Create sentimentorr.py

sentimentorr.py

@@ -0,0 +1,76 @@
+import pandas as pd
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from torch.nn.functional import softmax as softmax 
+import numpy as np
+import torch
+
+
+  
+tokenizer = AutoTokenizer.from_pretrained("joeddav/distilbert-base-uncased-go-emotions-student")
+
+model = AutoModelForSequenceClassification.from_pretrained("joeddav/distilbert-base-uncased-go-emotions-student")
+
+labels = ["admiration","amusement","anger","annoyance","approval","caring","confusion","curiosity","desire","disappointment", "disapproval", "disgust", "embarrassment", "excitement", "fear", "gratitude", "grief", "joy", "love", "nervousness", "optimism", "pride", "realization", "relief", "remorse", "sadness", "surprise", "neutral"
+]
+
+labels7larg=['admiration',
+ 'amusement',
+ 'anger',
+ 'annoyance',
+ 'approval',
+ 'caring',
+ 'confusion',
+ 'curiosity',
+ 'desire',
+ 'disappointment',
+ 'disapproval',
+ 'disgust',
+ 'embarrassment',
+ 'excitement',
+ 'fear',
+ 'gratitude',
+ 'grief',
+ 'joy',
+ 'love',
+ 'nervousness',
+ 'optimism',
+ 'pride',
+ 'realization',
+ 'relief',
+ 'remorse',
+ 'sadness',
+ 'surprise',
+ 'neutral',
+ 'larg']
+ 
+
+
+def sentimentor(mmm):
+    
+    dfda = pd.Series(mmm)
+
+    vecs = np.array([model(**tokenizer(txt, return_tensors="pt", padding=True))[0][0].detach().numpy() for txt in dfda])
+
+
+    
+    ds=pd.DataFrame(columns=labels7larg)
+    for iii in range(len(vecs)):
+        softt=softmax(torch.from_numpy(vecs[iii]), dim=0)
+        kki=pd.DataFrame(softt, index=labels)
+        ji=kki.nlargest(1, 0)
+        dv=pd.DataFrame(columns=labels)
+
+        dv.loc[iii,:]=softt
+
+        dv.loc[iii,'larg']=ji.index[0]
+
+        ds=pd.concat([ds, dv])
+
+    if len(ds)==len(dfda):
+        concatt = pd.concat([dfda,ds], axis=1)
+        xsd=concatt['larg']
+        return xsd[0]
+    else:
+        print('eshteba kardi')
+        
+