Python Training Script | Score dataset using bank marking data | Teradata Open Analytics Framework - Run the Python Training Script - Teradata VantageCloud Lake

#!/usr/bin/env python3
import sys
import pandas as pd
import pickle
import xgboost as xgb
def load_data():
    try:
        return pd.read_csv(sys.stdin, delimiter=",", header=None)
    except Exception as e:
        print(e, file=sys.stderr)
        sys.exit(0)
def main():
    df = load_data()
    print(f"Number of columns in df: {len(df.columns)}\n", file=sys.stderr)
    print(f"Number of rows in df: {len(df)}\n", file=sys.stderr)
    if df.empty:
        sys.exit(0)
    category_columns_indices = [1,2,3,4, 6,7,8,10,15]
    for col in category_columns_indices:
        df[col] = df[col].astype('category')
    train = df
    x_train = train.iloc[:, 0:15]
    y_train = train.iloc[:, 16]
    y_train = y_train.map({'yes': 1, 'no': 0})
    dtrain_reg = xgb.DMatrix(x_train, y_train, enable_categorical=True)
    params = {"objective": "binary:hinge",}
    n = 100
    model = xgb.train(
        params=params,
        dtrain=dtrain_reg,
        num_boost_round=n,
    )
    model_file_location = '/lob/model.json'
    model.save_model(model_file_location)
    print(model_file_location)