ML задание 2

import pandas as pd
import numpy as np

dataset_array = pd.read_csv(
    'C:\python hz\dataset.csv',
    delimiter=':',
    names=['NameOfUser', 'Q1', 'Q2',
           'Q3', 'Q4', 'Q5', 'Q6', 'Q7', 'Q8',
           'Q9', 'Q10']
)
# ----------------------------------------------------------------------------------------------
# ВОССТАНОВЛЕНИЕ ДАННЫХ

nameList = ['']
for i in range(len(dataset_array)):
    if dataset_array['NameOfUser'][i] not in nameList:
        nameList.append(dataset_array['NameOfUser'][i])
        dataset_array['NameOfUser'][i] = (len(nameList))
    else:
        for j in range(len(nameList)):
            if nameList[j] == dataset_array['NameOfUser'][i]:
                dataset_array['NameOfUser'][i] = j
                break
dataset_array = dataset_array.sort_values('NameOfUser')
for i in range(len(dataset_array)):
    dataset_array['NameOfUser'][i] = 'User' + str(dataset_array['NameOfUser'][i])
# ----------------------------------------------------------------------------------------------
# НОРМАЛИЗАЦИЯ ДАННЫХ

for j in range(1, 11):
    for i in range(len(dataset_array)):
        if int(dataset_array['Q' + str(j)][i]) > 10:
            dataset_array['Q' + str(j)][i] = 10
        elif int(dataset_array['Q' + str(j)][i]) < 1:
            dataset_array['Q' + str(j)][i] = 1
# ----------------------------------------------------------------------------------------------
# ОЧИСТКА ОТ ГРЯЗНЫХ ДАННЫХ

z = 0
for i in range(len(dataset_array)):
    # УДАЛЕНИЕ СТРОК СО ВСЕМИ ОДИНАКОВЫМИ СТОЛБЦАМИ
    for j in range(1, 11):
        if int(dataset_array['Q' + str(j)][i]) == int(dataset_array['Q1'][i]):
            continue
        else:
            z = 1
            break
    if z == 0:
        dataset_array = dataset_array.drop(index=i)
    z = 0
dataset_array = dataset_array.reset_index(drop=True)
# ----------------------------------------------------------------------------------------------
# УДАЛЕНИЕ ДУБЛИРУЮЩИХСЯ СТРОК

stringList = ['']*len(dataset_array)
for i in range(len(dataset_array)):
    thisString = ''
    for j in range(1, 11):
        thisString += str(dataset_array['Q' + str(j)][i])
    if thisString not in stringList:
        stringList[i] = thisString
    else:
        dataset_array = dataset_array.drop(index=i)
    thisString = ''
dataset_array = dataset_array.reset_index(drop=True)
# ----------------------------------------------------------------------------------------------

numberList = [i for i in range(len(dataset_array))]
dataset_array = pd.DataFrame(data=dataset_array, index=numberList)

for i in range(1, 11):
    array = np.array(dataset_array['Q' + str(i)])
    arrayMax = max(array)
    arrayMin = min(array)
    for j in range(len(array)):
        value = str(((array[j]) - arrayMin) / float(arrayMax - arrayMin))
        dataset_array['Q' + str(i)][j] = value[0:8]  # 8 ЗНАКОВ ПОСЛЕ ЗАПЯТОЙ

print(dataset_array)
dataset_array.to_csv('C:\python hz\dataset2.csv', index=False)