errors model

application/__init__.py

@@ -6,6 +6,8 @@ def create_app():
     CORS(application)
 
     from application.services.sentiment_service import sentiment_service
+    from application.services.errors_service import errors_service
     application.register_blueprint(sentiment_service)
+    application.register_blueprint(errors_service)
 
     return application

application/functions/errors.py

@@ -0,0 +1,11 @@
+from transformers import AutoTokenizer
+from transformers import pipeline
+
+model = 'application/models/errors_model'
+tokenizer = AutoTokenizer.from_pretrained('application/tokenizers/errors_tokenizer')
+
+def errors_correction(data):
+    pipe = pipeline("text2text-generation",model=model,tokenizer=tokenizer,max_length=2000)
+    result = pipe(data)
+    
+    return result

application/models/errors_model/config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "sdadas/polish-bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 50002
+}

application/models/errors_model/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.2"
+}

application/services/errors_service.py

@@ -0,0 +1,15 @@
+from flask import(
+    request,   
+    jsonify, 
+    Blueprint,
+    )
+from application.functions.errors import errors_correction
+
+errors_service = Blueprint("errors_service", __name__)    
+
+@errors_service.route("/get_errors", methods=['PUT'])
+def get_data():
+    data = request.get_json()
+    predicitons = errors_correction(data['sentence']) #korekcja
+
+    return jsonify({"predictions": predicitons})

application/services/sentiment_service.py

@@ -7,7 +7,7 @@ from application.functions.sentiment import sentiment_prediction, count_predicti
 
 sentiment_service = Blueprint("sentiment_service", __name__)    
 
-@sentiment_service.route("/get_sentiment_data", methods=['GET'])
+@sentiment_service.route("/get_sentiment_data", methods=['PUT'])
 def get_data():
     data = request.get_json()
     predicitons = sentiment_prediction(data['sentences']) #predykcje

application/tokenizers/errors_tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "original/polish-bart-base", "tokenizer_class": "BartTokenizer"}