使用决策树和随机森林预测员工离职率

• 我们的任务是帮助人事部门门理解员工为何离职，预测- -个员工离职的可能性.数据来源:

#引入工具包
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as matplot
import seaborn as sns
%matplotlib inline
#读取数据
df = pd.read_csv("./data/HR_comma_sep.csv",index_col = None)
# 数据预处理
#检查数据是否又缺失值
df.isnull().any()
df.head()
#重命名
df.rename(columns=({'satisfaction_level': 'satisfaction', 
                        'last_evaluation': 'evaluation',
                        'number_project': 'projectCount',
                        'average_montly_hours': 'averageMonthlyHours',
                        'time_spend_company': 'yearsAtCompany',
                        'Work_accident': 'workAccident',
                        'promotion_last_5years': 'promotion',
                        'sales' : 'department',
                        'left' : 'turnover'}),inplace=True)
# 将预测标签放第一列
font = df['turnover']
df.drop(labels=['turnover'],axis=1,inplace=True)
df.insert(0,'turnover',font)
df.head()

分析数据

• 14999 条数据,每一条数据包含10个特征
• 总的离职率24%
• 平均满意度0.61

turnover_rate = df.turnover.value_counts()/len(df)
turnover_rate
#显示统计数据
df.describe()

turnover_summary = df.groupby('turnover')
turnover_summary.mean()

相关性分析

---

正相关的特征:

• projectCount VS evaluation: 0.349333
• projectCount VS averageMonthlyHours: 0.417211
• averageMonthlyHours VS evaluation: 0.339742

负相关的特征:

• satisfaction VS turnover: -0.388375

思考:

• 什么特征的影响最大?
• 什么特征之间相关性最大?

# 相关性矩阵
corr = df.corr()
sns.heatmap(corr,xticklabels=corr.columns.values,yticklabels=corr.columns.values)
corr

# 比较离职和未离职员工的满意度
emp_population = df['satisfaction'][df['turnover']==0].mean()
emp_turnover_satisfaction = df[df['turnover']==1]['satisfaction'].mean()

print('未离职员工满意度',emp_population)
print('离职员工满意度',emp_turnover_satisfaction)

model

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import  accuracy_score, classification_report, precision_score, recall_score, confusion_matrix, precision_recall_curve
#将string型转换为整数型
df['department'] = df['department'].astype('category').cat.codes
df['salary'] = df['department'].astype('category').cat.codes

#产生x，y
target_name = 'turnover'
# 产生x,y
y = df['turnover']
x = df.drop('turnover',axis=1)
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.15,random_state=123,stratify=y)
df.head()

决策树

from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report
from sklearn.ensemble import RandomForestClassifier
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier

#决策树
dtree = tree.DecisionTreeClassifier(
    criterion='entropy',
    #max_depth=3, #定义树的深度，可以用来防止过拟合
    min_weight_fraction_leaf=0.01 #定义叶子节点最少需要包含多少个样本(使用百分比表达)，防止过拟合
)
dtree = dtree.fit(x_train,y_train)
print('\n\n---决策树---')
dt_roc_auc = roc_auc_score(y_test,dtree.predict(x_test))
print('决策树的roc_auc_score  ',dt_roc_auc)
print(classification_report(y_test,dtree.predict(x_test)))

随机森林

# 随机森林
rf = RandomForestClassifier(
    criterion = 'entropy',
    n_estimators=1000,
    max_depth=None,  #定义树的深度，可以用来防止过拟合
    min_samples_split=10 # 定义至少多少个样本的情况下才继续分叉
   # min_weight_fraction_leaf=0.01 #定义叶子节点最少需要包含多少个样本(使用百分比表达)，防止过拟合
)
rf.fit(x_train,y_train)
print('\n\n--随机森林--')
rt_roc_auc = roc_auc_score(y_test,rf.predict(x_test))
print('\n\n--随机森林auc--',rt_roc_auc)
print(classification_report(y_test,rf.predict(x_test)))

roc图

from sklearn.metrics import roc_curve
rf_fpr, rf_tpr, rf_thresholds = roc_curve(y_test, rf.predict_proba(x_test)[:,1])
dt_fpr, dt_tpr, dt_thresholds = roc_curve(y_test, dtree.predict_proba(x_test)[:,1])

plt.figure()

# 随机森林 ROC
plt.plot(rf_fpr, rf_tpr, label='Random Forest (area = %0.2f)' % rt_roc_auc)

# 决策树 ROC
plt.plot(dt_fpr, dt_tpr, label='Decision Tree (area = %0.2f)' % dt_roc_auc)

plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Graph')
plt.legend(loc="lower right")
plt.show()

通过决策树分析不同的特征的重要性

## 画出决策树特征的重要性 ##
importances = rf.feature_importances_
feat_names = df.drop(['turnover'],axis=1).columns
indices = np.argsort(importances)[::1]
plt.figure(figsize=(12,6))
plt.title("Feature importances by Decis ionTreeClassifier")
plt.bar(range(len(indices)),importances[indices],color='lightblue',align='center')
plt.step(range(len(indices)),np.cumsum(importances[indices]),where='mid',label='Cumulative')
plt.xticks(range(len(indices)),feat_names[indices],rotation='vertical',fontsize=14)
plt.xlim([-1,len(indices)])
plt.show()

## 画出决策树的特征的重要性 ##
importances = rf.feature_importances_
feat_names = df.drop(['turnover'],axis=1).columns


indices = np.argsort(importances)[::-1]
plt.figure(figsize=(12,6))
plt.title("Feature importances by Decision Tree")
plt.bar(range(len(indices)), importances[indices], color='lightblue',  align="center")
plt.step(range(len(indices)), np.cumsum(importances[indices]), where='mid', label='Cumulative')
plt.xticks(range(len(indices)), feat_names[indices], rotation='vertical',fontsize=14)
plt.xlim([-1, len(indices)])
plt.show()