koppd

import pandas as pd
from sklearn.preprocessing import OneHotEncoder, LabelEncoder, StandardScaler

dataset = pd.read_csv("../../data/Karan/DataGenerationRaw/adult.csv")
dataset.drop(labels = ["education"], axis = 1, inplace = True)
dataset.dropna(how = "any", inplace = True)

Y_VAR = "income"

def preprocess_dataset(raw_dataset: pd.DataFrame):

koppd

import numpy as np
import pandas as pd

# Scikit-learn
from sklearn.base import ClassifierMixin
from sklearn.svm import SVC
from sklearn.base import clone
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

george

this is public