Examples - FE

Simple Python programs to understand Feature Engineering (FE) clearly.

Program 1: Creating a New Feature

import pandas as pd

data = {
    "Height": [1.70, 1.65, 1.80],
    "Weight": [70, 60, 85]
}

df = pd.DataFrame(data)

# Creating BMI feature
df["BMI"] = df["Weight"] / (df["Height"] ** 2)

print(df)

Output:

Height  Weight        BMI
0    1.70      70  24.221453
1    1.65      60  22.038567
2    1.80      85  26.234568

Output Concept

A new column BMI is created using Height and Weight.

Program 2: Extracting Date Features

import pandas as pd

data = {
    "Order_Date": ["2026-01-15", "2026-03-22", "2026-05-07"]
}

df = pd.DataFrame(data)

df["Order_Date"] = pd.to_datetime(df["Order_Date"])

df["Year"] = df["Order_Date"].dt.year
df["Month"] = df["Order_Date"].dt.month
df["Day"] = df["Order_Date"].dt.day
df["Weekday"] = df["Order_Date"].dt.day_name()

print(df)

Output:

 Order_Date  Year  Month  Day   Weekday
0 2026-01-15  2026      1   15  Thursday
1 2026-03-22  2026      3   22    Sunday
2 2026-05-07  2026      5    7  Thursday

Output Concept

From one date column, we create Year, Month, Day, and Weekday features.

Program 3: Creating Interaction Features

import pandas as pd

data = {
    "Length": [10, 20, 15],
    "Width": [5, 8, 6]
}

df = pd.DataFrame(data)

# Creating area feature
df["Area"] = df["Length"] * df["Width"]

print(df)

Output:

   Length  Width  Area
0      10      5    50
1      20      8   160
2      15      6    90

Output Concept

A new feature Area is created by combining Length and Width.

Program 4: Aggregation Features

import pandas as pd

data = {
    "Customer": ["A", "A", "B", "B", "C"],
    "Purchase_Amount": [1000, 1500, 2000, 2500, 3000]
}

df = pd.DataFrame(data)

customer_summary = df.groupby("Customer")["Purchase_Amount"].agg(
    Total_Spending="sum",
    Average_Spending="mean",
    Purchase_Count="count"
).reset_index()

print(customer_summary)

Output:

  Customer  Total_Spending  Average_Spending  Purchase_Count
0        A            2500            1250.0               2
1        B            4500            2250.0               2
2        C            3000            3000.0               1

Output Concept

Customer-level features like Total Spending, Average Spending, and Purchase Count are created.

Program 5: Binning Numerical Data

import pandas as pd

data = {
    "Age": [15, 22, 35, 48, 67]
}

df = pd.DataFrame(data)

df["Age_Group"] = pd.cut(
    df["Age"],
    bins=[0, 18, 35, 60, 100],
    labels=["Teen", "Young Adult", "Adult", "Senior"]
)

print(df)

Output:

   Age    Age_Group
0   15         Teen
1   22  Young Adult
2   35  Young Adult
3   48        Adult
4   67       Senior

Output Concept

Continuous age values are converted into age groups.

Program 6: Complete Feature Engineering Example

import pandas as pd

data = {
    "Name": ["John", "Alex", "Ravi"],
    "Height": [1.70, 1.65, 1.80],
    "Weight": [70, 60, 85],
    "Join_Date": ["2024-01-10", "2024-03-15", "2024-05-20"],
    "Salary": [50000, 60000, 90000]
}

df = pd.DataFrame(data)

# BMI feature
df["BMI"] = df["Weight"] / (df["Height"] ** 2)

# Date features
df["Join_Date"] = pd.to_datetime(df["Join_Date"])
df["Join_Year"] = df["Join_Date"].dt.year
df["Join_Month"] = df["Join_Date"].dt.month

# Salary category
df["Salary_Level"] = pd.cut(
    df["Salary"],
    bins=[0, 55000, 80000, 150000],
    labels=["Low", "Medium", "High"]
)

print(df)

Output:

  Name  Height  Weight  Join_Date  Salary        BMI  Join_Year  Join_Month  \
0  John    1.70      70 2024-01-10   50000  24.221453       2024           1   
1  Alex    1.65      60 2024-03-15   60000  22.038567       2024           3   
2  Ravi    1.80      85 2024-05-20   90000  26.234568       2024           5   

  Salary_Level  
0          Low  
1       Medium  
2         High  

Output Concept

This program creates multiple useful features from raw data:

• BMI
• Join Year
• Join Month
• Salary Level

Keywords

Feature Engineering Programs, Feature Engineering using Python, Feature Engineering using Pandas, Python Feature Engineering Tutorial, Feature Creation in Python, Date Feature Extraction Python, Aggregation Features Python, Interaction Features Python, Data Binning in Python, Machine Learning Feature Engineering Programs