import numpy as np
import pandas as pb
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression, Perceptron
from sklearn.neural_network import MLPClassifier, MLPRegressor
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, MinMaxScaler
from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier

df = pb.read_csv("StudentsPerformance.csv", sep=",", encoding="windows-1251")
df1 = df
print("Данные без подготовки:")
with pb.option_context('display.max_rows', None, 'display.max_columns', None, 'display.width', 1000):
    print(df[:5])

def prepareStringData(columnName):
    uniq = df[columnName].unique()
    mp = {}
    for i in uniq:
        mp[i] = len(mp)
    df[columnName] = df[columnName].map(mp)


print()
print("Данные после подготовки:")
prepareStringData("gender")
prepareStringData("race/ethnicity")
prepareStringData("parental level of education")
prepareStringData("lunch")
prepareStringData("test preparation course")
with pb.option_context('display.max_rows', None, 'display.max_columns', None, 'display.width', 1000):
    print(df[:5])

X = df[["gender", "race/ethnicity", "lunch", "test preparation course", "math score", "reading score", "writing score"]]
y = df["parental level of education"]
X_train, X_Test, y_train, y_test = train_test_split(X, y, test_size=0.01, random_state=42)
dtc = DecisionTreeClassifier()
dtc = dtc.fit(X_train, y_train)
dtr = DecisionTreeRegressor()
dtr = dtr.fit(X_train, y_train)
print()
print("Результат дерева класификации на учебных данных: ", dtc.score(X_train, y_train))
print("Результат дерева класификации на тестовых данных: ", dtc.score(X_Test, y_test))
print()
print("Результат дерева регрессии на учебных данных: ", dtr.score(X_train, y_train))
print("Результат дерева регрессии на тестовых данных: ", dtr.score(X_Test, y_test))