Python Programming for Data Science

• Python Exercises
• List Comprehension Exercises
• Pandas Exercises
• Rule-Based Classification I (Persona)
• Rule-Based Classification II (Gezinomi)

Python Exercises

GitHub Repository:

One Example from the Exercises:

Task 7:

3 lists are given below. In the lists, there is a lesson code, credit and quota information, respectively. Print course information using zip().

ders_kodu = ['CMP1005', 'PSY1001', 'HUK1005', 'SEN2204']
kredi = [3, 4, 2, 4]
kontenjan = [30, 75, 150, 25]

Expected Output:

Kredisi 3 olan CMP1005 kodlu dersin kontenjanı 30 kişidir.
Kredisi 4 olan PSY1001 kodlu dersin kontenjanı 75 kişidir.
Kredisi 2 olan HUK1005 kodlu dersin kontenjanı 150 kişidir.
Kredisi 4 olan SEN2204 kodlu dersin kontenjanı 25 kişidir.

📝 Notes

• 'ders_kodu' refers to 'lecture code'
• 'kredi' refers to 'credit'
• 'kontenjan' refers to 'quota'

List Comprehension Exercises

GitHub Repository:

Task 1:

Using the list comprehension structure, capitalize the names of the numeric variables in the 'car_crashes' data and add 'NUM' to the beginning.

import seaborn as sns
df = sns.load_dataset('car_crashes')
df.columns    

Expected Output:

['NUM_TOTAL',
 'NUM_SPEEDING',
 'NUM_ALCOHOL',
 'NUM_NOT_DISTRACTED',
 'NUM_NO_PREVIOUS',
 'NUM_INS_PREMIUM',
 'NUM_INS_LOSSES',
 'ABBREV']

📝 Notes

• All variable names must be uppercase.
• Must be done with a single list comprehension structure.

Task 2:

Using the list comprehension structure, write 'FLAG' at the end of the variables that do not contain 'no' in their names in the 'car_crashes' data.

Expected Output:

['TOTAL_FLAG',
'SPEEDING_FLAG',
'ALCOHOL_FLAG',
'NOT_DISTRACTED',
'NO_PREVIOUS',
'INS_PREMIUM_FLAG',
'INS_LOSSES_FLAG',
'ABBREV_FLAG']

📝 Notes

• All variable names must be uppercase.
• Must be done with a single list comprehension structure.

Task 3:

Using the list comprehension structure, select the names of the variables that are DIFFERENT from the variable names given below and create a new dataframe.

og_list = ['abbrev', 'no_previous']

Expected Output:

📝 Note

• First, create a new list named new_cols using list comprehension according to the list above. Then create a new df by selecting these variables with df[new_cols] and name it new_df.

Requirements

• pandas=1.5.1
• seaborn=0.12.1

Pandas Exercises

GitHub Repository:

Some Examples from the Exercises:

Task 1:

Identify the 'titanic' dataset from the Seaborn library.

Task 2:

Find the number of male and 'female' passengers in the 'titanic' dataset defined above.

Task 3:

Find the number of unique values ​​for each column.

Requirements

• numpy==1.24.3
• pandas==1.5.1
• seaborn==0.12.1

Calculating Lead-Based Returns with Rule-Based Classification using Persona's Dataset

GitHub Repository:

Business Problem
A game company wants to create level-based new customer definitions (personas) by using some features of its customers, and to create segments according to these new customer definitions and to estimate how much the new customers can earn on average according to these segments.

For Example: It is desired to determine how much a 25-year-old male user from Türkiye who is an IOS user can earn on average.

Dataset Story
The persona.csv dataset contains the prices of the products sold by an international game company and some demographic information of the users who buy these products. The dataset consists of records created in each sales transaction. This means that the table is not deduplicated. In other words, a user with certain demographic characteristics may have made more than one purchase.

Variables

• PRICE: Customer spending amount
• SOURCE: The type of device the customer is connecting with
• SEX: Gender of the customer
• COUNTRY: Country of the customer
• AGE: Age of the customer

Before Application Dataset:

Expected Output:

Requirements

• pandas==1.5.1

Calculating Lead-Based Returns with Rule-Based Classification using Gezinomi's Dataset

GitHub Repository:

Business Problem
Gezinomi wants to create new level-based sales definitions by using some of the features of the sales it makes, and to create segments according to these new sales definitions and to estimate how much the new customers can earn on average according to these segments.

For Example: It is desired to determine how much a customer who wants to go to an All Inclusive hotel from Antalya during a busy period can earn on average.

Dataset Story
gezinomi.xlsx dataset contains the prices of the sales made by Gezinomi company and information about these sales. The dataset consists of records created in each sales transaction. This means that the table is not deduplicated. In other words, the customer may have made more than one purchase.

Variables

• SaleId: Sales id
• SaleDate: Sale Date
• CheckInDate: Customer's check-in date
• Price: Price paid for sale
• ConceptName: Hotel concept information
• SaleCityName: The city where the hotel is located
• CInDay: Customer's check-in day
• SaleCheckInDayDiff: Check in and check in date difference
• Season: Season information on the check-in date

Before Application Dataset:

Expected Output:

Requirements

• pandas==1.5.1