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
from scipy.cluster.hierarchy import dendrogram, linkage

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[:15]
X = X[["math score", "reading score", "writing score"]].values
labelList = []
for i in X:
    st = ""
    for j in i:
        st += str(j)
        st += ","
    st = "(" + st[:len(st) - 1] + ")"
    labelList.append(st)
linked = linkage(X, 'single')

plt.figure(figsize=(10, 7))
dendrogram(linked,
            orientation='top',
            labels=labelList,
            distance_sort='descending',
            show_leaf_counts=True)
plt.show()