Projet-fianale/RFM.py at main · Damstat/Projet-fianale · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
import pandas as pd
from datetime import timedelta
import matplotlib.pyplot as plt


def build_rfm_base(df):
    """
    Construction de la base RFM (même logique que le notebook)
    """

    df = df.copy()
    df["InvoiceDate"] = pd.to_datetime(df["InvoiceDate"])
    df["Montant"] = df["Quantity"] * df["UnitPrice"]

    # Date de référence (lendemain du dernier achat)
    analysis_date = df["InvoiceDate"].max() + timedelta(days=1)

    rfm = df.groupby("CustomerID").agg({
        "InvoiceDate": lambda x: (analysis_date - x.max()).days,
        "InvoiceNo": "nunique",
        "Montant": "sum"
    }).reset_index()

    rfm.columns = ["CustomerID", "Recence", "Frequence", "Montant"]

    return rfm


def compute_rfm_scores(rfm):
    """
    Calcul des scores R, F et M par quantiles
    """

    rfm = rfm.copy()

    rfm["R_Score"] = pd.qcut(
        rfm["Recence"], 5, labels=[5, 4, 3, 2, 1]
    )

    rfm["F_Score"] = pd.qcut(
        rfm["Frequence"].rank(method="first"), 5, labels=[1, 2, 3, 4, 5]
    )

    rfm["M_Score"] = pd.qcut(
        rfm["Montant"], 5, labels=[1, 2, 3, 4, 5]
    )

    rfm["RFM_Score"] = (
        rfm["R_Score"].astype(int) +
        rfm["F_Score"].astype(int) +
        rfm["M_Score"].astype(int)
    )

    return rfm


def segment_clients(rfm):
    """
    Segmentation RFM (interprétation métier)
    """

    rfm = rfm.copy()

    def segment(row):
        if row["RFM_Score"] >= 13:
            return "Clients Premium"
        elif row["RFM_Score"] >= 10:
            return "Clients Fidèles"
        elif row["RFM_Score"] >= 7:
            return "Clients Potentiels"
        elif row["RFM_Score"] >= 5:
            return "Clients Occasionnels"
        else:
            return "Clients à risque"

    rfm["Segment"] = rfm.apply(segment, axis=1)

    return rfm


def segment_summary(rfm):
    return (
        rfm.groupby("Segment")
        .agg(
            Nb_Clients=("CustomerID", "nunique"),
            Montant_Moyen=("Montant", "mean"),
            Frequence_Moyenne=("Frequence", "mean"),
            Recence_Moyenne=("Recence", "mean")
        )
        .round(1)
        .reset_index()
    )


def plot_rfm_segments(rfm):

    fig, ax = plt.subplots()
    rfm["Segment"].value_counts().plot(
        kind="bar",
        ax=ax
    )

    ax.set_title("Répartition des segments RFM")
    ax.set_xlabel("Segment")
    ax.set_ylabel("Nombre de clients")

    return fig