利用机器学习-随机森林预测客户流失

# 添加了可视化信息 import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import classification_report, confusion_matrix, accuracy_score # 1. 加载数据 data = pd.read_csv("N.csv") # 2. 数据清洗与预处理 data = data.drop(["RowNumber", "CustomerId", "Surname"], axis=1) data = pd.get_dummies(data, columns=["Geography", "Gender"], drop_first=True) X = data.drop("Exited", axis=1) y = data["Exited"] # 3. 划分训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 4. 特征缩放 scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) # 5. 创建随机森林分类器并拟合训练数据 classifier = RandomForestClassifier(n_estimators=100, random_state=42) classifier.fit(X_train, y_train) # 6. 预测测试集 y_pred = classifier.predict(X_test) # 7. 评估模型 print(confusion_matrix(y_test, y_pred)) print(classification_report(y_test, y_pred)) print(accuracy_score(y_test, y_pred)) # 8. 可视化特征重要性 importances = classifier.feature_importances_ indices = np.argsort(importances)[::-1] feature_names = X.columns plt.figure(figsize=(12, 6)) plt.title("Feature importances") plt.bar(range(X_train.shape[1]), importances[indices], color="r", align="center") plt.xticks(range(X_train.shape[1]), feature_names[indices], rotation=90) plt.xlim([-1, X_train.shape[1]]) plt.show() # 9. 可视化混淆矩阵 conf_mat = confusion_matrix(y_test, y_pred) plt.figure(figsize=(8, 6)) sns.heatmap(conf_mat, annot=True, cmap="Blues", fmt="d", cbar=False, xticklabels=[0, 1], yticklabels=[0, 1]) plt.xlabel("Predicted") plt.ylabel("Actual") plt.title("Confusion Matrix") plt.show()