111_牛客博客

import numpy as np
import pandas as pd
df = pd.read_csv('WA_Fn-UseC_-HR-Employee-Attrition.csv')
df.nunique().nsmallest(10)
df.drop(['StandardHours'], axis=1, inplace=True)
df.drop(['EmployeeCount'], axis=1, inplace=True)
df.drop(['Over18'], axis=1, inplace=True)
df.isnull().sum() 
df[df.duplicated()] 
corrmat = df.corr()
import matplotlib.pyplot as plt
import seaborn as sns

sns.heatmap(corrmat, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 11}, cmap="YlGnBu", 
            linewidths=0.5, linecolor='blue')

h1 = corrmat.loc['Age':'NumCompaniesWorked', 'Age':'NumCompaniesWorked']
h2 = corrmat.loc['PercentSalaryHike':, 'Age':'NumCompaniesWorked']
h3 = corrmat.loc['PercentSalaryHike':, 'PercentSalaryHike':]

sns.set(rc = {'figure.figsize':(15,8)})
sns.heatmap(h1, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 11}, cmap="YlGnBu", 
            linewidths=0.5, linecolor='blue')
sns.heatmap(h2, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 11}, cmap="YlGnBu", 
            linewidths=0.5, linecolor='blue')
sns.heatmap(h3, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 11}, cmap="YlGnBu", 
            linewidths=0.5, linecolor='blue')
df_final = df.drop(['JobLevel','TotalWorkingYears','YearsInCurrentRole', 'YearsWithCurrManager' , 'PercentSalaryHike'], axis=1)
df_final
df_final.columns
# 数据预处理
from sklearn import preprocessing
def preprocessor(df):
    res_df = df.copy()
    le = preprocessing.LabelEncoder()
    
    res_df['BusinessTravel'] = le.fit_transform(res_df['BusinessTravel'])
    res_df['Department'] = le.fit_transform(res_df['Department'])
    res_df['Education'] = le.fit_transform(res_df['Education'])
    res_df['EducationField'] = le.fit_transform(res_df['EducationField'])
    res_df['JobRole'] = le.fit_transform(res_df['JobRole'])
    res_df['Gender'] = le.fit_transform(res_df['Gender'])
    res_df['MaritalStatus'] = le.fit_transform(res_df['MaritalStatus'])
    res_df['OverTime'] = le.fit_transform(res_df['OverTime'])
    res_df['Attrition'] = le.fit_transform(res_df['Attrition'])
    return res_df
encoded_df = preprocessor(df_final)
encoded_df
X = encoded_df.drop(['Attrition'],axis =1)
y = encoded_df['Attrition']
y
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X = sc.fit_transform(X)
mean = np.mean(X, axis=0)
print('均值')
print(mean)
standard_deviation = np.std(X, axis=0)
print('标准差')
print(standard_deviation)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression()
logreg.fit(X_train,y_train)
# 性能分析
# 混淆矩阵
from sklearn import metrics
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import roc_curve, auc

y_pred=logreg.predict(X_test)
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
class_names=[0,1]
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# create heatmap
sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
print("Precision:",metrics.precision_score(y_test, y_pred))
print("Recall:",metrics.recall_score(y_test, y_pred))
# ROC曲线
y_pred_proba = logreg.predict_proba(X_test)[::,1]
fpr, tpr, _ = metrics.roc_curve(y_test,  y_pred_proba)
auc = metrics.roc_auc_score(y_test, y_pred_proba)
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()
from sklearn.svm import SVC
from sklearn import metrics
svc=SVC()
svc.fit(X_train,y_train)
y_pred=svc.predict(X_test)
print('Accuracy Score:')
print(metrics.accuracy_score(y_test,y_pred))
# Linear Kernel
svc=SVC(kernel='linear')
svc.fit(X_train,y_train)
y_pred=svc.predict(X_test)
print('Accuracy Score:')
print(metrics.accuracy_score(y_test,y_pred))
# Polynomial Kernel
svc=SVC(kernel='poly')
svc.fit(X_train,y_train)
y_pred=svc.predict(X_test)
print('Accuracy Score:')
print(metrics.accuracy_score(y_test,y_pred))
# Radial Kernel
svc=SVC(kernel='rbf')
svc.fit(X_train,y_train)
y_pred=svc.predict(X_test)
print('Accuracy Score:')
print(metrics.accuracy_score(y_test,y_pred))
# GridSearchCV优化
svm_model= SVC()
tuned_parameters = {
 'C': (np.arange(2,3,0.1)) , 'kernel': ['linear', 'poly', 'rbf'],
 'C': (np.arange(2,3,0.1)) , 'gamma': [0.01,0.02,0.03,0.04,0.05], 'kernel': ['linear', 'poly', 'rbf'],
 'degree': [2,3,4] ,'gamma':[0.01,0.1,1], 'C':(np.arange(2,3,0.1)) , 'kernel':['poly', 'linear','rbf']
    }
from sklearn.model_selection import GridSearchCV
model_svm = GridSearchCV(svm_model, tuned_parameters,cv=10,scoring='accuracy')
model_svm.fit(X_train, y_train)
print(model_svm.best_score_)
print(model_svm.best_params_)
y_pred=model_svm.predict(X_test)
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
class_names=[0,1] # name  of classes
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# create heatmap
sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
print("Precision:",metrics.precision_score(y_test, y_pred))
print("Recall:",metrics.recall_score(y_test, y_pred))