gyb-classification-model 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

app/main.py

@@ -0,0 +1,5 @@
+from gyb_classification_model import predictor
+
+def predict_category(text):
+    category = predictor.predict_text(text)
+    return category

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, "vectorizerV28.pkl"), "rb") as f:
+with open(os.path.join(base_path, "vectorizerV29.pkl"), "rb") as f:
     tfidf_vectorizer = pickle.load(f)
 
-with open(os.path.join(base_path, "label_mapV28.pkl"), "rb") as f:
+with open(os.path.join(base_path, "label_mapV29.pkl"), "rb") as f:
     reverse_label_map = pickle.load(f)
 
-with open(os.path.join(base_path, "textClassificationModelV28.pkl"), "rb") as f:
+with open(os.path.join(base_path, "textClassificationModelV29.pkl"), "rb") as f:
     model = pickle.load(f)
 
 
@@ -39,13 +39,13 @@ with open(os.path.join(base_path, "OnlyDeliverSlipPharmOrderModelV4.pkl"), "rb")
 
 
 # Load files for Medical Reports
-with open(os.path.join(base_path, "MedicalReportVectorizerV9.pkl"), "rb") as f:
+with open(os.path.join(base_path, "MedicalReportVectorizerV10.pkl"), "rb") as f:
     medical_vectorizer = pickle.load(f)
 
-with open(os.path.join(base_path, "MedicalReportLabelMapV9.pkl"), "rb") as f:
+with open(os.path.join(base_path, "MedicalReportLabelMapV10.pkl"), "rb") as f:
     reverse_medical_map = pickle.load(f)
 
-with open(os.path.join(base_path, "MedicalReportClassifierV9.pkl"), "rb") as f:
+with open(os.path.join(base_path, "MedicalReportClassifierV10.pkl"), "rb") as f:
     medical_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"]
@@ -129,7 +129,7 @@ def predict_text(input_text):
 
     result = {
         "category": category,
-        "probability": round(probability, 4)
+        "probability": round(float(probability), 4)
     }
 
     return result

{gyb_classification_model-0.1.6.dist-info → gyb_classification_model-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gyb-classification-model
-Version: 0.1.6
+Version: 0.1.8
 Summary: ML classification models package
 Home-page: https://github.com/GreenBills/GYB-Classification-Model
 Author: Hrutik-M

gyb_classification_model-0.1.8.dist-info/RECORD

@@ -0,0 +1,18 @@
+app/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/main.py,sha256=uksl9bO_2zeHFTiiOVXvOyv6S4XnJk92fSkyb5uci9A,139
+gyb_classification_model/__init__.py,sha256=BmCaBc8PZ9FMpP_7QvJs9F5X-qLhLw5BpixkryN4eq4,36
+gyb_classification_model/predictor.py,sha256=FFfiXB-EdCR_lkWLvUdAGhNQb5WHMKbKQ-pQFgo0u2c,4307
+gyb_classification_model-0.1.8.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+models/MedicalReportClassifierV10.pkl,sha256=NuqifPaY-E6kRW3-K32dHi2QKQQfcakjkRUfJXlSsMY,14536409
+models/MedicalReportLabelMapV10.pkl,sha256=Xad4MdlAEK_0f5WXKjHOAeWN3Z__G97dsCpxZqP5Xck,752
+models/MedicalReportVectorizerV10.pkl,sha256=SQeg-MZsj4W0m86zLkcFJAOmh7naXf7j73LYI0y39Ws,959811
+models/OnlyDeliverSlipPharmOrderModelV4.pkl,sha256=Glonp71H561tq3hxR9Fgm74GI3QZPVrzuh3Wby46hLQ,401961
+models/OnlyDeliverSlipPharmOrderVectorizerV4.pkl,sha256=m1MykxWdAMkwC4qmcD4BnLkItJh2NFUf-0rby_wBY0Y,265450
+models/OnlyDeliverSlipPharmOrderlabel_mapV4.pkl,sha256=4kcube3Wp1YPPm-13j-p4jEWAQJ4lvKCq61Yen5zvU8,173
+models/label_mapV29.pkl,sha256=ovZqFLzel6qObDBnb2qcMQdagvN10hITXdGOroJEjug,482
+models/textClassificationModelV29.pkl,sha256=YinKL-XuVBpG34YSmxHdV_KDdTq_mFWCx4lCNJkLZBE,1661001
+models/vectorizerV29.pkl,sha256=oQOOIVNUV7sGTrU6ypUfao7x4ft1g9DKYrSv8NUb1zY,7966562
+gyb_classification_model-0.1.8.dist-info/METADATA,sha256=6yEH5OFTqjR59XhEHGNrsWcHyG8ycJviLn9wUf9lKZo,1167
+gyb_classification_model-0.1.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+gyb_classification_model-0.1.8.dist-info/top_level.txt,sha256=aRuWSVtred104QcY9epZ9zD90KOeAsxIergjGPUMWe8,29
+gyb_classification_model-0.1.8.dist-info/RECORD,,

{gyb_classification_model-0.1.6.dist-info → gyb_classification_model-0.1.8.dist-info}/top_level.txt

@@ -1 +1,2 @@
+app
 gyb_classification_model

gyb_classification_model-0.1.6.dist-info/RECORD

@@ -1,16 +0,0 @@
-gyb_classification_model/__init__.py,sha256=BmCaBc8PZ9FMpP_7QvJs9F5X-qLhLw5BpixkryN4eq4,36
-gyb_classification_model/predictor.py,sha256=JAUE8FJsh0FBdLLvFZnQV8MmHywEK_4TBf0AqXYChpg,4323
-gyb_classification_model-0.1.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-models/MedicalReportClassifierV9.pkl,sha256=3vUstfbv4oqM2-ct41JzMNWgrmKGXR3-qJ2tN96cmg4,14317849
-models/MedicalReportLabelMapV9.pkl,sha256=Xad4MdlAEK_0f5WXKjHOAeWN3Z__G97dsCpxZqP5Xck,752
-models/MedicalReportVectorizerV9.pkl,sha256=gLW-vFCEhkV7Xao5ZJOGGFymf3K2PBgyCpp4bGBTAPk,945673
-models/OnlyDeliverSlipPharmOrderModelV4.pkl,sha256=Glonp71H561tq3hxR9Fgm74GI3QZPVrzuh3Wby46hLQ,401961
-models/OnlyDeliverSlipPharmOrderVectorizerV4.pkl,sha256=m1MykxWdAMkwC4qmcD4BnLkItJh2NFUf-0rby_wBY0Y,265450
-models/OnlyDeliverSlipPharmOrderlabel_mapV4.pkl,sha256=4kcube3Wp1YPPm-13j-p4jEWAQJ4lvKCq61Yen5zvU8,173
-models/label_mapV28.pkl,sha256=ovZqFLzel6qObDBnb2qcMQdagvN10hITXdGOroJEjug,482
-models/textClassificationModelV28.pkl,sha256=GyDRan8ZaJlzLK8nqd7kNs5CbD4jvJO5i5DXZPCJHEY,1996636
-models/vectorizerV28.pkl,sha256=7Edbd3sTeb1r3QDgJ0O4jAbcNwd-Co42FOVrQ3ndQCw,7796262
-gyb_classification_model-0.1.6.dist-info/METADATA,sha256=MXZtfgAV3cU-qUDdWHuiojULn1tAEB_63IKguvGJN5o,1167
-gyb_classification_model-0.1.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-gyb_classification_model-0.1.6.dist-info/top_level.txt,sha256=epvMQ2IrnBRlZuewbS8jG-nrwUbVNSJG63tCXePnu1U,25
-gyb_classification_model-0.1.6.dist-info/RECORD,,