逻辑回归中KFold寻找最优正则化系数C画混淆矩阵以及找最优概率值

lr中通过kfold寻找最优C

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import recall_score
def printing_kfold_scores(x_train_data,y_train_data):
    flod = KFold(5,shuffle=False)
    c_param_range=[0.01,0.1,1,10,100]
    result_table = pd.DataFrame(index = range(len(c_param_range),2),columns=['C_parameter','Mean recall score'])
    result_table['C_parameter']=c_param_range
    j=0
    for c_param in c_param_range:
        print('-------------------------------------------')
        print('C parameter: ', c_param)
        print('-------------------------------------------')
        print('')
        recall_accs = []
        for iteration,indices in enumerate(flod.split(y_train_data),start=1):
            lr=LogisticRegression(C=c_param,penalty='l1')
            lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
            y_pred_undersample =lr.predict(x_train_data.iloc[indices[1],:].values)
            recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)
            recall_accs.append(recall_acc)
            print('Iteration ', iteration,': recall score = ', recall_acc)
        results_table.loc[j,'Mean recall score'] = np.mean(recall_accs)
        j += 1
        print('')
        print('Mean recall score ', np.mean(recall_accs))
        print('')
#     return result_table
    best_c = result_table.loc[results_table['Mean recall score'].astype('float').idxmax()]['C_parameter']
    print('*********************************************************************************')
    print('Best model to choose from cross validation is with C parameter = ', best_c)
    print('*********************************************************************************')
    
    return best_c
best_c = printing_kfold_scores(X_train_undersample,y_train_undersample)

　　

画混淆矩阵部分

def plot_confusion_matrix(cm,classes,title ='Confusion     matrix',cmap=plt.cm.Blues):
    '''画混淆矩阵'''
    plt.imshow(cm,interpolation='nearest',cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=0)
    plt.yticks(tick_marks, classes)
    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
            horizontalalignment="center",
            color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')       

lr中实现混淆矩阵

import itertools
from sklearn.metrics import confusion_matrix
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample = lr.predict(X_test_undersample.values)

# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_pred_undersample)
np.set_printoptions(precision=2)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()

　　

lr通过混淆矩阵找最优概率值

lr = LogisticRegression(C = 0.01, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample_proba = lr.predict_proba(X_test_undersample.values)

thresholds = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]

plt.figure(figsize=(10,10))

j = 1
for i in thresholds:
    y_test_predictions_high_recall = y_pred_undersample_proba[:,1] > i

    plt.subplot(3,3,j)
    j += 1

    # Compute confusion matrix
    cnf_matrix = confusion_matrix(y_test_undersample,y_test_predictions_high_recall)
    np.set_printoptions(precision=2)

    print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
    
    # Plot non-normalized confusion matrix
    class_names = [0,1]
    plot_confusion_matrix(cnf_matrix , classes=class_names , title='Threshold >= %s'%i)