In [12]:
import pandas as pd

df = pd.read_excel('/Users/jr/Jupyter Notebooks/Gathering_Data/customer.xlsx')
df
Out[12]:
ID Sex Number_Children Age Income Own_Car Address Credit_Bureau_Score Buy_Car
0 1 Male 1 25 26000 Yes QC 650 No
1 2 Male 2 37 42000 No QC 800 Yes
2 3 Male 2 27 26500 No QC 650 No
3 4 Male 3 56 77000 Yes Manila 700 Yes
4 5 Female 4 30 32000 No Manila 300 No
5 6 Male 5 30 31500 Yes Taguig 400 No
6 7 Female 3 45 55000 No Taguig 300 Yes
7 8 Female 2 35 37000 No Makati 550 Yes
8 9 Female 1 32 34000 No Marikina 600 Yes
9 10 Male 1 28 28500 Yes Marikina 700 No
10 11 Female 2 27 29000 Yes QC 650 No
11 12 Male 4 26 28500 No QC 300 Yes
12 13 Female 2 54 72000 No QC 450 Yes
13 14 Female 3 48 58000 No Taguig 500 Yes
14 15 Male 4 29 31500 Yes Taguig 700 No
15 16 Male 2 28 33000 Yes Manila 650 No
16 17 Female 1 30 32000 Yes Manila 250 No
17 18 Female 1 30 31500 Yes Manila 345 Yes
18 19 Male 1 30 30000 Yes QC 335 No
19 20 Female 2 30 32000 Yes Makati 300 No
In [17]:
print("#1")

df[0:6]

#1
Out[17]:
ID Sex Number_Children Age Income Own_Car Address Credit_Bureau_Score Buy_Car
0 1 Male 1 25 26000 Yes QC 650 No
1 2 Male 2 37 42000 No QC 800 Yes
2 3 Male 2 27 26500 No QC 650 No
3 4 Male 3 56 77000 Yes Manila 700 Yes
4 5 Female 4 30 32000 No Manila 300 No
5 6 Male 5 30 31500 Yes Taguig 400 No
In [20]:
print("#2")

filter = df.loc[df['Buy_Car']=="Yes"]
filter

#2
Out[20]:
ID Sex Number_Children Age Income Own_Car Address Credit_Bureau_Score Buy_Car
1 2 Male 2 37 42000 No QC 800 Yes
3 4 Male 3 56 77000 Yes Manila 700 Yes
6 7 Female 3 45 55000 No Taguig 300 Yes
7 8 Female 2 35 37000 No Makati 550 Yes
8 9 Female 1 32 34000 No Marikina 600 Yes
11 12 Male 4 26 28500 No QC 300 Yes
12 13 Female 2 54 72000 No QC 450 Yes
13 14 Female 3 48 58000 No Taguig 500 Yes
17 18 Female 1 30 31500 Yes Manila 345 Yes
In [27]:
print("#3")

filter2 = df.loc[df['Buy_Car']=="No"]
filter2[['Age','Income','Number_Children']]

#3
Out[27]:
Age Income Number_Children
0 25 26000 1
2 27 26500 2
4 30 32000 4
5 30 31500 5
9 28 28500 1
10 27 29000 2
14 29 31500 4
15 28 33000 2
16 30 32000 1
18 30 30000 1
19 30 32000 2
In [34]:
print("#4")

final = filter.loc[filter['Income']>30000]
final

#4
Out[34]:
ID Sex Number_Children Age Income Own_Car Address Credit_Bureau_Score Buy_Car
1 2 Male 2 37 42000 No QC 800 Yes
3 4 Male 3 56 77000 Yes Manila 700 Yes
6 7 Female 3 45 55000 No Taguig 300 Yes
7 8 Female 2 35 37000 No Makati 550 Yes
8 9 Female 1 32 34000 No Marikina 600 Yes
12 13 Female 2 54 72000 No QC 450 Yes
13 14 Female 3 48 58000 No Taguig 500 Yes
17 18 Female 1 30 31500 Yes Manila 345 Yes
In [36]:
#5

from pandas import ExcelWriter

writer = ExcelWriter('/Users/jr/Jupyter Notebooks/Gathering_Data/empty.xlsx')
final.to_excel(writer,'Sheet1',index=False)
writer.save()

finaldata = pd.read_excel('/Users/jr/Jupyter Notebooks/Gathering_Data/empty.xlsx')
print(finaldata)

   ID     Sex  Number_Children  Age  Income Own_Car   Address  \
0   2    Male                2   37   42000      No        QC   
1   4    Male                3   56   77000     Yes    Manila   
2   7  Female                3   45   55000      No    Taguig   
3   8  Female                2   35   37000      No    Makati   
4   9  Female                1   32   34000      No  Marikina   
5  13  Female                2   54   72000      No        QC   
6  14  Female                3   48   58000      No    Taguig   
7  18  Female                1   30   31500     Yes    Manila   

   Credit_Bureau_Score Buy_Car  
0                  800     Yes  
1                  700     Yes  
2                  300     Yes  
3                  550     Yes  
4                  600     Yes  
5                  450     Yes  
6                  500     Yes  
7                  345     Yes  

/var/folders/c2/854v91s51m105cd9bkk23cjr0000gn/T/ipykernel_14133/1077981400.py:7: FutureWarning: save is not part of the public API, usage can give unexpected results and will be removed in a future version
  writer.save()
In [ ]: