Summary  
This chapter explains how to group tabular data by multiple dimensions using pandas’ groupby and perform aggregations such as counts and averages to uncover deeper patterns.  

General domain of usage  
Marketing analytics

This video introduces multi-dimensional cohort segmentation, explaining how you can analyze user behavior across more than one attribute—such as combining signup month with acquisition channel or geography. You'll see why adding extra dimensions uncovers deeper business insights, and you'll walk through a practical example using Python and pandas to segment users by both when they signed up and how they were acquired. Real-world cases show how companies use this approach to discover patterns that single-dimensional analysis might miss. Each code sample in video should include no more than 10 lines of code.

Multi-dimensionel kohortesegmentering gør det muligt at gruppere brugere efter mere end ét attribut, såsom både måneden de tilmeldte sig og den kanal, de blev erhvervet gennem. Hvor traditionel kohorteanalyse ofte fokuserer på én enkelt faktor – som tilmeldingsdato – hjælper multi-dimensionel segmentering dig med at besvare mere komplekse spørgsmål. For eksempel kan du undersøge, om brugere fra en bestemt marketingkampagne i en given måned opfører sig anderledes end dem fra en anden kanal eller region. Denne tilgang er værdifuld for virksomheder, fordi den fremhæver mønstre og tendenser, som ikke er synlige ved analyse af kun én dimension. Ved at segmentere kohorter ud fra flere faktorer kan du målrette markedsføringsstrategier, forbedre kundeopbevaring og fordele ressourcer mere effektivt.

import pandas as pd

# Sample data
data = {
    "user_id": [1, 2, 3, 4, 5, 6],
    "signup_date": [
        "2023-01-15", "2023-01-15", "2023-02-10",
        "2023-02-15", "2023-01-25", "2023-02-18"
    ],
    "acquisition_channel": [
        "Email", "Email", "Social", "Ad", "Ad", "Social"
    ]
}

df = pd.DataFrame(data)
df["signup_month"] = pd.to_datetime(df["signup_date"]).dt.to_period("M")

# Multi-dimensional cohort segmentation by signup_month and acquisition_channel
cohorts = df.groupby(["signup_month", "acquisition_channel"])["user_id"].nunique().reset_index()
cohorts = cohorts.rename(columns={"user_id": "num_users"})

print(cohorts)

Ved at segmentere kohorter efter både `signup_month` og `acquisition_channel` kan du identificere skjulte tendenser, som en enkelt-dimensionel analyse måske overser. For eksempel kan du opdage, at brugere erhvervet via **"Email"** i januar er mere engagerede eller har højere fastholdelse end dem, der er erhvervet via **"Ad"** i samme måned. Dette detaljeringsniveau gør det muligt at træffe databaserede beslutninger om, hvor marketingbudgettet skal investeres, hvordan onboarding-oplevelser kan personaliseres, og hvilke kanaler der giver de mest værdifulde kunder. **Multi-dimensionel segmentering** er et effektivt værktøj til at afdække indsigter, der driver forretningsvækst.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import pandas as pd

class TestTask(unittest.TestCase):
    def setUp(self):
        self.expected = pd.DataFrame({
            'signup_month': [pd.Period('2023-01'), pd.Period('2023-01'), pd.Period('2023-01'), pd.Period('2023-02'), pd.Period('2023-02'), pd.Period('2023-02')],
            'acquisition_channel': ['Ad', 'Email', 'Social', 'Ad', 'Email', 'Social'],
            'num_users': [1, 1, 1, 1, 1, 1]
        })
        # Sort for comparison
        self.expected = self.expected.sort_values(['signup_month', 'acquisition_channel']).reset_index(drop=True)

    def test_cohorts_exists_and_type(self):
        import user_code
        importlib.reload(user_code)
        cohorts = getattr(user_code, 'cohorts', None)
        _dynamic_test(
            self,
            cohorts is not None and isinstance(cohorts, pd.DataFrame),
            "The 'cohorts' DataFrame exists and is a pandas DataFrame.",
            "The 'cohorts' DataFrame is missing or not a pandas DataFrame."
        )

    def test_cohorts_columns(self):
        import user_code
        importlib.reload(user_code)
        cohorts = getattr(user_code, 'cohorts', None)
        expected_cols = ['signup_month', 'acquisition_channel', 'num_users']
        _dynamic_test(
            self,
            cohorts is not None and list(cohorts.columns) == expected_cols,
            f"The 'cohorts' DataFrame has correct columns: {expected_cols}.",
            f"The 'cohorts' DataFrame columns are incorrect. Got: {list(cohorts.columns)}"
        )

    def test_cohorts_values(self):
        import user_code
        importlib.reload(user_code)
        cohorts = getattr(user_code, 'cohorts', None)
        # Sort both DataFrames for comparison
        if cohorts is not None:
            cohorts_sorted = cohorts.sort_values(['signup_month', 'acquisition_channel']).reset_index(drop=True)
            # Compare values
            same_shape = cohorts_sorted.shape == self.expected.shape
            same_cols = list(cohorts_sorted.columns) == list(self.expected.columns)
            same_values = cohorts_sorted.equals(self.expected)
            _dynamic_test(
                self,
                same_shape and same_cols and same_values,
                "The 'cohorts' DataFrame has the correct grouped values.",
                f"The grouped values in 'cohorts' are incorrect.\\nExpected:\\n{self.expected}\\nGot:\\n{cohorts_sorted}"
            )
        else:
            _dynamic_test(
                self,
                False,
                "The 'cohorts' DataFrame has the correct grouped values.",
                "The 'cohorts' DataFrame is missing."
            )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()


test_main.py

Behersk kohorteanalyse-teknikker ved hjælp af Python. Dette kursus dækker strukturering af kohortedata, avanceret segmentering, fastholdelsesanalyse og handlingsorienterede forretningsindsigter med praktiske udfordringer i hver sektion.

Lær hvordan man strukturerer, forbehandler og forbereder data til avanceret kohorteanalyse, herunder kohortetildeling og feature engineering.

Dyk ned i avancerede segmenteringsstrategier og beregning af fastholdelsesmetrikker for at afdække dybere indsigter fra kohortedata.

Visualiser kohortedata og udled handlingsorienterede forretningsindsigter ved hjælp af avancerede plot- og fortolkningsteknikker.

Multi-Dimensionel Kohortsegmentering

Løsning