Khách hàng rời bỏ

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import make_pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_curve, roc_auc_score

subscribers = pd.read_csv("subscribers.csv")
numbers = ["months_subscribed", "boxes_skipped", "complaints", "monthly_price", "delivery_rating"]
text = ["plan", "channel"]
X = subscribers[numbers + text]
y = subscribers["churned"]

# Các luồng xử lý, như trong phần Prepare the Data
number_steps = make_pipeline(SimpleImputer(strategy="median"), StandardScaler())
text_steps = make_pipeline(SimpleImputer(strategy="constant", fill_value="unknown"), OneHotEncoder())
prep = ColumnTransformer([("numbers", number_steps, numbers), ("words", text_steps, text)])

# Các độ sâu của cây cần thử
n = int(input())
depths = []
for i in range(n):
    depths.append(int(input()))

fig, ax = plt.subplots()
ax.set_title("Who Will Cancel?")
ax.set_xlabel("False positive rate")
ax.set_ylabel("Recall")

# Viết code của bạn bên dưới