Upload New File

%% Cell type:markdown id: tags:

# Setup and data

%% Cell type:code id: tags:

``` python

from transformers import BertTokenizer, BertForSequenceClassification

from transformers import pipeline

```

%% Output

    c:\Users\ESenn\Miniconda3\envs\llm_class\Lib\site-packages\tqdm\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html

      from .autonotebook import tqdm as notebook_tqdm

%% Cell type:code id: tags:

``` python

# load your data here

```

%% Cell type:markdown id: tags:

# Transformers Library for Sentiment Classification using BERT

%% Cell type:markdown id: tags:

**Task:** Review classification

**Model:** A pretrained BERT model including a sentiment classification head (which is not trained on our task).

We use the hidden states of BERT for Sentiment Classification.

The classifier is not trained. See notebooks for chapter 2 for training, and chapter 5 for a step-by-stey description of how to train it.

%% Cell type:code id: tags:

``` python

# Load pre-trained BERT tokenizer and model for sentiment classification

tokenizer = BertTokenizer.from_pretrained(

    "nlptown/bert-base-multilingual-uncased-sentiment"

)

model = BertForSequenceClassification.from_pretrained(

    "nlptown/bert-base-multilingual-uncased-sentiment"

)

# Load the classification pipeline

classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

# Example texts for classification

texts = [

    "This movie was fantastic! I loved it.",

    "The food was terrible, I will never come back.",

    "The service was just okay, nothing special.",

]

# Perform classification

results = classifier(texts)

# Display the results

for text, result in zip(texts, results):

    print(f"Text: {text}")

    print(f"Sentiment: {result['label']}")

```

%% Output

    c:\Users\ESenn\Miniconda3\envs\llm_class\Lib\site-packages\transformers\tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884

      warnings.warn(

    Text: This movie was fantastic! I loved it.

    Sentiment: 5 stars

    Text: The food was terrible, I will never come back.

    Sentiment: 1 star

    Text: The service was just okay, nothing special.

    Sentiment: 3 stars