为什么我不能直接使用特征矩阵进行预测？

Question

[已解决]下面的过程是我处理新数据并尝试预测但使用数据和训练模型失败的过程。

首先我导入，

import pandas as pd
from sklearn import preprocessing
import sklearn.model_selection as ms
from sklearn import linear_model
import sklearn.metrics as sklm
import numpy as np
import numpy.random as nr
import matplotlib.pyplot as plt
import seaborn as sns
import scipy.stats as ss
import math

%matplotlib inline

导入数据和数据处理

##test
##prepare test_data
x_test_data = pd.read_csv('AW_test.csv')
x_test_data.loc[:,x_test_data.dtypes==object].isnull().sum()

##dropnan
cols_of_interest = ['Title','MiddleName','Suffix','AddressLine2']
x_test_data.drop(cols_of_interest,axis=1,inplace=True)

##dropduplicate
x_test_data.drop_duplicates(subset = 'CustomerID', keep = 'first', 
inplace=True)
print(x_test_data.shape)

然后我将分类变量特征转换为单热编码矩阵

##change categorical variables to numeric variables
def encode_string(cat_features):
    enc = preprocessing.LabelEncoder()
    enc.fit(cat_features)
    enc_cat_features = enc.transform(cat_features)
    ohe = preprocessing.OneHotEncoder()
    encoded = ohe.fit(enc_cat_features.reshape(-1,1))
    return encoded.transform(enc_cat_features.reshape(-1,1)).toarray()

categorical_columns = 
['CountryRegionName','Education','Occupation','Gender','MaritalStatus']
Features = encode_string(x_test_data['CountryRegionName'])
for col in categorical_columns:
    temp = encode_string(x_test_data[col])
    Features = np.concatenate([Features, temp],axis=1)
print(Features)

然后，我将其余的数字特征添加到矩阵中

##add numeric variables
Features = np.concatenate([Features, 
np.array(x_test_data[['HomeOwnerFlag','NumberCarsOwned',
'TotalChildren','YearlyIncome']])], axis=1)

接下来，我缩放特征矩阵

##scale numeric variables
with open('./lin_reg_scaler.pickle', 'rb') as file:
scaler =pickle.load(file)
Features[:,-5:] = scaler.transform(Features[:,-5:])

我加载我在另一个文件中训练的线性回归模型（如果需要我可以 post 它）

# Loading the saved linear regression model pickle
import pickle
loaded_model = pickle.load(open('./lin_reg_mod.pickle', 'rb'))

我直接把我的特征矩阵放在

#predict
loaded_model.predict(Features)

然而，这就是我得到的

array([-5.71697209e+12, -4.64634881e+12, -4.64634881e+12, -4.64634881e+12,
   -4.64634881e+12, -4.64634881e+12, -5.71697209e+12, -4.64634881e+12,
   -5.71697209e+12, -4.64634881e+12, -5.71697209e+12, -4.64634881e+12,
   -4.64634881e+12, -4.64634881e+12, -5.71697209e+12, -4.64634881e+12,
   -4.64634881e+12, -5.71697209e+12, -5.71697209e+12, -5.71697209e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -4.64634881e+12,
   -4.64634881e+12, -5.71697209e+12, -4.64634881e+12, -5.71697209e+12,
   -5.71697209e+12, -4.64634881e+12, -5.71697209e+12, -5.71697209e+12,
   -4.64634881e+12, -5.71697209e+12, -4.64634881e+12, -5.71697209e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -4.64634881e+12,
   -5.71697209e+12, -5.71697209e+12, -4.64634881e+12, -4.64634881e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -5.71697209e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -4.64634881e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -4.64634881e+12,
   -4.64634881e+12, -5.71697209e+12, -4.64634881e+12, -5.71697209e+12,
   -4.64634881e+12, -4.64634881e+12, -4.64634881e+12, -5.71697209e+12,
   -5.71697209e+12, -5.71697209e+12, -5.71697209e+12, -4.64634881e+12,............

在我的其他文件中，我已经成功地训练了我的模型并使用我的测试数据对其进行了测试。

这是我在该文件中输入 x_test 到我的模型时得到的结果（我想要得到的结果）：

[83.75482221 66.31820493 47.22211384 ... 69.65032224 88.45908874
  58.45193545]

我不知道发生了什么，有人可以帮忙吗

[更新]下面是我训练模型的代码

custs = pd.read_csv('combined_custs.csv')
custs.dtypes

##avemonthspend data
ams = pd.read_csv('AW_AveMonthSpend.csv')
ams.drop_duplicates(subset='CustomerID', keep='first', inplace=True)
##merge
combined_custs=custs.merge(ams)
combined_custs.to_csv('./ams_combined_custs.csv')
combined_custs.head(20)
##change categorical variables to numeric variables
def encode_string(cat_features):
enc = preprocessing.LabelEncoder()
enc.fit(cat_features)
enc_cat_features = enc.transform(cat_features)
ohe = preprocessing.OneHotEncoder()
encoded = ohe.fit(enc_cat_features.reshape(-1,1))
return encoded.transform(enc_cat_features.reshape(-1,1)).toarray()

categorical_columns = 
['CountryRegionName','Education','Occupation','Gender','MaritalStatus']
Features = encode_string(combined_custs['CountryRegionName'])
for col in categorical_columns:
    temp = encode_string(combined_custs[col])
    Features = np.concatenate([Features, temp],axis=1)
print(Features.shape)
print(Features[:2,:])

##add numeric variables
Features = np.concatenate([Features, 


np.array(combined_custs[['HomeOwnerFlag',
'NumberCarsOwned','TotalChildren','YearlyIncome']])], axis=1)

print(Features.shape)
print(Features)

##train_test_split
nr.seed(9988)
labels = np.array(combined_custs['AveMonthSpend'])
indx = range(Features.shape[0])
indx = ms.train_test_split(indx, test_size = 300)
x_train = Features[indx[0],:]
y_train = np.ravel(labels[indx[0]])
x_test = Features[indx[1],:]
y_test = np.ravel(labels[indx[1]])
print(x_test.shape)

##scale numeric variables
scaler = preprocessing.StandardScaler().fit(x_train[:,-5:])

x_train[:,-5:] = scaler.transform(x_train[:,-5:])
x_test[:,-5:] = scaler.transform(x_test[:,-5:])
x_train[:2,]

import pickle
file = open('./lin_reg_scaler.pickle', 'wb')
pickle.dump(scaler, file)
file.close()

##define and fit the linear regression model
lin_mod = linear_model.LinearRegression(fit_intercept=False)
lin_mod.fit(x_train,y_train)
print(lin_mod.intercept_)
print(lin_mod.coef_)

import pickle
file = open('./lin_reg_mod.pickle', 'wb')
pickle.dump(lin_mod, file)
file.close()

lin_mod.predict(x_test)

我的训练模型的预测是：

array([ 78.20673535,  91.11860042,  75.27284767,  63.69507673,
   102.10758616,  74.64252358,  92.84218321,  77.9675721 ,
   102.18989779,  96.98098962,  87.61415378,  39.37006326,
    85.81839618,  78.41392293,  45.49439829,  48.0944897 ,
    36.06024114,  70.03880373, 128.90267485,  54.63235443,
    52.20289729,  82.61123334,  41.58779815,  57.6456416 ,
    46.64014991,  78.38639454,  77.61072157,  94.5899366 ,.....

Answer 1

您在训练和测试中都使用了此方法：

def encode_string(cat_features):
    enc = preprocessing.LabelEncoder()
    enc.fit(cat_features)
    enc_cat_features = enc.transform(cat_features)
    ohe = preprocessing.OneHotEncoder()
    encoded = ohe.fit(enc_cat_features.reshape(-1,1))
    return encoded.transform(enc_cat_features.reshape(-1,1)).toarray()

通过调用：

Features = encode_string(combined_custs['CountryRegionName'])
for col in categorical_columns:
    temp = encode_string(combined_custs[col])
    Features = np.concatenate([Features, temp],axis=1)

但正如我在上面的评论中所说，您需要对测试应用与在训练中相同的预处理。

这里发生的事情是，在测试期间，根据 x_test_data 中数据的顺序，编码会发生变化。因此，也许在训练期间获得数字 0 的字符串值现在获得数字 1，并且最终 Features 中的特征顺序发生变化。

为了解决这个问题，您需要为每一列分别保存LabelEncoder和OneHotEncoder。

所以在训练期间，这样做：

import pickle
def encode_string(cat_features):
    enc = preprocessing.LabelEncoder()
    enc.fit(cat_features)
    enc_cat_features = enc.transform(cat_features)

    # Save the LabelEncoder for this column
    encoder_file = open('./'+cat_features+'_encoder.pickle', 'wb')
    pickle.dump(lin_mod, encoder_file)
    encoder_file.close()

    ohe = preprocessing.OneHotEncoder()
    encoded = ohe.fit(enc_cat_features.reshape(-1,1))

    # Same for OHE
    ohe_file = open('./'+cat_features+'_ohe.pickle', 'wb')
    pickle.dump(lin_mod, ohe_file)
    ohe_file.close()

    return encoded.transform(enc_cat_features.reshape(-1,1)).toarray()

然后，在测试期间：

def encode_string(cat_features):
    # Load the previously saved encoder
    with open('./'+cat_features+'_encoder.pickle', 'rb') as file:
        enc = pickle.load(file)

    # No fitting, only transform
    enc_cat_features = enc.transform(cat_features)

    # Same for OHE
    with open('./'+cat_features+'_ohe.pickle', 'rb') as file:
        enc = pickle.load(file)

    return encoded.transform(enc_cat_features.reshape(-1,1)).toarray()

为什么我不能直接使用特征矩阵进行预测？

Why couldn't I predict directly using Features Matrix?

machine-learning

scikit-learn

edx