Create annotator.py

annotator.py

@@ -0,0 +1,96 @@
+import numpy as np
+import transformers
+from sklearn import metrics
+import pandas as pd
+import streamlit as st
+def ignitor_load():
+    dataj=pd.read_json('tinyignitorfile.json')
+    return dataj
+
+def appendor(thex):
+    gaa=ignitor_load()
+    shortt=gaa.loc[:21,['text','index']]
+    shortt.loc[21,'text']=thex
+    return shortt
+
+
+
+tokenizerr = transformers.DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+modell = transformers.TFDistilBertModel.from_pretrained('distilbert-base-uncased')
+
+
+encod=[]
+def allll(df):
+    for i in range(len(df)):
+        v=df.loc[i,'text']
+        embed=np.array(np.array(modell(np.array(tokenizerr.encode(v))[np.newaxis,:])[0][0][1:-1]).mean(0))
+        encod.append(embed)
+#allll(shortt)
+
+
+    
+    labs = {}
+    
+    labs["SALARY"] = ['underpay','underpaid','overpay','overpaying','payments','wage','payroll','pay','paycheck']
+    labs["COLLEAGUES"] = ['colleague','employee','staff' ,'coworker','co-worker','colleagues']
+    labs["SUPERVISION"] = ['boss','supervisors','manager','supervisor']
+    labs["TIMEDAY"] = ['monday','weekday','day','weekend']
+    labs["TIMEDAYNOMONDAY"] = ['weekday','day','weekend']
+    emblabs={}
+    emblabss=[]
+    keyy=[]
+    for key,v in labs.items():
+        keyy.append(key)
+        embed=np.array(np.array(modell(np.array(tokenizerr.encode(v))[np.newaxis,:])[0][0][1:-1]).mean(0))
+        emblabss.append(embed)
+        
+    for i in range(len(keyy)):
+        emblabs[keyy[i]] = emblabss[i]
+        
+    hamme=[]
+    for a,z in emblabs.items():
+        jj=z.reshape(-1, 1)
+        hamme.append(jj)
+        
+        
+    sim=[]
+    for i in range(len(hamme)):
+        zz=metrics.pairwise.cosine_similarity(encod, hamme[i].T)
+        sim.append(zz)
+        
+    sim=np.array(sim)
+    cyr1=st.secrets["cyr1"]
+    cyr1=float(cyr1)
+    cyr2=st.secrets["cyr2"]
+    cyr2=float(cyr2)
+    cyr3=st.secrets["cyr3"]
+    cyr3=float(cyr3)
+    cyr4=st.secrets["cyr4"]
+    cyr4=float(cyr4)
+    cyr5=st.secrets["cyr5"]
+    cyr5=float(cyr5)
+
+    referirv=[cyr1,cyr2,cyr3,cyr4,cyr5]
+    meanss=[]
+    labels = list(emblabs.keys())
+    for i in range(len(sim)):
+        sim[i] = sim[i] / sum(sim[i])
+        meanss.append(sim[i].mean())
+    zarayeb = [ii / jj for ii, jj in zip(referirv, meanss)]
+    
+    for i in range(len(sim)):
+    
+        sim[i] = (sim[i])*zarayeb[i]
+    
+    threshhold=st.secrets["threshhold"]
+    threshhold=float(threshhold)    
+    tags=[]
+    for j in range(len(sim[0])):
+        if np.amax([sim[:,j,0]]) <= threshhold:
+            label='None'
+            tags.append(label)
+        else:
+            label=np.argmax([sim[:,j,0]])
+            tags.append(label)
+            
+    return tags[-1]