Date feature extraction in Data Analysis Python - Step-by-Step Execution

Concept Flow - Date feature extraction

Start with Date Column

↓

Extract Year

↓

Extract Month

↓

Extract Day

↓

Extract Weekday

↓

Add Features to DataFrame

↓

End

We start with a date column, then extract year, month, day, and weekday features step-by-step, adding them to the data.

Execution Sample

Data Analysis Python

import pandas as pd

df = pd.DataFrame({'date': pd.to_datetime(['2024-01-01', '2024-06-15', '2024-12-31'])})
df['year'] = df['date'].dt.year
df['month'] = df['date'].dt.month
df['day'] = df['date'].dt.day
df['weekday'] = df['date'].dt.day_name()

This code creates a DataFrame with dates and extracts year, month, day, and weekday names as new columns.

Execution Table

Step	Action	Date Value	Extracted Year	Extracted Month	Extracted Day	Extracted Weekday	DataFrame State
1	Start with date '2024-01-01'	2024-01-01					{'date': '2024-01-01'}
2	Extract year	2024-01-01	2024				{'date': '2024-01-01', 'year': 2024}
3	Extract month	2024-01-01	2024	1			{'date': '2024-01-01', 'year': 2024, 'month': 1}
4	Extract day	2024-01-01	2024	1	1		{'date': '2024-01-01', 'year': 2024, 'month': 1, 'day': 1}
5	Extract weekday	2024-01-01	2024	1	1	Monday	{'date': '2024-01-01', 'year': 2024, 'month': 1, 'day': 1, 'weekday': 'Monday'}
6	Repeat for '2024-06-15'	2024-06-15	2024	6	15	Saturday	{...second row added with extracted features...}
7	Repeat for '2024-12-31'	2024-12-31	2024	12	31	Tuesday	{...third row added with extracted features...}
8	Final DataFrame with all features						{'date': [...], 'year': [...], 'month': [...], 'day': [...], 'weekday': [...]}

💡 All dates processed; features extracted and added to DataFrame.

Variable Tracker

Variable	Start	After 1	After 2	After 3	Final
df['date']	empty	2024-01-01	2024-06-15	2024-12-31	[2024-01-01, 2024-06-15, 2024-12-31]
df['year']	empty	2024	2024	2024	[2024, 2024, 2024]
df['month']	empty	1	6	12	[1, 6, 12]
df['day']	empty	1	15	31	[1, 15, 31]
df['weekday']	empty	Monday	Saturday	Tuesday	[Monday, Saturday, Tuesday]

Key Moments - 3 Insights

Why do we use 'dt' before year, month, day, and weekday?

The 'dt' accessor tells pandas we want to extract parts of a datetime object. Without 'dt', pandas can't access date features. See execution_table steps 2-5.

What happens if the date column is not in datetime format?

Extraction will fail or give errors because pandas needs datetime type to extract features. We convert with pd.to_datetime first (see execution_sample line 3).

Why is weekday extracted as a name, not a number?

Using 'day_name()' gives a friendly weekday name like 'Monday'. You can also use 'dt.weekday' for numbers 0-6. See execution_table step 5.

Visual Quiz - 3 Questions

Look at the variable_tracker table, what is the value of df['month'] after processing the second date?

A [1, 6, 12]

B 6

C [1, 6]

D 15

💡 Hint

Check the 'df["month"]' row and the 'After 2' column in variable_tracker.

According to the execution_table, what weekday is extracted for the date '2024-12-31'?

A Tuesday

B Saturday

C Monday

D Sunday

💡 Hint

Look at step 7 in execution_table under 'Extracted Weekday'.

If the date column was not converted to datetime first, what would happen?

A Extraction works normally

B Only year is extracted

C Extraction fails or errors occur

D Weekday is extracted as number

💡 Hint

Refer to key_moments question about datetime conversion.

Concept Snapshot

Date feature extraction:
- Use pandas 'dt' accessor on datetime column
- Extract year, month, day, weekday easily
- Convert column to datetime first with pd.to_datetime
- Add extracted features as new DataFrame columns
- Useful for time-based analysis and modeling

Full Transcript

This visual execution shows how to extract features from a date column in pandas. We start with a DataFrame containing dates. Using the 'dt' accessor, we extract year, month, day, and weekday name from each date. These features are added as new columns to the DataFrame. The execution table traces each step for each date, showing how the DataFrame grows. The variable tracker shows how each column changes after processing each date. Key moments clarify why the 'dt' accessor is needed and why datetime conversion is important. The quiz tests understanding of the extracted values and common pitfalls. This method helps turn raw dates into useful features for data analysis.