How can I show Label output only from Transformers Pipeline - Sentiment Analysis

Question

Picture of Output

From the picture, I've given the model a few sentences to analyse. The result from the analysis, I've added a new column to the dataframe called "sentiment".

As you can see, it gives the results in a list format with labels and scores.

What i'm trying to do is only add the Label result. i.e: "POSITIVE", "NEGATIVE", etc.. Is there a way of doing this?

Many thanks in advance.

Answer 1

I have no idea how works your pipe but you have list with dict and pandas has .str to work with string but .str[index] works also with list or dict.

df['Sentiment'] = df['Sentiment'].str[0].str['label']

---

Minimal working example

import pandas as pd

df = pd.DataFrame({
   'Sentiment': [
      [{'label':'Negative', 'score': 0.1}],
      [{'label':'Positive', 'score': 0.9}],
   ]      
}) 

print('\n--- before ---\n')
print(df)

df['Sentiment'] = df['Sentiment'].str[0].str['label']

print('\n--- after ---\n')
print(df)

Result:

--- before ---

                               Sentiment
0  [{'label': 'Negative', 'score': 0.1}]
1  [{'label': 'Positive', 'score': 0.9}]

--- after ---

  Sentiment
0  Negative
1  Positive