Personal loans are a lucrative revenue stream for banks. The typical interest rate of a two year loan in the United Kingdom is around 10%. This might not sound like a lot, but in September 2022 alone UK consumers borrowed around £1.5 billion, which would mean approximately £300 million in interest generated by banks over two years!
You have been asked to work with a bank to clean and store the data they collected as part of a recent marketing campaign, which aimed to get customers to take out a personal loan. They plan to conduct more marketing campaigns going forward so would like you to set up a PostgreSQL database to store this campaign's data, designing the schema in a way that would allow data from future campaigns to be easily imported.
They have supplied you with a csv file called "bank_marketing.csv", which you will need to clean, reformat, and split, in order to save separate files based on the tables you will create. It is recommended to use pandas for these tasks.
Lastly, you will write the SQL code that the bank can execute to create the tables and populate with the data from the csv files. As the bank are quite strict about their security, you'll save SQL files as multiline string variables that they can then use to create the database on their end.
You have been asked to design a database that will have three tables:
client
| column | data type | description | original column in dataset |
|---|---|---|---|
id | serial | Client ID - primary key | client_id |
age | integer | Client's age in years | age |
job | text | Client's type of job | job |
marital | text | Client's marital status | marital |
education | text | Client's level of education | education |
credit_default | boolean | Whether the client's credit is in default | credit_default |
housing | boolean | Whether the client has an existing housing loan (mortgage) | housing |
loan | boolean | Whether the client has an existing personal loan | loan |
campaign
| column | data type | description | original column in dataset |
|---|---|---|---|
campaign_id | serial | Campaign ID - primary key | N/A - new column |
client_id | serial | Client ID - references id in the client table | client_id |
number_contacts | integer | Number of contact attempts to the client in the current campaign | campaign |
contact_duration | integer | Last contact duration in seconds | duration |
pdays | integer | Number of days since contact in previous campaign (999 = not previously contacted) | pdays |
previous_campaign_contacts | integer | Number of contact attempts to the client in the previous campaign | previous |
previous_outcome | boolean | Outcome of the previous campaign | poutcome |
campaign_outcome | boolean | Outcome of the current campaign | y |
last_contact_date | date | Last date the client was contacted | A combination of day, month, and the newly created year |
economics
| column | data type | description | original column in dataset |
|---|---|---|---|
client_id | serial | Client ID - references id in the client table | client_id |
emp_var_rate | float | Employment variation rate (quarterly indicator) | emp_var_rate |
cons_price_idx | float | Consumer price index (monthly indicator) | cons_price_idx |
euribor_three_months | float | Euro Interbank Offered Rate (euribor) three month rate (daily indicator) | euribor3m |
number_employed | float | Number of employees (quarterly indicator) | nr_employed |
Imported necessary packages
Instruction 1: Read in
bank_marketing.csv
Instruction 2: Split the data into three DataFrames using information provided about the desired tables as your guide: one with information about the
client, another containingcampaigndata, and a third to store information abouteconomicsat the time of the campaign.
- Master DataFrame as
df - Split the DataFrame into the specified DataFrames:
client,campaignandeconomics
import pandas as pd
import numpy as np
df = pd.read_csv('bank_marketing.csv')
print(list(df))
client = df[['client_id', 'age', 'job', 'marital', 'education', 'credit_default', 'housing', 'loan']]
campaign = df[['client_id', 'campaign', 'duration', 'duration', 'pdays', 'previous', 'poutcome', 'y', 'day', 'month']]
economics = df[['client_id', 'emp_var_rate', 'cons_price_idx', 'euribor3m', 'nr_employed']]Instruction 3: Rename the column
"client_id"to"id"inclient(leave as-is in the other subsets);"duration"to"contact_duration","previous"to"previous_campaign_contacts","y"to"campaign_outcome","poutcome"to"previous_outcome", and"campaign"to"number_contacts"incampaign; and"euribor3m"to"euribor_three_months"and"nr_employed"to"number_employed"ineconomics.
client = client.rename(columns = {'client_id':'id'})
campaign = campaign.rename(columns = {
'duration': 'contact_duration',
'previous': 'previous_campaign_contacts',
'y' : 'campaign_outcome',
'poutcome': 'previous_outcome',
'campaign': 'number_contacts'
})
economics = economics.rename(columns = {
'euribor3m': 'euribor_three_months',
'nr_employed': 'number_employed'
})View the three DataFrames
clientcampaigneconomicsInstruction 3: Clean the
"education"column, changing"."to"_"and"unknown"to NumPy's null values.
Instruction 4: Remove periods from the
"job"column.
Instruction 5: Convert
"success"and"failure"in the"previous_outcome"and"campaign_outcome"columns to binary (1or0), along with the changing"nonexistent"to NumPy's null values in"previous_outcome".
Instruction 6: Add a column called
campaign_idincampaign, where all rows have a value of1.
# Education column
client['education'] = client['education'].apply(lambda x: x.replace('.', '_'))
client['education'].replace('unknown', np.nan, inplace=True)
# Job column
client['job'] = client['job'].apply(lambda x: x.replace('.', ''))
# Campaign outcomes
outcome_map = {'success': 1, 'failure': 0, 'non_existent': np.nan, 'yes': 1, 'no': 0}
campaign['previous_outcome'] = campaign['previous_outcome'].map(outcome_map)
campaign['campaign_outcome'] = campaign['campaign_outcome'].map(outcome_map)
# Add column campaign_id into campaign
campaign['campaign_id'] = 1clientcampaignInstruction 7: Create a
datetimecolumn calledlast_contact_date, in the format of"year-month-day", where the year is2022, and the month and day values are taken from the"month"and"day"columns.
# Create late_contact_date of type datetime
campaign['year'] = 2022
campaign['last_contact_date'] = pd.to_datetime(
campaign['year'].astype(str) + '-' +
campaign['month'].astype(str) + '-' +
campaign['day'].astype(str),
errors='coerce'
)