gyb-classification-model 0.1.7__tar.gz → 0.1.9__tar.gz

{gyb_classification_model-0.1.7/gyb_classification_model.egg-info → gyb_classification_model-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gyb-classification-model
-Version: 0.1.7
+Version: 0.1.9
 Summary: ML classification models package
 Home-page: https://github.com/GreenBills/GYB-Classification-Model
 Author: Hrutik-M

{gyb_classification_model-0.1.7 → gyb_classification_model-0.1.9}/gyb_classification_model/predictor.py

@@ -17,13 +17,13 @@ script_dir = os.path.dirname(os.path.abspath(__file__))
 base_path = os.path.abspath(os.path.join(script_dir, '../models'))
 
 # Load files
-with open(os.path.join(base_path, "vectorizerV29.pkl"), "rb") as f:
+with open(os.path.join(base_path, "vectorizerV30.pkl"), "rb") as f:
     tfidf_vectorizer = pickle.load(f)
 
-with open(os.path.join(base_path, "label_mapV29.pkl"), "rb") as f:
+with open(os.path.join(base_path, "label_mapV30.pkl"), "rb") as f:
     reverse_label_map = pickle.load(f)
 
-with open(os.path.join(base_path, "textClassificationModelV29.pkl"), "rb") as f:
+with open(os.path.join(base_path, "textClassificationModelV30.pkl"), "rb") as f:
     model = pickle.load(f)
 
 
@@ -101,7 +101,7 @@ def predict_text(input_text):
 
     category = reverse_label_map.get(predicted_label)
 
-    if category == "EOB_EOR" and probability <= 0.5:
+    if probability <= 0.6:
         category = "MISC"
 
     order_delivery = ["DELIVERY_SLIP_ORDER"]

{gyb_classification_model-0.1.7 → gyb_classification_model-0.1.9/gyb_classification_model.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gyb-classification-model
-Version: 0.1.7
+Version: 0.1.9
 Summary: ML classification models package
 Home-page: https://github.com/GreenBills/GYB-Classification-Model
 Author: Hrutik-M

{gyb_classification_model-0.1.7 → gyb_classification_model-0.1.9}/gyb_classification_model.egg-info/SOURCES.txt

@@ -10,9 +10,9 @@ app/../models/MedicalReportVectorizerV10.pkl
 app/../models/OnlyDeliverSlipPharmOrderModelV4.pkl
 app/../models/OnlyDeliverSlipPharmOrderVectorizerV4.pkl
 app/../models/OnlyDeliverSlipPharmOrderlabel_mapV4.pkl
-app/../models/label_mapV29.pkl
-app/../models/textClassificationModelV29.pkl
-app/../models/vectorizerV29.pkl
+app/../models/label_mapV30.pkl
+app/../models/textClassificationModelV30.pkl
+app/../models/vectorizerV30.pkl
 gyb_classification_model/__init__.py
 gyb_classification_model/predictor.py
 gyb_classification_model.egg-info/PKG-INFO
@@ -26,16 +26,16 @@ gyb_classification_model/../models/MedicalReportVectorizerV10.pkl
 gyb_classification_model/../models/OnlyDeliverSlipPharmOrderModelV4.pkl
 gyb_classification_model/../models/OnlyDeliverSlipPharmOrderVectorizerV4.pkl
 gyb_classification_model/../models/OnlyDeliverSlipPharmOrderlabel_mapV4.pkl
-gyb_classification_model/../models/label_mapV29.pkl
-gyb_classification_model/../models/textClassificationModelV29.pkl
-gyb_classification_model/../models/vectorizerV29.pkl
+gyb_classification_model/../models/label_mapV30.pkl
+gyb_classification_model/../models/textClassificationModelV30.pkl
+gyb_classification_model/../models/vectorizerV30.pkl
 models/MedicalReportClassifierV10.pkl
 models/MedicalReportLabelMapV10.pkl
 models/MedicalReportVectorizerV10.pkl
 models/OnlyDeliverSlipPharmOrderModelV4.pkl
 models/OnlyDeliverSlipPharmOrderVectorizerV4.pkl
 models/OnlyDeliverSlipPharmOrderlabel_mapV4.pkl
-models/label_mapV29.pkl
-models/textClassificationModelV29.pkl
-models/vectorizerV29.pkl
+models/label_mapV30.pkl
+models/textClassificationModelV30.pkl
+models/vectorizerV30.pkl
 test/test.py

{gyb_classification_model-0.1.7 → gyb_classification_model-0.1.9}/setup.py

@@ -6,7 +6,7 @@ long_description = (curr_directory / "README.md").read_text()
 
 setup(
     name='gyb-classification-model',                          # Package name (what you'll pip install)
-    version='0.1.7',
+    version='0.1.9',
     author='Hrutik-M',
     author_email='hrutik.m@codearray.tech',
     description='ML classification models package',

gyb_classification_model-0.1.9/test/test.py

@@ -0,0 +1,9 @@
+from gyb_classification_model import predictor
+
+text = "*000804* LM General Insurance Company P.O. Box 5014 Scranton PA 18505-5014 - INJURY CARE CHIROPRACTIC 2167 E 21st St Ste 148 Brooklyn, NY, 11229-3607 Liberty Mutual® INSURANCE CONTACT US Melissa.Maldonado@LibertyMut ual.com Direct: (516) 479-0773 Fax: (888) 268-8840 LM General Insurance Company P.O. Box 5014 Scranton PA 18505-5014 United States (800) 225-2467 LibertyMutual.com July 29, 2025 Claim Number: Date of Incident: Claimant: 059251780-04 04/27/2025 ANNA SARIBEGOV Policy Number: AOS-221-630070-40 Dear Billing Department, We take our responsibility to our customers seriously, and part of that responsibility is keeping you informed. Recently we've had to delay the processing of your bill. The reason for this delay is we haven't yet received all necessary information to complete our investigation, which may include a recorded interview, signed statement, and/or Examination Under Oath from the driver and/or passenger(s) involved OR other parties involved or related to the occurrence. Additional documentation may also be requested at the time of the Examination Under Oath or thereafter which may impact the investigation of this claim. This is the second notice .. Billing Details Patient Account Number: 100884709 Date of Service: From: 05/21/2025 To: 05/21/2025 Bill Amount: $1,000.05 Bill ID: N2032570017 We're Here to Help If you have any questions, please contact me and I'll be happy to help. I can assist you more quickly if you reference the Claim No. 059251780-04 in all communications. *400000010001000001000804804* Sincerely, MELISSA MALDONADO Claims Department CWL0116 Status to Provider 059251780-04 Page 1 of 2 :"
+
+# processed_text = predictor.preprocess_text(text)
+category = predictor.predict_text(text)
+
+print(category)
+

gyb_classification_model-0.1.7/test/test.py

@@ -1,9 +0,0 @@
-from gyb_classification_model import predictor
-
-text = "WERT MEDICAL CARE P.C. PRIMARY SURGEON: MATTHEW WERT MD, SANFORD WERT MD ASSISTANT SURGEON: MATTHEW WERT MD, SANFORD WERT MD, JESSE INKLES PA-C, HANNAH ECKSTEIN PA-C, CHRISTOPHER CARROLL PA-C, I. Wert PA-C INSURANCE (NF,) WC, PVT, LEIN, FUND) LS FAHMY, DIANA DOB:09/07/1989 (35) DOS:08/11/2025 Sex:Female MRN:4343 Physician: Wert, Matthew CPT SHOULDER (RT or LT or BILATERAL) 1 0.5 23472 Total Shoulder Arthroplasty 23700 Manipulation of shoulder joint (anesthesia) 813.77 406.89 29806 Arthroscopy, shoulder, surgical; capsulorrhaphy (Bankart Arthroscopy) 2698.28 1349.14 29807 Arthroscopy, repair of SLAP lesion 2738.59 1369.30 29819 Arthroscopy, surgical w/ removal of loose body or foreign body 1957.57 978.79 29820 Synovectomy, limited 1791.29 895.65 29821 Synovectomy, complete 1957.57 978.79 29822 Shoulder Arthroscopy / debridement, limited (2-3 Areas) Labrum Tear Chondromalacia GH Joint 1902.15 951.07 29823 Debridement, extensive (3 ormore areas) 2065.91 1032.96 29824 Arthroscopy, shoulder, surgical; distal claviculectomy including distal articular surface (Mumford procedure) 1305.05 652.53 29825 Lysis and resection of adhesions, w/ or w/o manipulation 2060.87 1030.44 29826 Decompression of subacromial space with partial acromioplasty w/ or w/o coracoacromial release 496.32 248.16 29827 Arthroscopy, shoulder, surgical; with rotator cuff repair 2348.08 1174.04 20610 Shoulder Injection 62.99 31.50 OTHER (PLEASE CODE) TOTAL CPT ANKLE / FOOT (RT or LT or BILATERAL) 1 0.5 27814 Open treatment of bimalleolar fracture 2174.24 1087.12 27792 Open treatment of Lateral malleolus fracture 1957.57 978.76 29897 Arthroscopy, ankle, surgical 1791.29 895.65 29894 Arthroscopic removal of loose body or foreign body 1892.07 946.04 29895 Synovectomy, partial 1791.29 895.65 29898 Debridement, extensive 1957.57 978.79 27829 Ankle syndesmosis repair 1305.05 652.53 29891 Excision of OCD lesion 2632.77 1316.39 27650 Achilles tendon repair 1957.57 978.79 OTHER (PLEASE CODE) TOTAL Partial RIC/Subscap Tear Labrum Tear Chondromalacia GH Joint Partial RTC/Subscap Tear "
-
-# processed_text = predictor.preprocess_text(text)
-category = predictor.predict_text(text)
-
-print(category)
-