我是Python和机器学习的新手，下周我有一个家庭作业要交。这是我到目前为止的代码：
# to get in-line plots
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import scipy as sp
from scipy import stats
# Load the data
IDnumber = 0000001
np.random.seed(IDnumber)
filename = "ccpp_Data_clean2018.csv"
Data = np.genfromtxt(filename, delimiter=';',skip_header=1)
dataDescription = stats.describe(Data)
print(dataDescription)
Data.shape
#get number of total samples
num_total_samples = Data.shape[0]
print("Total number of samples: "+str(num_total_samples))
#size of each chunk of data for training, validation, testing
size_chunk = int(num_total_samples/3.)
print("Size of each chunk of data: "+str(size_chunk))
#shuffle the data
np.random.shuffle(Data)
#training data
X_training = np.delete(Data[:size_chunk], 4, 1)
Y_training = Data[:size_chunk, 4]
print("Training data input size: "+str(X_training.shape))
print("Training data output size: "+str(Y_training.shape))
#validation data, to be used to choose among different models
X_validation = np.delete(Data[size_chunk:size_chunk*2], 4, 1)
Y_validation = Data[size_chunk:size_chunk*2, 4]
print("Validation data input size: "+str(X_validation.shape))
print("Validation data ouput size: "+str(Y_validation.shape))
#test data, to be used to estimate the true loss of the final model(s)
X_test = np.delete(Data[size_chunk*2:num_total_samples], 4, 1)
Y_test = Data[size_chunk*2: num_total_samples, 4]
print("Test data input size: "+str(X_test.shape))
print("Test data output size: "+str(Y_test.shape))
#scale the data
# standardize the input matrix
from sklearn import preprocessing
scaler = preprocessing.StandardScaler().fit(X_training)
X_training = scaler.transform(X_training)
print("Mean of the training input data:"+str(X_training.mean(axis=0)))
print("Std of the training input data:"+str(X_training.std(axis=0)))
X_validation = scaler.transform(X_validation) # use the same transformation on validation data
print("Mean of the validation input data:"+str(X_validation.mean(axis=0)))
print("Std of the validation input data:"+str(X_validation.std(axis=0)))
X_test = scaler.transform(X_test) # use the same transformation on test data
print("Mean of the test input data:"+str(X_test.mean(axis=0)))
print("Std of the test input data:"+str(X_test.std(axis=0)))
#compute linear regression coefficients for training data
#add a 1 at the beginning of each sample for training, validation, and testing
m_training = # COMPLETE: NUMBER OF POINTS IN THE TRAINING SET
X_training = np.hstack((np.ones((m_training,1)),X_training))
m_validation = # COMPLETE: NUMBER OF POINTS IN THE VALIDATION SET
X_validation = np.hstack((np.ones((m_validation,1)),X_validation))
m_test = # COMPLETE: NUMBER OF POINTS IN THE TEST SET
X_test = np.hstack((np.ones((m_test,1)),X_test))
# Compute the coefficients for linear regression (LR) using linalg.lstsq
w_np, RSStr_np, rank_X_tr, sv_X_tr = #COMPLETE
print("LR coefficients with numpy lstsq: "+ str(w_np))
# compute Residual sums of squares by hand
print("RSS with numpy lstsq: "+str(RSStr_np))
print("Empirical risk with numpy lstsq:"+str(RSStr_np/m_training))
我拆分集合的方式是任务的一部分，我必须预测的数据在最后一列，这就是数据集：http://archive.ics.uci.edu/ml/datasets/Combined+循环+动力+工厂。
我的问题是：在代码的最后部分("完整"行在哪里(，m_training、m_validation和m_test只是对应X的形状？我的意思是：
m_training = X_training.shape
等等。我不确定。最后，在linalg.lstsq函数的输入中，我必须传递哪些参数？
更新我正在继续代码，但我又被卡住了，这次我必须：
#compute predictions on training set, validation set, and test set
prediction_training = # COMPLETE
prediction_validation = # COMPLETE
prediction_test = # COMPLETE
#what about the RSS and loss for points in the validation data?
RSS_validation =# COMPLETE
RSS_test = # COMPLETE
print("RSS on validation data: "+str(RSS_validation))
print("Loss estimated from validation data:"+str(RSS_validation/m_validation))
#another measure of how good our linear fit is given by the following (that is 1 - R^2)
#compute 1 -R^2 for training, validation, and test set
Rmeasure_training = #COMPLETE
Rmeasure_validation = #COMPLETE
Rmeasure_test = #COMPLETE
我发现了很多困难，所以如果你能给我一些好的建议，告诉我在哪里可以找到并学习我需要的东西，我将不胜感激。我有一本课本，但里面没有编程，只有理论。
您可以使用
m_training=len(X_training)
但更好的方法确实是使用形状
X_training.shape
这将返回一个元组(m，n(，其中m是行数，n是列数。然后
m_training = X_training.shape[0]
就是你想要的。事实上，为了在数据的第一行中添加一列1，您需要指示行数。
对于函数linalg.lstsq，您可以查看中的示例：https://docs.scipy.org/doc/numpy-1.15.0/reference/generated/numpy.linalg.lstsq.html
在您的情况下，它应该是：
linalg.lstsq(X_training,y_training)