python的随机森林在处理训练数据时出现编码问题

[digittube]

请各位帮我看一下这个编码错误，困扰了我一天了。。。

# -*- coding: utf-8 -*-

from __future__ import print_function
import numpy as np
from time import time
from sklearn.datasets import load_svmlight_file
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import train_test_split
#from sklearn.metrics import classification_report
from sklearn import metrics
from sklearn.pipeline import Pipeline
from sklearn.externals import joblib
from sklearn.grid_search import GridSearchCV

import pandas as pd

def get_data(fname):
    content = pd.read_excel(fname, encoding='csc')
    label = content['label']   
    del content ['label']
    feature = pd.DataFrame(content)
    return feature, label

#文件读取与切割
print("Loading data")
t0 = time()
filename = "F:\\textdata\\sample.20160628(labelled).xlsx"

X0,y0 = get_data(filename)
X = X0.values
y = y0.values
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3,random_state=42)

t1 = time()
print("Loading completed, costing %0.3fs" % (t1-t0))

#搭建RandomForest模型
#X_single = X_test[0:1]
clf = RandomForestClassifier(n_estimators = 100)
print("Data Fitting START")
t0 = time()
clf.fit(X_train, y_train)
t1 = time()
print("Fitting completed, costing %0.3fs" % (t1-t0))

#模型测试
print("Model testing START")
t0 = time()
pred = clf.predict(X_test)
t1 = time()
print("Testing completed, costing %0.3fs" % (t1-t0))

#模型评估
accuracy = metrics.accuracy_score(y_test, pred)
print("accuracy_score: %f" % accuracy)
recall = metrics.recall_score(y_test, pred)
print("recall_score: %f" % recall)
print(metrics.classification_report(y_test, pred))

下面是错误信息：

[Doo_Bing]

解决了吗？是不是输入数据文本格式的问题？我也在学sklearn和机器学习。