akhilaarekal/ticket-classifier

Input text
    │
    ▼
sentence-transformers (all-MiniLM-L6-v2)
384-dimensional embedding
    │
    ▼
LogisticRegression classifier
    │
    ▼
label + confidence score

from sentence_transformers import SentenceTransformer
import joblib
import numpy as np

# Load models
encoder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
classifier = joblib.load("classifier.joblib")

def predict(text: str) -> dict:
    embedding = encoder.encode([text])
    label = classifier.predict(embedding)[0]
    proba = classifier.predict_proba(embedding)[0]
    confidence = float(np.max(proba))
    return {"label": label, "confidence": round(confidence, 4)}

# Example
result = predict("My laptop screen is flickering and won't turn on")
print(result)
# {"label": "Hardware", "confidence": 0.971}

from sentence_transformers import SentenceTransformer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import f1_score
import mlflow

mlflow.set_experiment("ticket-classifier")

with mlflow.start_run():
    encoder = SentenceTransformer("all-MiniLM-L6-v2")
    embeddings = encoder.encode(texts, batch_size=64)
    
    X_train, X_test, y_train, y_test = train_test_split(
        embeddings, labels, test_size=0.2, 
        random_state=42, stratify=labels
    )
    
    clf = LogisticRegression(max_iter=1000, C=1.0)
    clf.fit(X_train, y_train)
    
    f1 = f1_score(y_test, clf.predict(X_test), average="weighted")
    mlflow.log_metric("f1_weighted", f1)
    # F1: 0.9924