误差时通过对AUC分数进行交叉验证，微调随机森林算法的超参数

Question

我试图通过针对AUC分数进行交叉验证来微调随机森林算法的超参数。 在这样做的同时，我遇到了这个错误，我不知道为什么。 x_train数据集：（256，0） y_train数据集：（ 256，） x_test数据集：（86，0） y_test数据集：（86，） 代码：

# importing libraries for data handling and analysis
import pandas as pd
from pandas.plotting import scatter_matrix
from pandas import ExcelWriter
from pandas import ExcelFile
from openpyxl import load_workbook
import numpy as np
from scipy.stats import norm, skew
from scipy import stats
import statsmodels.api as sm
# importing libraries for data visualisations
import seaborn as sns
from matplotlib import pyplot
import matplotlib.pyplot as plt
import matplotlib.pylab as pylab
import matplotlib
color = sns.color_palette()
from IPython.display import display
pd.options.display.max_columns = None
# Standard plotly imports
import plotly
from chart_studio import plotly
import plotly.offline as pyoff
import plotly.graph_objs as go
import plotly.figure_factory as ff
import plotly.graph_objs as go
from plotly.offline import iplot, init_notebook_mode
# Using plotly + cufflinks in offline mode
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import cufflinks as cf
cf.set_config_file(offline=True)
import cufflinks
cufflinks.go_offline(connected=True)
init_notebook_mode(connected=True)
# sklearn modules for preprocessing
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
# from imblearn.over_sampling import SMOTE  # SMOTE
# sklearn modules for ML model selection
from sklearn.model_selection import train_test_split  # import 'train_test_split'
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import RandomizedSearchCV
from sklearn.model_selection import ShuffleSplit
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score

# Libraries for data modelling
from sklearn import svm, tree, linear_model, neighbors
from sklearn import naive_bayes, ensemble, discriminant_analysis, gaussian_process
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from xgboost import XGBClassifier
from sklearn.ensemble import RandomForestClassifier

# Common sklearn Model Helpers
from sklearn import feature_selection
from sklearn import model_selection
from sklearn import metrics
# from sklearn.datasets import make_classification
from sklearn.model_selection import KFold
# sklearn modules for performance metrics
from sklearn.metrics import confusion_matrix, classification_report, precision_recall_curve
from sklearn.metrics import auc, roc_auc_score, roc_curve, recall_score, log_loss
from sklearn.metrics import f1_score, accuracy_score, roc_auc_score, make_scorer
from sklearn.metrics import average_precision_score
# importing misceallenous libraries
import os
import re
import sys
import timeit
import string
from datetime import datetime
from time import time
from dateutil.parser import parse
# ip = get_ipython()
# ip.register_magics(jupyternotify.JupyterNotifyMagics)
from sklearn.model_selection import GridSearchCV


# Read Excel file
df_sourcefile = pd.read_excel(
    'C:/Parth/ChurnPrediciton/not so accurate model/data.xls', sheet_name=0)
df_HR = df_sourcefile.copy()
df_HR.info()
rf_classifier = RandomForestClassifier(class_weight = "balanced",
                                       random_state=7)
target = df_HR['Attrition'].copy()
# let's remove the target feature and redundant features from the dataset
df_HR.drop(['Attrition', 'Total Working Hours', 'Leaves taken',
            'Employee Number'], axis=1, inplace=True)
print('Size of Full dataset is: {}'.format(df_HR.shape))
# Since we have class imbalance (i.e. more employees with turnover=0 than turnover=1)
# let's use stratify=y to maintain the same ratio as in the training dataset when splitting the dataset
X_train, X_test, y_train, y_test = train_test_split(df_HR,
                                                    target,
                                                    test_size=0.25,
                                                    random_state=7,
                                                    stratify=target)
print("Number transactions X_train dataset: ", X_train.shape)
print("Number transactions y_train dataset: ", y_train.shape)
print("Number transactions X_test dataset: ", X_test.shape)
print("Number transactions y_test dataset: ", y_test.shape)
param_grid = {'n_estimators': [50, 75, 100, 125, 150, 175],
              'min_samples_split':[2,4,6,8,10],
              'min_samples_leaf': [1, 2, 3, 4],
              'max_depth': [5, 10, 15, 20, 25]}

grid_obj = GridSearchCV(rf_classifier,
                        iid=True,
                        return_train_score=True,
                        param_grid=param_grid,
                        scoring='roc_auc',
                        cv=10)

grid_fit = grid_obj.fit(X_train, y_train)
rf_opt = grid_fit.best_estimator_

print('='*20)
print("best params: " + str(grid_obj.best_estimator_))
print("best params: " + str(grid_obj.best_params_))
print('best score:', grid_obj.best_score_)
print('='*20)
importances = rf_opt.feature_importances_
indices = np.argsort(importances)[::-1] # Sort feature importances in descending order
names = [X_train.columns[i] for i in indices] # Rearrange feature names so they match the sorted feature importances
plt.figure(figsize=(15, 7)) # Create plot
plt.title("Feature Importance") # Create plot title
plt.bar(range(X_train.shape[1]), importances[indices]) # Add bars
plt.xticks(range(X_train.shape[1]), names, rotation=90) # Add feature names as x-axis labels
plt.show() # Show plot
importances = rf_opt.feature_importances_
df_param_coeff = pd.DataFrame(columns=['Feature', 'Coefficient'])
for i in range(44):
    feat = X_train.columns[i]
    coeff = importances[i]
    df_param_coeff.loc[i] = (feat, coeff)
df_param_coeff.sort_values(by='Coefficient', ascending=False, inplace=True)
df_param_coeff = df_param_coeff.reset_index(drop=True)
df_param_coeff.head(10)
## Confusion Matrix
cnf_matrix = metrics.confusion_matrix(y_test, rf_opt.predict(X_test))
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 of RandomForest Regression Classifier on test set: {:.2f}'.format(rf_opt.score(X_test, y_test)*100))
# Classification report for the optimised RF Regression
rf_opt.fit(X_train, y_train)
print(classification_report(y_test, rf_opt.predict(X_test)))

错误：

非常感谢帮助！！