ValueError：matmul：输入操作数 1 在其核心维度 0 中不匹配，带有 gufunc 签名 (n?,k),(k,m?)->(n?,m?)

Question

尝试使用我的决策树模型进行预测会在最后一行代码中出现名义错误。

     X=BTC_cleanData[-1:]
---> print(regressor.predict(X))
ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),
(k,m?)->(n?,m?) (size 145 is different from 146)

据我所知，我已经成功地训练和测试了模型，但是当我尝试输出预测时我做错了。我认为我定义要预测的目标的方式是在某处向矩阵添加一列，因此出现 matmul 错误。如何编写有效的预测函数？

这是完整的代码，因为它很长，所以我省略了功能选择：

import pandas as pd
import numpy as np
import talib
import matplotlib.pyplot as plt
%matplotlib inline
import investpy
from investpy import data 
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split

#Import open, high, low, close, volume and Return data from csv using investpy
BTC = data = investpy.get_crypto_historical_data(crypto='bitcoin', from_date='01/01/2014', to_date='06/08/2020')

#Convert Data from Int to Float
BTC.Volume = BTC.Volume.astype(float)
BTC.High = BTC.High.astype(float)
BTC.Low = BTC.Low.astype(float)
BTC.Close = BTC.Close.astype(float)

#Drop Unnecessary Columns
del BTC['Currency']

#Select Indicators as Features
BTC['AD'] = talib.AD(BTC['High'].values, BTC['Low'].values, BTC['Close'].values, BTC['Volume'].values)
...(there is a long list here)

#Create forward looking columns using shift
BTC['NextDayPrice'] = BTC['Close'].shift(-1)

#Copy dataframe and clean data 
BTC_cleanData = BTC.copy()
BTC_cleanData.dropna(inplace=True)
BTC_cleanData.to_csv('C:/Users/Admin/Desktop/BTCdata.csv')

#Split Data into Training and Testing Set
#separate the features and targets into separate datasets.
#split the data into training and testing sets using a 70/30 split 
#Using splicing, separate the features from the target into individual data sets.  
X_all = BTC_cleanData.iloc[:, BTC_cleanData.columns != 'NextDayPrice']  # feature values for all days
y_all = BTC_cleanData['NextDayPrice']  # corresponding targets/labels
print (X_all.head())  # print the first 5 rows

#Split the data into training and testing sets using the given feature as the target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=0.30, random_state=42)

from sklearn.linear_model import LinearRegression


#Create a decision tree regressor and fit it to the training set
regressor = LinearRegression()
regressor.fit(X_train,y_train)

print ("Training set: {} samples".format(X_train.shape[0]))
print ("Test set: {} samples".format(X_test.shape[0]))

#Evaluate Model (out of sample Accuracy and Mean Squared Error)
from sklearn.model_selection import cross_validate
from sklearn.model_selection import cross_val_score

scores = cross_val_score(regressor, X_test, y_test, cv=10)
print ("accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() / 2))    

from sklearn.metrics import mean_squared_error

mse = mean_squared_error(y_test, regressor.predict(X_test))
print("MSE: %.4f" % mse)

#Evaluate Model (In sample Accuracy and Mean Squared Error)
trainscores = cross_val_score(regressor, X_train, y_train, cv=10)
print ("accuracy: %0.2f (+/- %0.2f)" % (trainscores.mean(), trainscores.std() / 2))    

mse = mean_squared_error(y_train, regressor.predict(X_train))
print("MSE: %.4f" % mse)
print(regressor.predict(X_train))

#Predict Next Day Price
X=BTC_cleanData[-1:]
print(regressor.predict(X))

Answer 1

您已经使用 X_train 数据训练了您的模型。要预测看不见的数据，你只需要print(regressor.predict(X_test))。

之前：

X=BTC_cleanData[-1:] # this has one more column compared to X_train and X_test
print(regressor.predict(X))

但BTC_cleanData[-1:] 与 X_train 和 X_test 相比多了一列。但是，模型是使用没有此附加列的X_train 训练的，这会导致错误。

---

干净的工作代码：

import pandas as pd
import numpy as np
import talib
import matplotlib.pyplot as plt
%matplotlib inline
import investpy
from investpy.crypto import get_crypto_historical_data
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import cross_validate
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

#Import open, high, low, close, volume and Return data from csv using investpy
BTC = get_crypto_historical_data(crypto='bitcoin', from_date='01/01/2014', to_date='06/08/2020')

#Convert Data from Int to Float
BTC.Volume = BTC.Volume.astype(float)
BTC.High = BTC.High.astype(float)
BTC.Low = BTC.Low.astype(float)
BTC.Close = BTC.Close.astype(float)

#Drop Unnecessary Columns
del BTC['Currency']

#Select Indicators as Features
BTC['AD'] = talib.AD(BTC['High'].values, BTC['Low'].values, BTC['Close'].values, BTC['Volume'].values)


#Create forward looking columns using shift
BTC['NextDayPrice'] = BTC['Close'].shift(-1)

#Copy dataframe and clean data 
BTC_cleanData = BTC.copy()
BTC_cleanData.dropna(inplace=True)
#BTC_cleanData.to_csv('C:/Users/Admin/Desktop/BTCdata.csv')

#Split Data into Training and Testing Set
#separate the features and targets into separate datasets.
#split the data into training and testing sets using a 70/30 split 
#Using splicing, separate the features from the target into individual data sets.  
X_all = BTC_cleanData.iloc[:, BTC_cleanData.columns != 'NextDayPrice']  # feature values for all days
y_all = BTC_cleanData['NextDayPrice']  # corresponding targets/labels
print (X_all.head())  # print the first 5 rows

#Split the data into training and testing sets using the given feature as the target
X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=0.30, random_state=42)

#Create a decision tree regressor and fit it to the training set
regressor = LinearRegression()
regressor.fit(X_train,y_train)

print ("Training set: {} samples".format(X_train.shape[0]))
print ("Test set: {} samples".format(X_test.shape[0]))

#Evaluate Model (out of sample Accuracy and Mean Squared Error)
scores = cross_val_score(regressor, X_test, y_test, cv=10)
print ("accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() / 2))    

mse = mean_squared_error(y_test, regressor.predict(X_test))
print("MSE: %.4f" % mse)

#Evaluate Model (In sample Accuracy and Mean Squared Error)
trainscores = cross_val_score(regressor, X_train, y_train, cv=10)
print ("accuracy: %0.2f (+/- %0.2f)" % (trainscores.mean(), trainscores.std() / 2))    

mse = mean_squared_error(y_train, regressor.predict(X_train))
print("MSE: %.4f" % mse)
print(regressor.predict(X_train))

#Predict Next Day Price
print(regressor.predict(X_test))