keithmcnulty

import pandas as pd
from scipy import stats
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import RandomizedSearchCV, KFold
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from xgboost import XGBClassifier

# spit data into train test
def split_data(df: pd.DataFrame, parameters: dict) -> dict:

keithmcnulty

import pandas as pd
import os
import glob
import opendatasets as od

# dataset URL
dataset = 'https://www.kaggle.com/datasets/aashita/nyt-comments/'

# Using opendatasets let's download the data sets (480 MB)
od.download(dataset)