scratch/debug_ibm2.py

import sys, os, io
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from app.models.text_classifier_ensemble import ensemble_predict

text = """Machine learning is the subset of artificial intelligence (AI) focused on algorithms that can “learn” the patterns of training data and, subsequently, make accurate inferences about new data. This pattern recognition ability enables machine learning models to make decisions or predictions without explicit, hard-coded instructions.

Machine learning has come to dominate the field of AI: it provides the backbone of most modern AI systems, from forecasting models to autonomous vehicles to large language models (LLMs) and other generative AI tools.

The central premise of machine learning (ML) is that if you optimize a model’s performance on a dataset of tasks that adequately resemble the real-world problems it will be used for—through a process called model training—the model can make accurate predictions on the new data it sees in its ultimate use case.

Training itself is simply a means to an end: generalization, the translation of strong performance on training data to useful results in real-world scenarios, is the fundamental goal of machine learning. In essence, a trained model is applying patterns it learned from training data to infer the correct output for a real-world task: the deployment of an AI model is therefore called AI inference.

Deep learning, the subset of machine learning driven by large—or rather, “deep”—artificial neural networks, has emerged over the past few decades as the state-of-the-art AI model architecture across nearly every domain in which AI is used. In contrast to the explicitly defined algorithms of traditional machine learning, deep learning relies on distributed “networks” of mathematical operations that provide an unparalleled ability to learn the intricate nuances of very complex data. Because deep learning requires very large amounts of data and computational resources, its advent has coincided with the escalated importance “big data” and graphics processing units (GPUs).   

The discipline of machine learning is closely intertwined with that of data science. In a sense, machine learning can be understood as a collection of algorithms and techniques to automate data analysis and (more importantly) apply learnings from that analysis to the autonomous execution of relevant tasks.

The origin of the term (albeit not the core concept itself) is often attributed to Arthur L. Samuel’s 1959 article in IBM Journal, “Some Studies in Machine Learning Using the Game of Checkers.” In the paper’s introduction, Samuel neatly articulates machine learning’s ideal outcome: “a computer can be programmed so that it will learn to play a better game of checkers than can be played by the person who wrote the program." """

res = ensemble_predict(text, mode="deep")
print(f"\nFinal AI Prob : {res['ai_probability']:.4f} ({res['ai_probability']*100:.1f}%)")
print(f"Verdict       : {res['verdict']}")
print(f"Layer Scores  : {res['layer_scores']}")