7.2 KiB
7.2 KiB
import pandas as pd
import numpy as np
data = pd.read_csv("Customers.csv")
print(data[:10]) CustomerID Gender Age Annual Income ($) Spending Score (1-100) \
0 1 Male 19 15000 39
1 2 Male 21 35000 81
2 3 Female 20 86000 6
3 4 Female 23 59000 77
4 5 Female 31 38000 40
5 6 Female 22 58000 76
6 7 Female 35 31000 6
7 8 Female 23 84000 94
8 9 Male 64 97000 3
9 10 Female 30 98000 72
Profession Work Experience Family Size
0 Healthcare 1 4
1 Engineer 3 3
2 Engineer 1 1
3 Lawyer 0 2
4 Entertainment 2 6
5 Artist 0 2
6 Healthcare 1 3
7 Healthcare 1 3
8 Engineer 0 3
9 Artist 1 4
dataF = data
# Changing words to numbers
mapping = {'NaN' : 0, 'Healthcare' : 1, 'Engineer' : 2, 'Lawyer' : 3, 'Entertainment' : 4, 'Artist' : 5, 'Executive' : 6,
'Doctor' : 7, 'Homemaker' : 8, 'Marketing' : 9}
mapping2 = {'Male' : 0, 'Female' : 1}
dataF = dataF.replace({'Profession': mapping})
dataF = dataF.replace({'Gender': mapping2})
dataF = dataF.drop(columns=['CustomerID'])
# Normalization
dataF['Profession'] = dataF['Profession'].fillna(0)
normalized_dataF = (dataF - dataF.min())/(dataF.max() - dataF.min())
print(normalized_dataF[:10])Gender Age Annual Income ($) Spending Score (1-100) Profession \ 0 0.0 0.191919 0.078958 0.39 0.111111 1 0.0 0.212121 0.184236 0.81 0.222222 2 1.0 0.202020 0.452694 0.06 0.222222 3 1.0 0.232323 0.310569 0.77 0.333333 4 1.0 0.313131 0.200027 0.40 0.444444 5 1.0 0.222222 0.305305 0.76 0.555556 6 1.0 0.353535 0.163180 0.06 0.111111 7 1.0 0.232323 0.442166 0.94 0.111111 8 0.0 0.646465 0.510596 0.03 0.222222 9 1.0 0.303030 0.515860 0.72 0.555556 Work Experience Family Size 0 0.058824 0.375 1 0.176471 0.250 2 0.058824 0.000 3 0.000000 0.125 4 0.117647 0.625 5 0.000000 0.125 6 0.058824 0.250 7 0.058824 0.250 8 0.000000 0.250 9 0.058824 0.375
train_data = normalized_dataF[0:1600]
dev_data = normalized_dataF[1600:1800]
test_data = normalized_dataF[1800:]print(f"Wielkość zbioru Customers: {len(data)} elementów")
print(f"Wielkość zbioru trenującego: {len(train_data)} elementów")
print(f"Wielkość zbioru walidującego: {len(dev_data)} elementów")
print(f"Wielkość zbioru testującego: {len(test_data)} elementów")
print(f" \nDane i wartości na temat zbioru: \n \n {normalized_dataF.describe()}")Wielkość zbioru Customers: 2000 elementów
Wielkość zbioru trenującego: 1600 elementów
Wielkość zbioru walidującego: 200 elementów
Wielkość zbioru testującego: 200 elementów
Dane i wartości na temat zbioru:
Gender Age Annual Income ($) Spending Score (1-100) \
count 2000.000000 2000.000000 2000.000000 2000.000000
mean 0.593000 0.494545 0.582879 0.509625
std 0.491398 0.287169 0.240767 0.279347
min 0.000000 0.000000 0.000000 0.000000
25% 0.000000 0.252525 0.392538 0.280000
50% 1.000000 0.484848 0.579263 0.500000
75% 1.000000 0.737374 0.784806 0.750000
max 1.000000 1.000000 1.000000 1.000000
Profession Work Experience Family Size
count 2000.000000 2000.000000 2000.000000
mean 0.467167 0.241324 0.346062
std 0.250289 0.230718 0.246344
min 0.000000 0.000000 0.000000
25% 0.222222 0.058824 0.125000
50% 0.555556 0.176471 0.375000
75% 0.555556 0.411765 0.500000
max 1.000000 1.000000 1.000000