Untitled

import pandas as pd

df=pd.read_excel("Automatic Ticket Assignment.xlsx")
df.head()

df.dropna(inplace=True)

df['Assignment group']

import neattext.functions as nfx

def preprocess_text(text):
    if not isinstance(text, str):
        return text
    
    # Apply various text cleaning functions using neattext
    text = nfx.remove_userhandles(text)
    text = nfx.remove_puncts(text)
    text = nfx.remove_numbers(text)
    text = nfx.remove_special_characters(text)
    text = nfx.remove_multiple_spaces(text)
    text = nfx.remove_html_tags(text)
    text = nfx.remove_dates(text)
    
    
    # Remove stopwords using a custom function
    text = nfx.remove_stopwords(text)
    
    return text

for col in df.columns:
    if col != 'Assignment group':
        df[col] = df[col].apply(preprocess_text)


print(df.head())


# Split the dataset into training and validation sets (you can adjust the test_size)
from sklearn.model_selection import train_test_split
train_df, val_df = train_test_split(df, test_size=0.2, random_state=42)



from transformers import BertTokenizer, BertForSequenceClassification
import torch

# Assuming 'train_df' and 'val_df' are your DataFrames

model_name = 'bert-base-uncased'
tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertForSequenceClassification.from_pretrained(model_name, num_labels=74)

def tokenize_data(data):
    input_text = data['Short description'] + ' ' + data['Description'] + ' ' + data['Caller'] + ' ' + data['Assignment group']
    #print("Inut Text ",input_text)
    inputs = tokenizer(
        input_text.tolist(),  # Convert to list
        padding=True,
        truncation=True,
        return_tensors="pt",
        return_attention_mask=True,
        return_token_type_ids=False,
        verbose=True
    )
    labels = [group.split('_')[-1] for group in data['Assignment group']]
    inputs["labels"] = torch.tensor([int(label) for label in labels])
    return inputs


train_dataset = tokenize_data(train_df)
val_dataset = tokenize_data(val_df)

print("Train Dataset ",train_dataset)
print("Val Dataset ",val_dataset)

## Working till here

from transformers import BertForSequenceClassification, Trainer, TrainingArguments


## Training and rediction
# Define the model
model_name = 'bert-base-uncased'
model = BertForSequenceClassification.from_pretrained(model_name, num_labels=74)

# Define training arguments
training_args = TrainingArguments(
    output_dir='./results',
    num_train_epochs=3,
    per_device_train_batch_size=8,
    evaluation_strategy="steps",
    logging_dir='./logs',
    logging_steps=10,
    do_train=True,
    do_eval=True,
    do_predict=True,
    load_best_model_at_end=True,
    metric_for_best_model="accuracy",
    greater_is_better=True,
    save_total_limit=3
)


# Define trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=val_dataset,
)

# Train the model
trainer.train()

# Evaluate the model
results = trainer.evaluate()