rfmanalysis 0.1.1

This repository contains a Python implementation of RFM (Recency, Frequency, Monetary) analysis, a customer segmentation technique used in marketing and customer relationship management. The RFM analysis helps identify customer segments based on their purchasing behavior, allowing businesses to tailor their marketing strategies and customer retention efforts.

Here’s the README.md in reStructuredText format:

RFM Analysis

This repository contains a Python implementation of RFM (Recency, Frequency, Monetary) analysis, a customer segmentation technique used in marketing and customer relationship management. The RFM analysis helps identify customer segments based on their purchasing behavior, allowing businesses to tailor their marketing strategies and customer retention efforts.

RFMAnalysis

The RFMAnalysis class provides methods to perform RFM analysis on customer transaction data. Here is an overview of the class and its methods:

### Class Initialization

RFMAnalysis(data, id_col, date_col, revenue_col)

• data: Pandas DataFrame containing customer transaction data.

• id_col: Column name representing the unique customer identifier.

• date_col: Column name representing the transaction date.

• revenue_col: Column name representing the transaction revenue.

### Methods

• create_rfm_columns(): Creates the RFM columns (Recency, Frequency, Monetary) based on the transaction data.

• scale_rfm_columns(): Scales the RFM columns into quartiles (4 segments) for scoring.

• rfm_scores(): Calculates the RFM scores and segments for each customer.

• top_customers(): Sorts the customers by RFM segments in descending order.

• give_names_to_segments(): Assigns segment names to each RFM segment based on the RFM scores.

• segments_distribution(): Returns a DataFrame with the mean RFM values and segment counts.

RFMVisualizer

The RFMVisualizer class provides visualizations for RFM analysis. Here is an overview of the class and its methods:

### Static Methods

• plot_rfm(rfm_data): Plots the distribution of RFM scores.

• visualize_segments(rfm_data): Displays a treemap visualization of customer segments.

• segment_distribution_barplot(rfm_data): Displays a bar chart of segment counts.

• segment_boxplot(rfm_data): Displays boxplots of RFM scores for each segment.

• segment_comparison(rfm_data): Displays bar charts comparing average RFM scores for each segment.

Usage

To use the RFMAnalysis and RFMVisualizer classes, follow these steps:

1. Load the customer transaction data into a Pandas DataFrame.

2. Instantiate the RFMAnalysis class, providing the necessary parameters.

3. Call the methods of the RFMAnalysis class to perform RFM analysis and generate segment information.

4. Instantiate the RFMVisualizer class.

5. Call the visualization methods of the RFMVisualizer class, passing the RFM data generated by the RFMAnalysis class.

Here’s an example of how to use these classes:

import pandas as pd
from RFMAnalysis import RFMAnalysis
from RFMVisualizer import RFMVisualizer

# Load the customer transaction data
data = pd.read_csv('customer_transactions.csv')

# Perform RFM analysis
analysis = RFMAnalysis(data, 'customer_id', 'transaction_date', 'revenue')
analysis.create_rfm_columns()
analysis.scale_rfm_columns()
analysis.rfm_scores()
analysis.top_customers()
analysis.give_names_to_segments()

# Visualize RFM analysis
visualizer = RFMVisualizer()
visualizer.plot_rfm(

analysis.rfm_data)

visualizer.visualize_segments(analysis.rfm_data) visualizer.segment_distribution_barplot(analysis.rfm_data) visualizer.segment_boxplot(analysis.rfm_data) visualizer.segment_comparison(analysis.rfm_data)

Requirements

The implementation requires the following libraries to be installed:

• pandas

• seaborn

• matplotlib

• squarify

You can install them using pip:

pip install pandas seaborn matplotlib squarify

License

This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.

History

0.1.0 (2023-05-16)

• First release on PyPI.