ium_444421/preparation.ipynb at 05da5fc1b5e0be8b0fabcbe1d3151761a11fc4c6

!kaggle datasets download -d tejashvi14/travel-insurance-prediction-data

!unzip -o travel-insurance-prediction-data.zip

import pandas as pd
travel_insurance=pd.read_csv('TravelInsurancePrediction.csv', index_col=0)
travel_insurance

	Age	Employment Type	GraduateOrNot	AnnualIncome	FamilyMembers	ChronicDiseases	FrequentFlyer	EverTravelledAbroad	TravelInsurance
0	31	Government Sector	Yes	400000	6	1	No	No	0
1	31	Private Sector/Self Employed	Yes	1250000	7	0	No	No	0
2	34	Private Sector/Self Employed	Yes	500000	4	1	No	No	1
3	28	Private Sector/Self Employed	Yes	700000	3	1	No	No	0
4	28	Private Sector/Self Employed	Yes	700000	8	1	Yes	No	0
5	25	Private Sector/Self Employed	No	1150000	4	0	No	No	0
6	31	Government Sector	Yes	1300000	4	0	No	No	0
7	31	Private Sector/Self Employed	Yes	1350000	3	0	Yes	Yes	1
8	28	Private Sector/Self Employed	Yes	1450000	6	1	Yes	Yes	1
9	33	Government Sector	Yes	800000	3	0	Yes	No	0
10	31	Government Sector	Yes	400000	9	1	No	No	0
11	26	Private Sector/Self Employed	Yes	1400000	5	0	Yes	Yes	1
12	32	Government Sector	Yes	850000	6	0	No	No	1
13	31	Government Sector	Yes	1500000	6	0	Yes	Yes	1
14	31	Government Sector	Yes	400000	3	0	No	No	0
15	34	Private Sector/Self Employed	Yes	700000	7	0	No	No	0
16	28	Private Sector/Self Employed	Yes	1150000	4	1	No	No	0
17	28	Private Sector/Self Employed	Yes	800000	7	0	No	No	1
18	29	Private Sector/Self Employed	Yes	1050000	5	1	No	No	1
19	34	Private Sector/Self Employed	Yes	1500000	2	0	Yes	Yes	1
20	28	Private Sector/Self Employed	Yes	1150000	6	0	Yes	No	0
21	29	Private Sector/Self Employed	Yes	350000	3	0	No	No	1
22	31	Private Sector/Self Employed	Yes	1100000	4	0	No	No	0
23	28	Government Sector	Yes	600000	9	0	No	No	1
24	31	Government Sector	Yes	1500000	7	0	Yes	Yes	0
25	35	Private Sector/Self Employed	No	800000	4	0	No	Yes	0
26	34	Private Sector/Self Employed	No	1300000	6	0	Yes	No	1
27	28	Private Sector/Self Employed	Yes	1250000	2	0	Yes	No	0
28	26	Private Sector/Self Employed	Yes	600000	4	0	Yes	No	0
29	31	Private Sector/Self Employed	Yes	900000	3	0	No	No	0
...	...	...	...	...	...	...	...	...	...
1957	31	Private Sector/Self Employed	Yes	1250000	7	0	No	No	0
1958	31	Government Sector	Yes	1300000	3	1	No	No	0
1959	28	Private Sector/Self Employed	No	550000	6	0	No	No	0
1960	28	Government Sector	Yes	300000	6	0	No	No	1
1961	26	Government Sector	Yes	500000	3	0	No	No	0
1962	25	Private Sector/Self Employed	No	1150000	7	0	No	No	0
1963	33	Government Sector	Yes	1100000	4	0	No	No	1
1964	28	Government Sector	Yes	1100000	4	0	No	No	0
1965	30	Private Sector/Self Employed	No	550000	3	0	No	No	1
1966	34	Private Sector/Self Employed	Yes	700000	3	0	Yes	No	0
1967	34	Private Sector/Self Employed	Yes	700000	3	1	No	No	0
1968	28	Government Sector	Yes	300000	5	1	No	No	0
1969	31	Private Sector/Self Employed	Yes	500000	4	1	No	No	0
1970	29	Private Sector/Self Employed	Yes	500000	4	0	No	No	1
1971	31	Private Sector/Self Employed	Yes	950000	5	0	No	No	0
1972	28	Private Sector/Self Employed	Yes	800000	5	1	No	No	0
1973	31	Private Sector/Self Employed	Yes	1350000	3	0	No	Yes	1
1974	28	Private Sector/Self Employed	Yes	1200000	6	0	Yes	No	0
1975	26	Private Sector/Self Employed	Yes	1400000	9	0	No	Yes	1
1976	32	Government Sector	Yes	900000	6	0	No	No	0
1977	25	Private Sector/Self Employed	No	1350000	6	0	No	Yes	1
1978	34	Private Sector/Self Employed	Yes	700000	5	0	No	No	1
1979	28	Private Sector/Self Employed	Yes	1100000	4	1	No	No	0
1980	25	Private Sector/Self Employed	No	1150000	5	1	No	No	0
1981	27	Government Sector	Yes	850000	3	0	No	No	1
1982	33	Private Sector/Self Employed	Yes	1500000	4	0	Yes	Yes	1
1983	28	Private Sector/Self Employed	Yes	1750000	5	1	No	Yes	0
1984	28	Private Sector/Self Employed	Yes	1150000	6	1	No	No	0
1985	34	Private Sector/Self Employed	Yes	1000000	6	0	Yes	Yes	1
1986	34	Private Sector/Self Employed	Yes	500000	4	0	No	No	0

1987 rows × 9 columns

# usunięcie wierszy zawierających braki
travel_insurance.dropna(axis='index', how='any')

# normalizacja danych
for column in travel_insurance.columns:
    if travel_insurance[column].dtype == 'object':
        travel_insurance[column] = travel_insurance[column].str.lower()

travel_insurance

	Age	Employment Type	GraduateOrNot	AnnualIncome	FamilyMembers	ChronicDiseases	FrequentFlyer	EverTravelledAbroad	TravelInsurance
0	31	government sector	yes	400000	6	1	no	no	0
1	31	private sector/self employed	yes	1250000	7	0	no	no	0
2	34	private sector/self employed	yes	500000	4	1	no	no	1
3	28	private sector/self employed	yes	700000	3	1	no	no	0
4	28	private sector/self employed	yes	700000	8	1	yes	no	0
5	25	private sector/self employed	no	1150000	4	0	no	no	0
6	31	government sector	yes	1300000	4	0	no	no	0
7	31	private sector/self employed	yes	1350000	3	0	yes	yes	1
8	28	private sector/self employed	yes	1450000	6	1	yes	yes	1
9	33	government sector	yes	800000	3	0	yes	no	0
10	31	government sector	yes	400000	9	1	no	no	0
11	26	private sector/self employed	yes	1400000	5	0	yes	yes	1
12	32	government sector	yes	850000	6	0	no	no	1
13	31	government sector	yes	1500000	6	0	yes	yes	1
14	31	government sector	yes	400000	3	0	no	no	0
15	34	private sector/self employed	yes	700000	7	0	no	no	0
16	28	private sector/self employed	yes	1150000	4	1	no	no	0
17	28	private sector/self employed	yes	800000	7	0	no	no	1
18	29	private sector/self employed	yes	1050000	5	1	no	no	1
19	34	private sector/self employed	yes	1500000	2	0	yes	yes	1
20	28	private sector/self employed	yes	1150000	6	0	yes	no	0
21	29	private sector/self employed	yes	350000	3	0	no	no	1
22	31	private sector/self employed	yes	1100000	4	0	no	no	0
23	28	government sector	yes	600000	9	0	no	no	1
24	31	government sector	yes	1500000	7	0	yes	yes	0
25	35	private sector/self employed	no	800000	4	0	no	yes	0
26	34	private sector/self employed	no	1300000	6	0	yes	no	1
27	28	private sector/self employed	yes	1250000	2	0	yes	no	0
28	26	private sector/self employed	yes	600000	4	0	yes	no	0
29	31	private sector/self employed	yes	900000	3	0	no	no	0
...	...	...	...	...	...	...	...	...	...
1957	31	private sector/self employed	yes	1250000	7	0	no	no	0
1958	31	government sector	yes	1300000	3	1	no	no	0
1959	28	private sector/self employed	no	550000	6	0	no	no	0
1960	28	government sector	yes	300000	6	0	no	no	1
1961	26	government sector	yes	500000	3	0	no	no	0
1962	25	private sector/self employed	no	1150000	7	0	no	no	0
1963	33	government sector	yes	1100000	4	0	no	no	1
1964	28	government sector	yes	1100000	4	0	no	no	0
1965	30	private sector/self employed	no	550000	3	0	no	no	1
1966	34	private sector/self employed	yes	700000	3	0	yes	no	0
1967	34	private sector/self employed	yes	700000	3	1	no	no	0
1968	28	government sector	yes	300000	5	1	no	no	0
1969	31	private sector/self employed	yes	500000	4	1	no	no	0
1970	29	private sector/self employed	yes	500000	4	0	no	no	1
1971	31	private sector/self employed	yes	950000	5	0	no	no	0
1972	28	private sector/self employed	yes	800000	5	1	no	no	0
1973	31	private sector/self employed	yes	1350000	3	0	no	yes	1
1974	28	private sector/self employed	yes	1200000	6	0	yes	no	0
1975	26	private sector/self employed	yes	1400000	9	0	no	yes	1
1976	32	government sector	yes	900000	6	0	no	no	0
1977	25	private sector/self employed	no	1350000	6	0	no	yes	1
1978	34	private sector/self employed	yes	700000	5	0	no	no	1
1979	28	private sector/self employed	yes	1100000	4	1	no	no	0
1980	25	private sector/self employed	no	1150000	5	1	no	no	0
1981	27	government sector	yes	850000	3	0	no	no	1
1982	33	private sector/self employed	yes	1500000	4	0	yes	yes	1
1983	28	private sector/self employed	yes	1750000	5	1	no	yes	0
1984	28	private sector/self employed	yes	1150000	6	1	no	no	0
1985	34	private sector/self employed	yes	1000000	6	0	yes	yes	1
1986	34	private sector/self employed	yes	500000	4	0	no	no	0

1987 rows × 9 columns

# podział na podzbiory train/dev/test
import sklearn
from sklearn.model_selection import train_test_split
travel_insurance_train, travel_insurance_rest = sklearn.model_selection.train_test_split(travel_insurance, test_size=0.4, random_state=1)
travel_insurance_test, travel_insurance_dev = sklearn.model_selection.train_test_split(travel_insurance_rest, test_size=0.5, random_state=1)

travel_insurance.describe(include='all')

	Age	Employment Type	GraduateOrNot	AnnualIncome	FamilyMembers	ChronicDiseases	FrequentFlyer	EverTravelledAbroad	TravelInsurance
count	1987.0	1987	1988	1.987000e+03	1988.000000	1988.000000	1988	1988	1988.000000
unique	11.0	2	2	NaN	NaN	NaN	2	2	NaN
top	28.0	private sector/self employed	yes	NaN	NaN	NaN	no	no	NaN
freq	506.0	1417	1693	NaN	NaN	NaN	1571	1608	NaN
mean	NaN	NaN	NaN	9.327630e+05	4.753018	0.277666	NaN	NaN	0.357646
std	NaN	NaN	NaN	3.768557e+05	1.609254	0.447960	NaN	NaN	0.479428
min	NaN	NaN	NaN	3.000000e+05	2.000000	0.000000	NaN	NaN	0.000000
25%	NaN	NaN	NaN	6.000000e+05	4.000000	0.000000	NaN	NaN	0.000000
50%	NaN	NaN	NaN	9.000000e+05	5.000000	0.000000	NaN	NaN	0.000000
75%	NaN	NaN	NaN	1.250000e+06	6.000000	1.000000	NaN	NaN	1.000000
max	NaN	NaN	NaN	1.800000e+06	9.000000	1.000000	NaN	NaN	1.000000

# zwracanie informacji o danym zbiorze 

import seaborn as sns

def printInformation(data):
    print(f'Size (rows): {len(data)}\n')
    mean_value = data.mean()
    min_value = data.min(numeric_only=True)
    max_value = data.max(numeric_only=True)
    std_value = data.std()
    median_value = data.median()
    print(f'(mean)\n{mean_value}', f'(min)\n{min_value}', f'(max)\n{max_value}', f'(std)\n{std_value}', f'(median)\n{median_value}', sep="\n\n")
    sns.pairplot(data=data, hue="TravelInsurance")

printInformation(travel_insurance)

Size (rows): 1988

(mean)
Age                    29.650226
AnnualIncome       932762.959235
FamilyMembers           4.753018
ChronicDiseases         0.277666
TravelInsurance         0.357646
dtype: float64

(min)
AnnualIncome       300000.0
FamilyMembers           2.0
ChronicDiseases         0.0
TravelInsurance         0.0
dtype: float64

(max)
AnnualIncome       1800000.0
FamilyMembers            9.0
ChronicDiseases          1.0
TravelInsurance          1.0
dtype: float64

(std)
Age                     2.913308
AnnualIncome       376855.684748
FamilyMembers           1.609254
ChronicDiseases         0.447960
TravelInsurance         0.479428
dtype: float64

(median)
Age                    29.0
AnnualIncome       900000.0
FamilyMembers           5.0
ChronicDiseases         0.0
TravelInsurance         0.0
dtype: float64

printInformation(travel_insurance_train)

Size (rows): 1192

(mean)
Age                    29.744128
AnnualIncome       933095.637584
FamilyMembers           4.814597
ChronicDiseases         0.269295
TravelInsurance         0.349832
dtype: float64

(min)
Age                    25
AnnualIncome       300000
FamilyMembers           2
ChronicDiseases         0
TravelInsurance         0
dtype: int64

(max)
Age                     35
AnnualIncome       1800000
FamilyMembers            9
ChronicDiseases          1
TravelInsurance          1
dtype: int64

(std)
Age                     2.923164
AnnualIncome       376856.587539
FamilyMembers           1.619576
ChronicDiseases         0.443780
TravelInsurance         0.477117
dtype: float64

(median)
Age                    29.0
AnnualIncome       900000.0
FamilyMembers           5.0
ChronicDiseases         0.0
TravelInsurance         0.0
dtype: float64

printInformation(travel_insurance_test)

Size (rows): 397

(mean)
Age                    29.561713
AnnualIncome       916120.906801
FamilyMembers           4.622166
ChronicDiseases         0.287154
TravelInsurance         0.362720
dtype: float64

(min)
Age                    25
AnnualIncome       300000
FamilyMembers           2
ChronicDiseases         0
TravelInsurance         0
dtype: int64

(max)
Age                     35
AnnualIncome       1750000
FamilyMembers            9
ChronicDiseases          1
TravelInsurance          1
dtype: int64

(std)
Age                     2.850544
AnnualIncome       379748.807848
FamilyMembers           1.627824
ChronicDiseases         0.453005
TravelInsurance         0.481392
dtype: float64

(median)
Age                    29.0
AnnualIncome       850000.0
FamilyMembers           4.0
ChronicDiseases         0.0
TravelInsurance         0.0
dtype: float64

printInformation(travel_insurance_dev)

Size (rows): 398

(mean)
Age                    29.457286
AnnualIncome       948366.834171
FamilyMembers           4.698492
ChronicDiseases         0.293970
TravelInsurance         0.374372
dtype: float64

(min)
Age                    25
AnnualIncome       300000
FamilyMembers           2
ChronicDiseases         0
TravelInsurance         0
dtype: int64

(max)
Age                     35
AnnualIncome       1800000
FamilyMembers            9
ChronicDiseases          1
TravelInsurance          1
dtype: int64

(std)
Age                     2.940542
AnnualIncome       374204.238614
FamilyMembers           1.554889
ChronicDiseases         0.456152
TravelInsurance         0.484569
dtype: float64

(median)
Age                     28.0
AnnualIncome       1000000.0
FamilyMembers            4.0
ChronicDiseases          0.0
TravelInsurance          0.0
dtype: float64

655 KiB Raw Blame History Unescape Escape

655 KiB

Raw Blame History