使用者流失預警—機器學習分類簡單案例分析

該案例主要目的：根據使用者一系列屬性，對使用者是否流失做出合理判斷

1.讀取資料

from __future__ import division
import pandas as pd
import numpy as np
#讀取資料
churn_df = pd.read_csv('churn.csv')
col_names = churn_df.columns.tolist()
#列印列名
print("Column names:")
print(col_names)
#顯示左邊五列和右邊五列資料
to_show = col_names[:6] + col_names[-6:]
#列印前六行
print("\nSample data:")
churn_df[to_show].head(6)
           

• 輸出結果如下：

  

2.資料預處理

#将最後一列标簽字段（字元型）資料類型轉化為數值型
churn_result = churn_df['Churn?']
y = np.where(churn_result == 'True.',1,0)
# 删除無用字段
to_drop = ['State','Area Code','Phone','Churn?']
churn_feat_space = churn_df.drop(to_drop,axis=1)
# 将"Int'l Plan"和"VMail Plan" 兩列轉化為數值型
yes_no_cols = ["Int'l Plan","VMail Plan"]
churn_feat_space[yes_no_cols] = churn_feat_space[yes_no_cols] == 'yes'
# 所有屬性字段名
features = churn_feat_space.columns
X = churn_feat_space.values.astype(np.float)
# 資料标準化
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X = scaler.fit_transform(X)
#顯示記錄數量和特征數量值
print('Feature space holds {} observations and {} features'.format( X.shape[0], X.shape[1]))
print("Unique target labels:", np.unique(y))
print(X[0])
print (len(y[y == 0]))
           

• 輸出結果如下：

  

3.訓練集的交叉驗證

from sklearn.sklearn.model_selection import KFold

def run_cv(X,y,clf_class,**kwargs):
    # 建立一個kfolds對象
    kf = KFold(len(y),n_folds=5,shuffle=True)
    y_pred = y.copy()
    # 對訓練集進行交叉驗證
    for train_index, test_index in kf.split(X)::
        X_train, X_test = X[train_index], X[test_index]
        y_train = y[train_index]
        # 初始化帶有參數的分類器
        clf = clf_class(**kwargs)
        clf.fit(X_train,y_train)
        y_pred[test_index] = clf.predict(X_test)
    return y_pred
           

4.分類模型建構—比較k近鄰、随機森林和支援向量機三個模型

from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier as RF
from sklearn.neighbors import KNeighborsClassifier as KNN

def accuracy(y_true,y_pred):
    # NumPy 可以将boolean類型（True and False）分别轉化為 1. 和 0.,傳回統計名額——精度值
    return np.mean(y_true == y_pred)
print ('Support vector machines:')
print ("%.3f" % accuracy(y, run_cv(X,y,SVC)))
print ("Random forest:")
print ("%.3f" % accuracy(y, run_cv(X,y,RF)))
print ("K-nearest-neighbors:")
print ("%.3f" % accuracy(y, run_cv(X,y,KNN)))
           

5.模型評價

通過函數predict_proba 計算分類器的正确率，根據predict_proba，我們分析不同門檻值下的正确率分數，會發現在某些門檻值下，正确率分數會更高。

def run_prob_cv(X, y, clf_class, **kwargs):
    kf = KFold(n_splits = 5, shuffle = True)
    y_prob = np.zeros((len(y),2))
    for train_index, test_index in kf.split(X):
        X_train, X_test = X[train_index], X[test_index]
        y_train = y[train_index]
        clf = clf_class(**kwargs)
        clf.fit(X_train,y_train)
        # 預測分類機率
        #predict_proba傳回的是一個 n 行 k 列的數組， 第 i 行 第 j 列上的數值是模型預測 第 i 個預測樣本為某個标簽的機率，并且每一行的機率和為1。
        y_prob[test_index] = clf.predict_proba(X_test)
    return y_prob

import warnings
warnings.filterwarnings('ignore')

# Use 10 estimators so predictions are all multiples of 0.1
pred_prob = run_prob_cv(X, y, RF, n_estimators=10)
#print pred_prob[0]
pred_churn = pred_prob[:,1]
is_churn = y == 1

# Number of times a predicted probability is assigned to an observation
counts = pd.value_counts(pred_churn)
#print counts

# 計算機率值
true_prob = {}
for prob in counts.index:
    true_prob[prob] = np.mean(is_churn[pred_churn == prob])
    true_prob = pd.Series(true_prob)

# pandas-fu
counts = pd.concat([counts,true_prob], axis=1).reset_index()
counts.columns = ['pred_prob', 'count', 'true_prob']
counts
           

• 輸出結果如下：

  

6.計算混淆矩陣并可視化

import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.utils.multiclass import unique_labels

def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    # 計算混淆矩陣
    cm = confusion_matrix(y_true, y_pred)
    # 僅适用标簽列
    classes = classes[unique_labels(y_true, y_pred)]
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    print(cm)

    fig, ax = plt.subplots()
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # 顯示橫坐标與縱坐标标簽
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    # 旋轉坐标标簽注釋
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")

    # 設定文本标簽的格式
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", va="center",
                    color="white" if cm[i, j] > thresh else "black")
    fig.tight_layout()
    return ax

plot_confusion_matrix(y, run_cv(X, y, RF), classes=np.array([1, 0]),
                      title='Confusion matrix, without normalization')
plt.show()
           

• 輸出結果

  

參考網站：https://scikit-learn.org/stable/auto_examples/model_selection/plot_confusion_matrix.html#sphx-glr-auto-examples-model-selection-plot-confusion-matrix-py

案例資料下載下傳位址：

連結：https://pan.baidu.com/s/1sHsIet6e7KCU6o7cme8JjQ

提取碼：4ya3