tezansahu

import mlfoundry as mlf
import random
import os
from simpletransformers.classification import ClassificationModel

# Function to load a Simple Transformers model & predict sentiment
def predict_model(model_params, input_headline):
    try:
        class_name_map = {
            0: "negative", 

tezansahu

training_args = {
    'train_batch_size':8, 
    'gradient_accumulation_steps':16, 
    'learning_rate': 2e-5, 
    'num_train_epochs': 5, 
    'max_seq_length': 60               # based on the histogram of number of words present in the headline
}

# model_type and model_name have been changed to now fine-tune RoBERTa instead of BERT
model_params = {

tezansahu

training_args = {
    'train_batch_size':8, 
    'gradient_accumulation_steps':16, 
    'learning_rate': 2e-5, 
    'num_train_epochs': 5,             # Change in 
    'max_seq_length': 60               # based on the histogram of number of words present in the headline
}

model_params = {
    'model_type': 'bert',

tezansahu

training_args = {
    'train_batch_size':8, 
    'gradient_accumulation_steps':16, 
    'learning_rate': 2e-5, 
    'num_train_epochs': 3, 
    'max_seq_length': 60               # based on the histogram of number of words present in the headline
}

model_params = {
    'model_type': 'bert',

tezansahu

import mlfoundry as mlf

mlf_api = mlf.get_client()
mlf_run = mlf_api.create_run(project_name='financial-sentiment-analysis', run_name='bert_3epochs')

tezansahu

def trainModel(model_params, training_args, run, run_name):
    # Log the training & evaluation datasets as CSV files
    run.log_dataset(train_df, data_slice=mlf.DataSlice.TRAIN, fileformat=mlf.FileFormat.CSV)
    run.log_dataset(eval_df, data_slice=mlf.DataSlice.TEST, fileformat=mlf.FileFormat.CSV)
    
    # Log the model specifications and the training hyperparameters as parameters for the run
    run.log_params({**model_params, **training_args})
    
    training_args['output_dir'] = os.path.join('outputs', run_name)
    training_args['overwrite_output_dir'] = True

tezansahu

def trainModel(model_params, training_args, run, run_name):
    training_args['output_dir'] = os.path.join('outputs', run_name)
    training_args['overwrite_output_dir'] = True

    model = ClassificationModel(
        model_params['model_type'], 
        model_params['model_name'], 
        num_labels=3, 
        args=training_args
    )

tezansahu

df = pd.read_csv("all-data.csv", header=None, names=["sentiment", "headline"], encoding = 'ISO-8859-1')

# Inspect the distribution of the number of words in the headlines
# to figure out the max number of tokens to be used by the tokenizer
num_words = df["headline"].apply(lambda x: len(x.split()))
plt.hist(num_words)

# Create labels from the sentiment values
labels = {
    "negative": 0,

tezansahu

import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn.model_selection import train_test_split
from sklearn.metrics import f1_score, accuracy_score

import torch

tezansahu

def loadAnswerSpace() -> List[str]:
    with open(os.path.join("dataset", "answer_space.txt")) as f:
        answer_space = f.read().splitlines()
    return answer_space


  def tokenizeQuestion(text_encoder, question, device) -> Dict:
    tokenizer = transformers.AutoTokenizer.from_pretrained(text_encoder)
    encoded_text = tokenizer(
        text=[question],