各位大佬，我用训练的模型去预测肿瘤的性质 结果我用性质为良的原数据代进去，为何结果全是恶性的？

# 1获取数据
#     读取的时候加上names
# 2数据处理
#     缺失值处理
# 3划分数据集
# 4特征工程：
#     无量纲化-标准化
# 5逻辑回归预估器
# 6模型评估




import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
# from sklearn.metrics import mean_squared_error
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
# 1读取数据
path = 'https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data'

column_name = ['Sample code number','Clump Thickness'
,'Uniformity of Cell Size','Uniformity of Cell Shape'
,'Marginal Adhesion','Single Epithelial Cell Size'
,'Bare Nuclei','Bland Chromatin','Normal Nucleoli','Mitoses','Class']
data = pd.read_csv(path,names=column_name)

# 2数据处理
#     1替换-》np.nan
data = data.replace(to_replace="?",value=np.nan)
#     2缺失值处理-删除缺失样本
data.dropna(inplace=True)
# print(data.isnull().any())#按列分组 #不存在缺失值

# 3划分数据集
x =data.iloc[:,1:-1]
y =data['Class']
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=22)
# print(x_train)
# 4特征工程：
#     无量纲化-标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)




# 5逻辑回归预估器
estimator = LogisticRegression()#参数按照默认就可以
estimator.fit(x_train,y_train)
# 逻辑回归的模型参数：权重系数和偏置
print('权重系数:\n',estimator.coef_)
print('偏置:\n',estimator.intercept_)


# 6模型评估
# 1直接对比真实值和预测值
y_predict = estimator.predict(x_test)
print('预测：\n', y_predict)
# 2为良性 4为恶性
print('直接对比真实值和预测值：\n',y_test == y_predict)
# 2计算准确率
score = estimator.score(x_test,y_test)
print('准确率为：\n',score)
# error = mean_squared_error(y_test, y_predict)
# print('均方误差为:\n', error)
# 召回率
repotr = classification_report(y_test,y_predict,labels=[2,4],target_names=['良性','恶性'])
print(repotr)
# y_ture:每个样本的真是类别，必须为0（反例），1（正例）标记
# 将y_test 转换成 0 1
y_ture = np.where(y_test > 3,1,0)
y_roc_auc_score = roc_auc_score(y_ture,y_predict)#指标越接近于1，分类器越好，越接近于0.5，越不好
print(y_roc_auc_score)
# 7预测
t0 = [[4,1,1,1,2,1,3,1,1],
      [4,1,1,1,2,1,3,1,1],
      [1,1,1,1,2,1,3,2,1],
      [1,3,1,2,1,2,1,1,1],
      [1,3,3,2,2,1,7,2,1],
      [1,1,4,1,2,1,2,1,1],
      [3,1,1,1,2,3,3,1,1],
      [2,1,1,1,3,1,2,1,1],
      [2,2,2,1,1,1,7,1,1],
      [4,1,1,2,2,1,2,1,1],
      [5,2,1,1,2,1,3,1,1],
      [3,1,1,1,2,2,7,1,1]]
t_predict = estimator.predict(t0)
print('t的预测结果',t_predict)

问题点: 性质为良的原数据误判为恶性.
分析思路: 预测模型的构建过程,数据经过各种预处理, 其中标准化对数据的影响比较大.
解决方案: 两种方法都可以让t的预测结果显示为良性.
①待预测的数据也进行标准化的处理；
②模型的训练过程,数据不作标准化.