Cross-tabulation with crosstab() in Data Analysis Python - Step-by-Step Execution

Concept Flow - Cross-tabulation with crosstab()

Start with DataFrame

↓

Select two columns

↓

Apply pd.crosstab()

↓

Count combinations

↓

Create cross-tab table

↓

Display result

We start with a data table, pick two columns, count how often each pair appears, and show the counts in a new table.

Execution Sample

Data Analysis Python

import pandas as pd

data = {'Gender': ['M', 'F', 'F', 'M', 'F'],
        'Preference': ['Tea', 'Coffee', 'Tea', 'Coffee', 'Tea']}
df = pd.DataFrame(data)

ct = pd.crosstab(df['Gender'], df['Preference'])
print(ct)

This code counts how many males and females prefer Tea or Coffee and shows the counts in a table.

Execution Table

Step	Action	DataFrame State	Cross-tab Result
1	Create DataFrame with Gender and Preference columns	{'Gender': ['M', 'F', 'F', 'M', 'F'], 'Preference': ['Tea', 'Coffee', 'Tea', 'Coffee', 'Tea']}	N/A
2	Select 'Gender' and 'Preference' columns	DataFrame with two columns	N/A
3	Apply pd.crosstab() to count combinations	Same DataFrame	Counts of each Gender-Preference pair
4	Count 'M' with 'Tea' → 1	Same DataFrame	M Tea: 1
5	Count 'M' with 'Coffee' → 2	Same DataFrame	M Coffee: 2
6	Count 'F' with 'Tea' → 2	Same DataFrame	F Tea: 2
7	Count 'F' with 'Coffee' → 1	Same DataFrame	F Coffee: 1
8	Build cross-tab table	Same DataFrame	Table: Coffee Tea F 1 2 M 2 1
9	Print cross-tab table	Same DataFrame	Output displayed
10	End of execution	Same DataFrame	Execution stops

💡 All rows processed, cross-tabulation complete

Variable Tracker

Variable	Start	After Step 1	After Step 3	Final
df	None	{'Gender': ['M', 'F', 'F', 'M', 'F'], 'Preference': ['Tea', 'Coffee', 'Tea', 'Coffee', 'Tea']}	Same DataFrame	Same DataFrame
ct	None	None	Counts of Gender-Preference pairs	Cross-tab table with counts

Key Moments - 2 Insights

Why does the cross-tab table show zeros for some combinations?

Because those Gender-Preference pairs do not appear in the data. For example, if no 'M' prefers 'Juice', that cell is zero. See execution_table step 8 where only existing pairs have counts.

Can crosstab() work with columns that have missing values?

Yes, but missing values are ignored by default. They won't appear in the cross-tab counts unless you specify parameters to include them.

Visual Quiz - 3 Questions

Look at the execution table at step 6, what is the count of females who prefer Tea?

A 1

B 3

C 2

D 0

💡 Hint

Check the 'Cross-tab Result' column at step 6 in the execution_table.

At which step does the cross-tab table get fully built?

A Step 4

B Step 8

C Step 7

D Step 10

💡 Hint

Look for the step where the table with all counts is shown in the execution_table.

If the data had an extra row with Gender 'M' and Preference 'Tea', how would the count at step 4 change?

A It would increase by 1

B It would decrease by 1

C It would stay the same

D It would reset to zero

💡 Hint

Step 4 shows counting 'M' with 'Tea'. Adding one more such row increases the count.

Concept Snapshot

pd.crosstab(index, columns) counts occurrences of combinations between two columns.
Input: two Series or columns from DataFrame.
Output: table with counts for each pair.
Useful for quick frequency tables.
Missing pairs show zero count by default.

Full Transcript

Cross-tabulation with pd.crosstab() takes two columns from a data table and counts how often each pair of values appears together. We start with a DataFrame containing columns like Gender and Preference. Then we select these columns and apply pd.crosstab() to count combinations. The result is a new table showing counts for each Gender-Preference pair. For example, how many males prefer Tea or Coffee. The process counts each pair step-by-step and builds the table. Missing pairs get zero counts. This method helps summarize relationships between two categorical variables quickly.