;32m--> 900\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_client\u001b[39m.\u001b[39;49manalyze_text(\n\u001b[1;32m 901\u001b[0m body\u001b[39m=\u001b[39;49mmodels\u001b[39m.\u001b[39;49mAnalyzeTextKeyPhraseExtractionInput(\n\u001b[1;32m 902\u001b[0m analysis_input\u001b[39m=\u001b[39;49m{\u001b[39m\"\u001b[39;49m\u001b[39mdocuments\u001b[39;49m\u001b[39m\"\u001b[39;49m: docs},\n\u001b[1;32m 903\u001b[0m parameters\u001b[39m=\u001b[39;49mmodels\u001b[39m.\u001b[39;49mKeyPhraseTaskParameters(\n\u001b[1;32m 904\u001b[0m logging_opt_out\u001b[39m=\u001b[39;49mdisable_service_logs,\n\u001b[1;32m 905\u001b[0m model_version\u001b[39m=\u001b[39;49mmodel_version,\n\u001b[1;32m 906\u001b[0m )\n\u001b[1;32m 907\u001b[0m ),\n\u001b[1;32m 908\u001b[0m show_stats\u001b[39m=\u001b[39;49mshow_stats,\n\u001b[1;32m 909\u001b[0m \u001b[39mcls\u001b[39;49m\u001b[39m=\u001b[39;49mkwargs\u001b[39m.\u001b[39;49mpop(\u001b[39m\"\u001b[39;49m\u001b[39mcls\u001b[39;49m\u001b[39m\"\u001b[39;49m, key_phrases_result),\n\u001b[1;32m 910\u001b[0m \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs\n\u001b[1;32m 911\u001b[0m )\n\u001b[1;32m 912\u001b[0m )\n\u001b[1;32m 914\u001b[0m \u001b[39m# api_versions 3.0, 3.1\u001b[39;00m\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_generated/_operations_mixin.py:111\u001b[0m, in \u001b[0;36mTextAnalyticsClientOperationsMixin.analyze_text\u001b[0;34m(self, body, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 110\u001b[0m mixin_instance\u001b[39m.\u001b[39m_deserialize \u001b[39m=\u001b[39m Deserializer(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_models_dict(api_version))\n\u001b[0;32m--> 111\u001b[0m \u001b[39mreturn\u001b[39;00m mixin_instance\u001b[39m.\u001b[39;49manalyze_text(body, show_stats, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/tracing/decorator.py:78\u001b[0m, in \u001b[0;36mdistributed_trace.<locals>.decorator.<locals>.wrapper_use_tracer\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 77\u001b[0m \u001b[39mif\u001b[39;00m span_impl_type \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m---> 78\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 80\u001b[0m \u001b[39m# Merge span is parameter is set, but only if no explicit parent are passed\u001b[39;00m\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_generated/v2023_04_01/operations/_text_analytics_client_operations.py:299\u001b[0m, in \u001b[0;36mTextAnalyticsClientOperationsMixin.analyze_text\u001b[0;34m(self, body, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 298\u001b[0m \u001b[39mif\u001b[39;00m response\u001b[39m.\u001b[39mstatus_code \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m [\u001b[39m200\u001b[39m]:\n\u001b[0;32m--> 299\u001b[0m map_error(status_code\u001b[39m=\u001b[39;49mresponse\u001b[39m.\u001b[39;49mstatus_code, response\u001b[39m=\u001b[39;49mresponse, error_map\u001b[39m=\u001b[39;49merror_map)\n\u001b[1;32m 300\u001b[0m error \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_deserialize\u001b[39m.\u001b[39mfailsafe_deserialize(_models\u001b[39m.\u001b[39mErrorResponse, pipeline_response)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/exceptions.py:165\u001b[0m, in \u001b[0;36mmap_error\u001b[0;34m(status_code, response, error_map)\u001b[0m\n\u001b[1;32m 164\u001b[0m error \u001b[39m=\u001b[39m error_type(response\u001b[39m=\u001b[39mresponse)\n\u001b[0;32m--> 165\u001b[0m \u001b[39mraise\u001b[39;00m error\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m: (401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.",
+ "\nThe above exception was the direct cause of the following exception:\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb Cell 8\u001b[0m line \u001b[0;36m7\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=65'>66</a>\u001b[0m \u001b[39mprint\u001b[39m(\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=66'>67</a>\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mThe articles that mention Microsoft are articles number: \u001b[39m\u001b[39m{}\u001b[39;00m\u001b[39m. Those are the ones I\u001b[39m\u001b[39m'\u001b[39m\u001b[39mm interested in reading.\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m.\u001b[39mformat(\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=67'>68</a>\u001b[0m \u001b[39m\"\u001b[39m\u001b[39m, \u001b[39m\u001b[39m\"\u001b[39m\u001b[39m.\u001b[39mjoin(articles_that_mention_microsoft)\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=68'>69</a>\u001b[0m )\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=69'>70</a>\u001b[0m )\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=72'>73</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39m__name__\u001b[39m \u001b[39m==\u001b[39m \u001b[39m'\u001b[39m\u001b[39m__main__\u001b[39m\u001b[39m'\u001b[39m:\n\u001b[0;32m---> <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=73'>74</a>\u001b[0m sample_extract_key_phrases()\n",
+ "\u001b[1;32m/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb Cell 8\u001b[0m line \u001b[0;36m5\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=37'>38</a>\u001b[0m text_analytics_client \u001b[39m=\u001b[39m TextAnalyticsClient(endpoint\u001b[39m=\u001b[39mendpoint, credential\u001b[39m=\u001b[39mAzureKeyCredential(key))\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=38'>39</a>\u001b[0m articles \u001b[39m=\u001b[39m [\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=39'>40</a>\u001b[0m \u001b[39m \u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=40'>41</a>\u001b[0m \u001b[39m Washington, D.C. Autumn in DC is a uniquely beautiful season. The leaves fall from the trees\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=51'>52</a>\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=52'>53</a>\u001b[0m ]\n\u001b[0;32m---> <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=54'>55</a>\u001b[0m result \u001b[39m=\u001b[39m text_analytics_client\u001b[39m.\u001b[39;49mextract_key_phrases(articles)\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=55'>56</a>\u001b[0m \u001b[39mfor\u001b[39;00m idx, doc \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(result):\n\u001b[1;32m <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/12_text_analytics_using_azure.ipynb#W0sdnNjb2RlLXJlbW90ZQ%3D%3D?line=56'>57</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m doc\u001b[39m.\u001b[39mis_error:\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/core/tracing/decorator.py:78\u001b[0m, in \u001b[0;36mdistributed_trace.<locals>.decorator.<locals>.wrapper_use_tracer\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 76\u001b[0m span_impl_type \u001b[39m=\u001b[39m settings\u001b[39m.\u001b[39mtracing_implementation()\n\u001b[1;32m 77\u001b[0m \u001b[39mif\u001b[39;00m span_impl_type \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m---> 78\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 80\u001b[0m \u001b[39m# Merge span is parameter is set, but only if no explicit parent are passed\u001b[39;00m\n\u001b[1;32m 81\u001b[0m \u001b[39mif\u001b[39;00m merge_span \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m passed_in_parent:\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_validate.py:79\u001b[0m, in \u001b[0;36mvalidate_multiapi_args.<locals>.decorator.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 77\u001b[0m \u001b[39m# the latest version is selected, we assume all features supported\u001b[39;00m\n\u001b[1;32m 78\u001b[0m \u001b[39mif\u001b[39;00m selected_api_version \u001b[39m==\u001b[39m VERSIONS_SUPPORTED[\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m]:\n\u001b[0;32m---> 79\u001b[0m \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 81\u001b[0m \u001b[39mif\u001b[39;00m version_method_added \u001b[39mand\u001b[39;00m version_method_added \u001b[39m!=\u001b[39m selected_api_version \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m 82\u001b[0m VERSIONS_SUPPORTED\u001b[39m.\u001b[39mindex(selected_api_version) \u001b[39m<\u001b[39m VERSIONS_SUPPORTED\u001b[39m.\u001b[39mindex(version_method_added):\n\u001b[1;32m 83\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m 84\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m'\u001b[39m\u001b[39m{\u001b[39;00mclient\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m{\u001b[39;00mfunc\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m'\u001b[39m\u001b[39m is not available in API version \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 85\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mselected_api_version\u001b[39m}\u001b[39;00m\u001b[39m. Use service API version \u001b[39m\u001b[39m{\u001b[39;00mversion_method_added\u001b[39m}\u001b[39;00m\u001b[39m or newer.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 86\u001b[0m )\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_text_analytics_client.py:927\u001b[0m, in \u001b[0;36mTextAnalyticsClient.extract_key_phrases\u001b[0;34m(self, documents, disable_service_logs, language, model_version, show_stats, **kwargs)\u001b[0m\n\u001b[1;32m 915\u001b[0m \u001b[39mreturn\u001b[39;00m cast(\n\u001b[1;32m 916\u001b[0m List[Union[ExtractKeyPhrasesResult, DocumentError]],\n\u001b[1;32m 917\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_client\u001b[39m.\u001b[39mkey_phrases(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 924\u001b[0m )\n\u001b[1;32m 925\u001b[0m )\n\u001b[1;32m 926\u001b[0m \u001b[39mexcept\u001b[39;00m HttpResponseError \u001b[39mas\u001b[39;00m error:\n\u001b[0;32m--> 927\u001b[0m \u001b[39mreturn\u001b[39;00m process_http_response_error(error)\n",
+ "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/azure/ai/textanalytics/_response_handlers.py:63\u001b[0m, in \u001b[0;36mprocess_http_response_error\u001b[0;34m(error)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[39mif\u001b[39;00m error\u001b[39m.\u001b[39mstatus_code \u001b[39m==\u001b[39m \u001b[39m404\u001b[39m:\n\u001b[1;32m 62\u001b[0m raise_error \u001b[39m=\u001b[39m ResourceNotFoundError\n\u001b[0;32m---> 63\u001b[0m \u001b[39mraise\u001b[39;00m raise_error(response\u001b[39m=\u001b[39merror\u001b[39m.\u001b[39mresponse, error_format\u001b[39m=\u001b[39mCSODataV4Format) \u001b[39mfrom\u001b[39;00m \u001b[39merror\u001b[39;00m\n",
+ "\u001b[0;31mClientAuthenticationError\u001b[0m: (401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.\nCode: 401\nMessage: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource."
+ ]
+ }
+ ],
+ "source": [
+ "# -------------------------------------------------------------------------\n",
+ "# Copyright (c) Microsoft Corporation. All rights reserved.\n",
+ "# Licensed under the MIT License. See License.txt in the project root for\n",
+ "# license information.\n",
+ "# --------------------------------------------------------------------------\n",
+ "\n",
+ "\"\"\"\n",
+ "FILE: sample_extract_key_phrases.py\n",
+ "\n",
+ "DESCRIPTION:\n",
+ " This sample demonstrates how to extract key talking points from a batch of documents.\n",
+ "\n",
+ " In this sample, we want to go over articles and read the ones that mention Microsoft.\n",
+ " We're going to use the SDK to create a rudimentary search algorithm to find these articles.\n",
+ "\n",
+ "USAGE:\n",
+ " python sample_extract_key_phrases.py\n",
+ "\n",
+ " Set the environment variables with your own values before running the sample:\n",
+ " 1) AZURE_LANGUAGE_ENDPOINT - the endpoint to your Language resource.\n",
+ " 2) AZURE_LANGUAGE_KEY - your Language subscription key\n",
+ "\"\"\"\n",
+ "\n",
+ "\n",
+ "def sample_extract_key_phrases() -> None:\n",
+ " print(\n",
+ " \"In this sample, we want to find the articles that mention Microsoft to read.\"\n",
+ " )\n",
+ " articles_that_mention_microsoft = []\n",
+ " # [START extract_key_phrases]\n",
+ " import os\n",
+ " from azure.core.credentials import AzureKeyCredential\n",
+ " from azure.ai.textanalytics import TextAnalyticsClient\n",
+ "\n",
+ " endpoint = \"https://xouhou-1234.cognitiveservices.azure.com/\"\n",
+ " key = \"d7fcbf17455647adbca355b021334c83\"\n",
+ "\n",
+ " text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))\n",
+ " articles = [\n",
+ " \"\"\"\n",
+ " Washington, D.C. Autumn in DC is a uniquely beautiful season. The leaves fall from the trees\n",
+ " in a city chock-full of forests, leaving yellow leaves on the ground and a clearer view of the\n",
+ " blue sky above...\n",
+ " \"\"\",\n",
+ " \"\"\"\n",
+ " Redmond, WA. In the past few days, Microsoft has decided to further postpone the start date of\n",
+ " its United States workers, due to the pandemic that rages with no end in sight...\n",
+ " \"\"\",\n",
+ " \"\"\"\n",
+ " Redmond, WA. Employees at Microsoft can be excited about the new coffee shop that will open on campus\n",
+ " once workers no longer have to work remotely...\n",
+ " \"\"\"\n",
+ " ]\n",
+ "\n",
+ " result = text_analytics_client.extract_key_phrases(articles)\n",
+ " for idx, doc in enumerate(result):\n",
+ " if not doc.is_error:\n",
+ " print(\"Key phrases in article #{}: {}\".format(\n",
+ " idx + 1,\n",
+ " \", \".join(doc.key_phrases)\n",
+ " ))\n",
+ " # [END extract_key_phrases]\n",
+ " if \"Microsoft\" in doc.key_phrases:\n",
+ " articles_that_mention_microsoft.append(str(idx + 1))\n",
+ "\n",
+ " print(\n",
+ " \"The articles that mention Microsoft are articles number: {}. Those are the ones I'm interested in reading.\".format(\n",
+ " \", \".join(articles_that_mention_microsoft)\n",
+ " )\n",
+ " )\n",
+ "\n",
+ "\n",
+ "if __name__ == '__main__':\n",
+ " sample_extract_key_phrases()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "venv",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}