#LLM #NLP #ML #AI #PYTHON #PYTORCH

https://xn--r1a.website/DataScienceM

#nlp #natural_language_processing #awesome #transformer #neural_networks #awesome_list #llama #transfer_learning #language_model #attention_mechanism #bert #gpt_2 #xlnet #pre_trained_language_models #gpt_3 #gpt_4 #chatgpt

#nlp #video #reinforcement_learning #deep_learning #neural_network #code #paper #corpus #modelzoo

#python #nlp #data_science #machine_learning #deep_learning #tensorflow #scikit_learn #keras #ml #data_visualization #pytorch #transformer #data_analysis #gpt #automl #jax #data_visualizations #gpt_3 #chatgpt

# Imports and Data
import re
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report
import nltk
from nltk.corpus import stopwords

# You may need to download stopwords for the first time
# nltk.download('stopwords')

# Sample Data (In a real project, load this from a file)
texts = [
    "I love this movie, it's fantastic!",
    "This was a terrible film.",
    "The acting was superb and the plot was great.",
    "I would not recommend this to anyone.",
    "It was an okay movie, not the best but enjoyable.",
    "Absolutely brilliant, a must-see!",
    "A complete waste of time and money.",
    "The story was compelling and engaging."
]
# Labels: 1 for Positive, 0 for Negative
labels = [1, 0, 1, 0, 1, 1, 0, 1]

# Text Preprocessing Function
stop_words = set(stopwords.words('english'))

def preprocess_text(text):
    # Make text lowercase
    text = text.lower()
    # Remove punctuation
    text = re.sub(r'[^\w\s]', '', text)
    # Tokenize and remove stopwords
    tokens = text.split()
    filtered_tokens = [word for word in tokens if word not in stop_words]
    return " ".join(filtered_tokens)

# Apply preprocessing to our dataset
processed_texts = [preprocess_text(text) for text in texts]
print("--- Original vs. Processed ---")
for i in range(3):
    print(f"Original: {texts[i]}")
    print(f"Processed: {processed_texts[i]}\n")

# Splitting data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(
    processed_texts, 
    labels, 
    test_size=0.25, # Use 25% of data for testing
    random_state=42 # for reproducibility
)

print(f"Training samples: {len(X_train)}")
print(f"Testing samples: {len(X_test)}")