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

imbd_data = pd.read_csv('imdb_top_1000.csv')

imbd_data.drop(columns=["Poster_Link"], inplace=True)
imbd_data.drop(columns=["Overview"], inplace=True)

imbd_data["Series_Title"] = imbd_data["Series_Title"].str.lower()
imbd_data["Genre"] = imbd_data["Genre"].str.lower()
imbd_data["Director"] = imbd_data["Director"].str.lower()
imbd_data["Star1"] = imbd_data["Star1"].str.lower()
imbd_data["Star2"] = imbd_data["Star2"].str.lower()
imbd_data["Star3"] = imbd_data["Star3"].str.lower()
imbd_data["Star4"] = imbd_data["Star4"].str.lower()

imbd_data = imbd_data.replace(np.nan, '', regex=True)
imbd_data["Gross"] = imbd_data["Gross"].str.replace(',', '')
imbd_data["Gross"] = pd.to_numeric(imbd_data["Gross"], errors='coerce')

imbd_data = imbd_data.dropna()

data_train, data_test = train_test_split(imbd_data, test_size=230, random_state=1)
data_test, data_dev = train_test_split(data_test, test_size=115, random_state=1)

print("Dataset successfully divided into test/dev/train sets ")
data_test.to_csv("data_test.csv", encoding="utf-8", index=False)
data_dev.to_csv("data_dev.csv", encoding="utf-8", index=False)
data_train.to_csv("data_train.csv", encoding="utf-8", index=False)