thigm85

!pip install numpy pandas pyvespa lightgbm

import json
import lightgbm as lgb
import numpy as np
import pandas as pd

thigm85

!rm -fr lightgbm
vespa_docker.container.stop(timeout=600)
vespa_docker.container.remove()

thigm85

assert features["model_prediction"].tolist() == features["vespa_relevance"].tolist()

thigm85

vespa_relevance = []
for idx, row in features.iterrows():
    vespa_relevance.append(
        compute_vespa_relevance(
            id_value=idx, 
            query_value = row["query(value)"]
        )
    )
features["vespa_relevance"] = vespa_relevance
features

thigm85

def compute_vespa_relevance(id_value, query_value):
    hits = app.query(
        body={
            "yql": "select * from sources * where id = {}".format(str(id_value)),
            "ranking": "classify",
            "ranking.features.query(value)": features.loc[id_value, "query(value)"],
            "hits": 1
        }
    ).hits
    return hits[0]["relevance"]

thigm85

features["model_prediction"] = model.predict(features)
features

thigm85

feed_batch = [
    {
        "id": idx, 
        "fields": {
            "id": idx,
            "numeric": row["attribute(numeric)"], 
            "categorical": row["attribute(categorical)"]
        }
    } for idx, row in features.iterrows()
]

thigm85

from vespa.deployment import VespaDocker

vespa_docker = VespaDocker()
app = vespa_docker.deploy_from_disk(
    application_name="lightgbm", 
    application_root="lightgbm"
)

thigm85

with open("lightgbm/models/lightgbm_model.json", "w") as f:
    json.dump(model.dump_model(), f, indent=2)

thigm85

from pathlib import Path
Path("lightgbm").mkdir(parents=True, exist_ok=True)
app_package.to_files("lightgbm")