التصنيف: Logistic Regression

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

df = pd.read_csv("churn.csv")
df["yearly"] = (df["contract"] == "yearly").astype(int)   # text -> 0/1

features = ["tenure", "bill", "complaints", "data_gb", "yearly"]
X_train, X_test, y_train, y_test = train_test_split(
    df[features], df["churned"], test_size=0.2,
    random_state=42, stratify=df["churned"])   # keep churn ratio equal

model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)

print("Accuracy:", round(model.score(X_test, y_test), 3))

import pandas as pd
from sklearn.linear_model import LogisticRegression

df = pd.read_csv("churn.csv")
df["yearly"] = (df["contract"] == "yearly").astype(int)
features = ["tenure", "bill", "complaints", "data_gb", "yearly"]
model = LogisticRegression(max_iter=1000).fit(df[features], df["churned"])

customers = pd.DataFrame([
    {"tenure": 60, "bill": 250, "complaints": 0, "data_gb": 10, "yearly": 1},
    {"tenure": 4,  "bill": 800, "complaints": 3, "data_gb": 65, "yearly": 0},
])
for i, p in enumerate(model.predict_proba(customers)[:, 1]):
    print(f"Customer {i + 1}: {p:.1%} chance to churn")