main.py

import pandas as pd
from sklearn.tree import DecisionTreeClassifier

# from matplotlib import pyplot
# import numpy as np
#
# from sklearn.preprocessing import StandardScaler, LabelEncoder
# from sklearn.model_selection import train_test_split
# from sklearn.linear_model import LogisticRegression


csv_file_name = "csv_file/db.csv"

df = pd.read_csv(csv_file_name, encoding='unicode_escape')
# column_headers = list(df.columns.values)
# print("The Column Header Names :", column_headers)
# df_most_profitable_mov = df[['Original Title', 'Gross\xa0USA', 'Gross Worldwide']]
# print(df_most_profitable_mov)

best_rated = df[['Company', 'Rate', 'Metascore']]

# print(best_rated)

X = best_rated.drop(columns=['Company'])
# print(X)
y = best_rated['Company']
# print(Y)


model = DecisionTreeClassifier
model.fit(X, y)