News Intelligence Artificielle : Le Guide Ultime 2026

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier

data = {
    "temperature": [60, 80, 90, 30, 50, 95],
    "vibrations": [10, 30, 40, 5, 8, 45],
    "humidite": [20, 40, 50, 10, 12, 55],
    "panne": [0, 1, 1, 0, 0, 1]
}

df = pd.DataFrame(data)
X = df[["temperature", "vibrations", "humidite"]]
y = df["panne"]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

model = DecisionTreeClassifier()
model.fit(X_train, y_train)

prediction = model.predict([[85, 35, 45]])
print("Panne probable :", "Oui" if prediction[0] == 1 else "Non")

from torchvision import models, transforms
from PIL import Image
import torch

model = models.resnet18(pretrained=True)
model.eval()

transform = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor()
])

image = Image.open("outil.jpg")
img_t = transform(image).unsqueeze(0)
output = model(img_t)

_, index = torch.max(output, 1)
print("Classe prédite :", index.item())

from transformers import pipeline

generator = pipeline("text-generation", model="gpt2")
result = generator("L'intelligence artificielle transforme l'industrie", max_length=50)

print(result[0]["generated_text"])

from transformers import pipeline

sentiment = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")

textes = [
    "Très satisfait de l'intervention.",
    "Le dépannage a été trop long.",
    "RAS sur la maintenance."
]

for t in textes:
    print(t, sentiment(t))

import spacy
nlp = spacy.load("fr_core_news_md")

texte = "Intervention du 12/01/2026 sur la machine P-450 au site de Chelles."

doc = nlp(texte)

for ent in doc.ents:
    print(ent.text, "->", ent.label_)

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

data = pd.DataFrame({
    "texte": [
        "Machine à l'arrêt, urgent",
        "Demande de réglage",
        "Maintenance préventive"
    ],
    "categorie": ["urgent", "reglage", "preventif"]
})

pipeline = Pipeline([
    ("tfidf", TfidfVectorizer()),
    ("clf", LogisticRegression())
])

pipeline.fit(data["texte"], data["categorie"])
print(pipeline.predict(["La ligne est stoppée, urgence"]))