update app.py file to work with orgs from gpt

app.py

@@ -7,18 +7,18 @@ from transformers import pipeline
 # from dotenv import load_dotenv, find_dotenv
 import huggingface_hub
 import json
-# from simcse import SimCSE # use for gpt
+from simcse import SimCSE # use for gpt
 from evaluate_data import store_sample_data, get_metrics_trf
 
 # store_sample_data()
 
 
 
-with open('./data/sample_data.json', 'r') as f:
-    # sample_data = [
-    #     {'id': "", 'text': "", 'orgs': ["", ""]}
-    # ]
-    sample_data = json.load(f)
+# with open('./data/sample_data.json', 'r') as f:
+#     # sample_data = [
+#     #     {'id': "", 'text': "", 'orgs': ["", ""]}
+#     # ]
+#     sample_data = json.load(f)
     
 # _ = load_dotenv(find_dotenv()) # read local .env file
 hf_token= os.environ['HF_TOKEN']
@@ -73,16 +73,16 @@ def find_orgs_gpt(sentence):
 #     return list(set(org_list))
 
 
-true_orgs = [sent['orgs'] for sent in sample_data]
+# true_orgs = [sent['orgs'] for sent in sample_data]
 
-predicted_orgs_gpt = [find_orgs_gpt(sent['text']) for sent in sample_data]
+# predicted_orgs_gpt = [find_orgs_gpt(sent['text']) for sent in sample_data]
 # predicted_orgs_trf = [find_orgs_trf(sent['text']) for sent in sample_data]
 
-all_metrics = {}
+# all_metrics = {}
 
 # sim_model = SimCSE('sentence-transformers/all-MiniLM-L6-v2')
 # all_metrics['gpt'] = calc_metrics(true_orgs, predicted_orgs_gpt, sim_model)
-print('Finiding all metrics trf')
+# print('Finiding all metrics trf')
 # all_metrics['trf'] = get_metrics_trf()
 
 
@@ -92,38 +92,26 @@ My latest exclusive for The Hill : Conservative frustration over Republican effo
 
 """
 def find_orgs(uploaded_file):
-    print('=*'*80)
-    print(type(uploaded_file))
-    # print(uploaded_file)
-    try:
-        print('inside try')
-        # print(uploaded_file.decode())
-        uploaded_data = json.loads(uploaded_file.decode())
+    uploaded_data = json.loads(uploaded_file)
+    all_metrics = {}
+    all_metrics['trf'] = get_metrics_trf(uploaded_data)
     
-    except:
-        print('inside except')
-        # print(uploaded_file.decode())
-        uploaded_data = json.loads(uploaded_file)
-    
-    
-    # all_metrics = {}
-    # all_metrics['trf'] = get_metrics_trf(uploaded_data)
-    
-    # store_sample_data(uploaded_data)
+
+    sample_data = store_sample_data(uploaded_data)
     # with open('./data/sample_data.json', 'r') as f:
     #     sample_data = json.load(f)
     
-#     gpt_orgs, true_orgs = [], []
+    gpt_orgs, true_orgs = [], []
     
-#     for sent in sample_data:
-#         gpt_orgs.append(find_orgs_gpt(sent['text']))
-#         true_orgs.append(sent['orgs'])
+    for sent in sample_data:
+        gpt_orgs.append(find_orgs_gpt(sent['text']))
+        true_orgs.append(sent['orgs'])
         
 
-    # sim_model = SimCSE('sentence-transformers/all-MiniLM-L6-v2')
-    # all_metrics['gpt'] = calc_metrics(true_orgs, gpt_orgs, sim_model)        
+    sim_model = SimCSE('sentence-transformers/all-MiniLM-L6-v2')
+    all_metrics['gpt'] = calc_metrics(true_orgs, gpt_orgs, sim_model)        
 
-    return get_metrics_trf(uploaded_data)
+    return all_metrics
 # radio_btn = gr.Radio(choices=['GPT', 'iSemantics'], value='iSemantics', label='Available models', show_label=True)
 # textbox = gr.Textbox(label="Enter your text", placeholder=str(all_metrics), lines=8)
 upload_btn = gr.UploadButton(label='Upload a json file.', type='binary')