Модель логистической регрессии со 100-процентной точностью

Я получил обзоры Amazon для продукта и теперь пытаюсь обучить на нем модель логистической регрессии, чтобы классифицировать отзывы клиентов. Это дает 100-процентную точность. Я не могу понять проблему. Вот образец из моего набора данных:

Вот мой код

import re
import nltk
import numpy as np
import pandas as pd
from bs4 import BeautifulSoup
from nltk.sentiment import SentimentIntensityAnalyzer
from nltk.tokenize import word_tokenize
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from sklearn.model_selection import train_test_split
from sklearn.utils.class_weight import compute_class_weight

# Ensure necessary NLTK datasets and models are downloaded
# nltk.download('punkt')
# nltk.download('vader_lexicon')

# Load the data
df = pd.read_csv("reviews.csv")  # Make sure to replace 'reviews.csv' with your actual file path

# Preprocess data
df['Stars'] = df['Stars'].fillna(3.0)  # Handle missing values
df['Title'] = df['Title'].str.lower()  # Standardize text formats
df['Description'] = df['Description'].str.lower()
df = df.drop(['Name', 'Date'], axis=1)  # Drop unnecessary columns
print(df)


# Categorize sentiment based on star ratings
def categorize_sentiment(stars):
    if stars >= 4.0:
        return 'Positive'
    elif stars <= 2.0:
        return 'Negative'
    else:
        return 'Neutral'


df['Sentiment'] = df['Stars'].apply(categorize_sentiment)


# Clean and tokenize text
def clean_text(text):
    text = BeautifulSoup(text, "html.parser").get_text()
    letters_only = re.sub("[^a-zA-Z]", " ", text)
    return letters_only.lower()


def tokenize(text):
    return word_tokenize(text)


df['Clean_Description'] = df['Description'].apply(clean_text)
df['Tokens'] = df['Clean_Description'].apply(tokenize)

# Apply NLTK's VADER for sentiment analysis
sia = SentimentIntensityAnalyzer()


def get_sentiment(text):
    score = sia.polarity_scores(text)
    if score['compound'] >= 0.05:
        return 'Positive'
    elif score['compound'] <= -0.05:
        return 'Negative'
    else:
        return 'Neutral'


df['NLTK_Sentiment'] = df['Clean_Description'].apply(get_sentiment)
print("df['NLTK_Sentiment'].value_counts()")
print(df['NLTK_Sentiment'].value_counts())

# Prepare data for machine learning
from sklearn.feature_extraction.text import TfidfVectorizer

vectorizer = TfidfVectorizer(tokenizer=tokenize)
X = vectorizer.fit_transform(df['Clean_Description'])
y = df['NLTK_Sentiment'].apply(lambda x: 1 if x == 'Positive' else 0)

# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=80)

# Train a Logistic Regression model

# Compute class weights
class_weights = compute_class_weight('balanced', classes=np.unique(y_train), y=y_train)
class_weights_dict = dict(enumerate(class_weights))
print(f"class_weights_dict {class_weights_dict}")
# Apply to Logistic Regression
# model = LogisticRegression(class_weight=class_weights_dict)
model = LogisticRegression(C=0.001, penalty='l2', class_weight='balanced')

model.fit(X_train, y_train)

# Predict sentiments on the test set
predictions = model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, predictions)
precision = precision_score(y_test, predictions, average='weighted')
recall = recall_score(y_test, predictions, average='weighted')
f1 = f1_score(y_test, predictions, average='weighted')

print(f"Accuracy: {accuracy:.4f}")
print(f"Precision: {precision:.4f}")
print(f"Recall: {recall:.4f}")
print(f"F1 Score: {f1:.4f}")

Вот результаты операторов печати:

НЛТК_Сентимент
Позитив 8000
Негатив 2000
Имя: count, тип d: int64

class_weights_dict {0:2.3696682464454977, 1:0.6337135614702155}
Точность: 1,0000
Точность: 1,0000
Напомним: 1.0000
Оценка F1: 1.0000

Я не могу найти причину, по которой моя модель всегда дает 100-процентную точность.