Data Preparation

import pandas as pd, numpy as np, time
from sklearn.model_selection import train_test_split

data = pd.read_csv("flights.csv")
data = data.sample(frac = 0.1, random_state=10)

data = data[["MONTH","DAY","DAY_OF_WEEK","AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT",
                 "ORIGIN_AIRPORT","AIR_TIME", "DEPARTURE_TIME","DISTANCE","ARRIVAL_DELAY"]]
data.dropna(inplace=True)

data["ARRIVAL_DELAY"] = (data["ARRIVAL_DELAY"]>10)*1

cols = ["AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT","ORIGIN_AIRPORT"]
for item in cols:
    data[item] = data[item].astype("category").cat.codes +1
 
train, test, y_train, y_test = train_test_split(data.drop(["ARRIVAL_DELAY"], axis=1), data["ARRIVAL_DELAY"],
                                                random_state=10, test_size=0.25)