Python 中的简单线性回归
Simple Linear Regression in Python
我正在尝试实现此算法以找到单个变量的截距和斜率：
这是我的 Python 代码，用于更新截距和斜率。但它不收敛。 RSS 随着迭代而增加而不是减少，并且在一些迭代之后它变得无限大。我在执行 algorithm.How 时没有发现任何错误 我可以解决这个问题吗？我也附上了 csv 文件。
这是代码。
import pandas as pd
import numpy as np
#Defining gradient_decend
#This Function takes X value, Y value and vector of w0(intercept),w1(slope)
#INPUT FEATURES=X(sq.feet of house size)
#TARGET VALUE=Y (Price of House)
#W=np.array([w0,w1]).reshape(2,1)
#W=[w0,
# w1]
def gradient_decend(X,Y,W):
intercept=W[0][0]
slope=W[1][0]
#Here i will get a list
#list is like this
#gd=[sum(predicted_value-(intercept+slope*x)),
# sum(predicted_value-(intercept+slope*x)*x)]
gd=[sum(y-(intercept+slope*x) for x,y in zip(X,Y)),
sum(((y-(intercept+slope*x))*x) for x,y in zip(X,Y))]
return np.array(gd).reshape(2,1)
#Defining Resudual sum of squares
def RSS(X,Y,W):
return sum((y-(W[0][0]+W[1][0]*x))**2 for x,y in zip(X,Y))
#Reading Training Data
training_data=pd.read_csv("kc_house_train_data.csv")
#Defining fixed parameters
#Learning Rate
n=0.0001
iteration=1500
#Intercept
w0=0
#Slope
w1=0
#Creating 2,1 vector of w0,w1 parameters
W=np.array([w0,w1]).reshape(2,1)
#Running gradient Decend
for i in range(iteration):
W=W+((2*n)* (gradient_decend(training_data["sqft_living"],training_data["price"],W)))
print RSS(training_data["sqft_living"],training_data["price"],W)
Here 是 CSV 文件。
首先，我发现在编写机器学习代码时，最好不要使用复杂的列表理解，因为任何可以迭代的东西，
- 正常循环和缩进时写起来更容易阅读and/or
- 可以用numpy broadcasting
来完成
并且使用适当的变量名可以帮助您更好地理解代码。仅当您擅长数学时，使用 Xs、Ys、Ws 作为简写形式才不错。就个人而言，我不会在代码中使用它们，尤其是在 python 中编写时。来自 import this：显式优于隐式。
我的经验法则是记住，如果我编写的代码在 1 周后仍无法阅读，那么它就是糟糕的代码。
首先，我们来决定梯度下降的输入参数是什么，你需要：
- feature_matrix（
X矩阵，类型：numpy.array，一个N * D大小的矩阵，其中N是第. of rows/datapoints 和 D 是 columns/features) 的编号
- 输出（
Y向量，类型：numpy.array，大小为N的向量）
- initial_weights（类型：
numpy.array，大小为 D 的向量）。
此外，要检查是否收敛，您需要：
- step_size（遍历改变权重时的变化幅度；类型：
float，一般为小数）
- tolerance（打破迭代的标准，当梯度幅度小于tolerance时，假设你的权重已经收敛，输入：
float，通常是数字小但比步长大得多）。
现在开始编写代码。
def regression_gradient_descent(feature_matrix, output, initial_weights, step_size, tolerance):
converged = False # Set a boolean to check for convergence
weights = np.array(initial_weights) # make sure it's a numpy array
while not converged:
# compute the predictions based on feature_matrix and weights.
# iterate through the row and find the single scalar predicted
# value for each weight * column.
# hint: a dot product can solve this easily
predictions = [??? for row in feature_matrix]
# compute the errors as predictions - output
errors = predictions - output
gradient_sum_squares = 0 # initialize the gradient sum of squares
# while we haven't reached the tolerance yet, update each feature's weight
for i in range(len(weights)): # loop over each weight
# Recall that feature_matrix[:, i] is the feature column associated with weights[i]
# compute the derivative for weight[i]:
# Hint: the derivative is = 2 * dot product of feature_column and errors.
derivative = 2 * ????
# add the squared value of the derivative to the gradient magnitude (for assessing convergence)
gradient_sum_squares += (derivative * derivative)
# subtract the step size times the derivative from the current weight
weights[i] -= (step_size * derivative)
# compute the square-root of the gradient sum of squares to get the gradient magnitude:
gradient_magnitude = ???
# Then check whether the magnitude is lower than the tolerance.
if ???:
converged = True
# Once it while loop breaks, return the loop.
return(weights)
希望扩展pseudo-code能帮助你更好地理解梯度下降。 ??? 为了不破坏你的作业，我就不填了。
请注意，您的 RSS 代码也不可读且无法维护。这样做更容易：
>>> import numpy as np
>>> prediction = np.array([1,2,3])
>>> output = np.array([1,1,5])
>>> residual = output - prediction
>>> RSS = sum(residual * residual)
>>> RSS
5
学习 numpy 基础知识将对机器学习和 matrix-vector 操作大有帮助，而不会因迭代而发疯：http://docs.scipy.org/doc/numpy-1.10.1/user/basics.html
我自己的问题已经解决了！
这是解决方法。
import numpy as np
import pandas as pd
import math
from sys import stdout
#function Takes the pandas dataframe, Input features list and the target column name
def get_numpy_data(data, features, output):
#Adding a constant column with value 1 in the dataframe.
data['constant'] = 1
#Adding the name of the constant column in the feature list.
features = ['constant'] + features
#Creating Feature matrix(Selecting columns and converting to matrix).
features_matrix=data[features].as_matrix()
#Target column is converted to the numpy array
output_array=np.array(data[output])
return(features_matrix, output_array)
def predict_outcome(feature_matrix, weights):
weights=np.array(weights)
predictions = np.dot(feature_matrix, weights)
return predictions
def errors(output,predictions):
errors=predictions-output
return errors
def feature_derivative(errors, feature):
derivative=np.dot(2,np.dot(feature,errors))
return derivative
def regression_gradient_descent(feature_matrix, output, initial_weights, step_size, tolerance):
converged = False
#Initital weights are converted to numpy array
weights = np.array(initial_weights)
while not converged:
# compute the predictions based on feature_matrix and weights:
predictions=predict_outcome(feature_matrix,weights)
# compute the errors as predictions - output:
error=errors(output,predictions)
gradient_sum_squares = 0 # initialize the gradient
# while not converged, update each weight individually:
for i in range(len(weights)):
# Recall that feature_matrix[:, i] is the feature column associated with weights[i]
feature=feature_matrix[:, i]
# compute the derivative for weight[i]:
#predict=predict_outcome(feature,weights[i])
#err=errors(output,predict)
deriv=feature_derivative(error,feature)
# add the squared derivative to the gradient magnitude
gradient_sum_squares=gradient_sum_squares+(deriv**2)
# update the weight based on step size and derivative:
weights[i]=weights[i] - np.dot(step_size,deriv)
gradient_magnitude = math.sqrt(gradient_sum_squares)
stdout.write("\r%d" % int(gradient_magnitude))
stdout.flush()
if gradient_magnitude < tolerance:
converged = True
return(weights)
#Example of Implementation
#Importing Training and Testing Data
# train_data=pd.read_csv("kc_house_train_data.csv")
# test_data=pd.read_csv("kc_house_test_data.csv")
# simple_features = ['sqft_living', 'sqft_living15']
# my_output= 'price'
# (simple_feature_matrix, output) = get_numpy_data(train_data, simple_features, my_output)
# initial_weights = np.array([-100000., 1., 1.])
# step_size = 7e-12
# tolerance = 2.5e7
# simple_weights = regression_gradient_descent(simple_feature_matrix, output,initial_weights, step_size,tolerance)
# print simple_weights
就是这么简单
def mean(values):
return sum(values)/float(len(values))
def variance(values, mean):
return sum([(x-mean)**2 for x in values])
def covariance(x, mean_x, y, mean_y):
covar = 0.0
for i in range(len(x)):
covar+=(x[i]-mean_x) * (y[i]-mean_y)
return covar
def coefficients(dataset):
x = []
y = []
for line in dataset:
xi, yi = map(float, line.split(','))
x.append(xi)
y.append(yi)
dataset.close()
x_mean, y_mean = mean(x), mean(y)
b1 = covariance(x, x_mean, y, y_mean)/variance(x, x_mean)
b0 = y_mean-b1*x_mean
return [b0, b1]
dataset = open('trainingdata.txt')
b0, b1 = coefficients(dataset)
n=float(raw_input())
print(b0+b1*n)
参考：www.machinelearningmastery.com/implement-simple-linear-regression-scratch-python/
我正在尝试实现此算法以找到单个变量的截距和斜率：
这是我的 Python 代码，用于更新截距和斜率。但它不收敛。 RSS 随着迭代而增加而不是减少，并且在一些迭代之后它变得无限大。我在执行 algorithm.How 时没有发现任何错误 我可以解决这个问题吗？我也附上了 csv 文件。 这是代码。
import pandas as pd
import numpy as np
#Defining gradient_decend
#This Function takes X value, Y value and vector of w0(intercept),w1(slope)
#INPUT FEATURES=X(sq.feet of house size)
#TARGET VALUE=Y (Price of House)
#W=np.array([w0,w1]).reshape(2,1)
#W=[w0,
# w1]
def gradient_decend(X,Y,W):
intercept=W[0][0]
slope=W[1][0]
#Here i will get a list
#list is like this
#gd=[sum(predicted_value-(intercept+slope*x)),
# sum(predicted_value-(intercept+slope*x)*x)]
gd=[sum(y-(intercept+slope*x) for x,y in zip(X,Y)),
sum(((y-(intercept+slope*x))*x) for x,y in zip(X,Y))]
return np.array(gd).reshape(2,1)
#Defining Resudual sum of squares
def RSS(X,Y,W):
return sum((y-(W[0][0]+W[1][0]*x))**2 for x,y in zip(X,Y))
#Reading Training Data
training_data=pd.read_csv("kc_house_train_data.csv")
#Defining fixed parameters
#Learning Rate
n=0.0001
iteration=1500
#Intercept
w0=0
#Slope
w1=0
#Creating 2,1 vector of w0,w1 parameters
W=np.array([w0,w1]).reshape(2,1)
#Running gradient Decend
for i in range(iteration):
W=W+((2*n)* (gradient_decend(training_data["sqft_living"],training_data["price"],W)))
print RSS(training_data["sqft_living"],training_data["price"],W)
Here 是 CSV 文件。
首先，我发现在编写机器学习代码时，最好不要使用复杂的列表理解，因为任何可以迭代的东西，
- 正常循环和缩进时写起来更容易阅读and/or
- 可以用numpy broadcasting 来完成
并且使用适当的变量名可以帮助您更好地理解代码。仅当您擅长数学时，使用 Xs、Ys、Ws 作为简写形式才不错。就个人而言，我不会在代码中使用它们，尤其是在 python 中编写时。来自 import this：显式优于隐式。
我的经验法则是记住，如果我编写的代码在 1 周后仍无法阅读，那么它就是糟糕的代码。
首先，我们来决定梯度下降的输入参数是什么，你需要：
- feature_matrix（
X矩阵，类型：numpy.array，一个N * D大小的矩阵，其中N是第. of rows/datapoints 和 D 是 columns/features) 的编号
- 输出（
Y向量，类型：numpy.array，大小为N的向量） - initial_weights（类型：
numpy.array，大小为 D 的向量）。
此外，要检查是否收敛，您需要：
- step_size（遍历改变权重时的变化幅度；类型：
float，一般为小数） - tolerance（打破迭代的标准，当梯度幅度小于tolerance时，假设你的权重已经收敛，输入：
float，通常是数字小但比步长大得多）。
现在开始编写代码。
def regression_gradient_descent(feature_matrix, output, initial_weights, step_size, tolerance):
converged = False # Set a boolean to check for convergence
weights = np.array(initial_weights) # make sure it's a numpy array
while not converged:
# compute the predictions based on feature_matrix and weights.
# iterate through the row and find the single scalar predicted
# value for each weight * column.
# hint: a dot product can solve this easily
predictions = [??? for row in feature_matrix]
# compute the errors as predictions - output
errors = predictions - output
gradient_sum_squares = 0 # initialize the gradient sum of squares
# while we haven't reached the tolerance yet, update each feature's weight
for i in range(len(weights)): # loop over each weight
# Recall that feature_matrix[:, i] is the feature column associated with weights[i]
# compute the derivative for weight[i]:
# Hint: the derivative is = 2 * dot product of feature_column and errors.
derivative = 2 * ????
# add the squared value of the derivative to the gradient magnitude (for assessing convergence)
gradient_sum_squares += (derivative * derivative)
# subtract the step size times the derivative from the current weight
weights[i] -= (step_size * derivative)
# compute the square-root of the gradient sum of squares to get the gradient magnitude:
gradient_magnitude = ???
# Then check whether the magnitude is lower than the tolerance.
if ???:
converged = True
# Once it while loop breaks, return the loop.
return(weights)
希望扩展pseudo-code能帮助你更好地理解梯度下降。 ??? 为了不破坏你的作业，我就不填了。
请注意，您的 RSS 代码也不可读且无法维护。这样做更容易：
>>> import numpy as np
>>> prediction = np.array([1,2,3])
>>> output = np.array([1,1,5])
>>> residual = output - prediction
>>> RSS = sum(residual * residual)
>>> RSS
5
学习 numpy 基础知识将对机器学习和 matrix-vector 操作大有帮助，而不会因迭代而发疯：http://docs.scipy.org/doc/numpy-1.10.1/user/basics.html
我自己的问题已经解决了！
这是解决方法。
import numpy as np
import pandas as pd
import math
from sys import stdout
#function Takes the pandas dataframe, Input features list and the target column name
def get_numpy_data(data, features, output):
#Adding a constant column with value 1 in the dataframe.
data['constant'] = 1
#Adding the name of the constant column in the feature list.
features = ['constant'] + features
#Creating Feature matrix(Selecting columns and converting to matrix).
features_matrix=data[features].as_matrix()
#Target column is converted to the numpy array
output_array=np.array(data[output])
return(features_matrix, output_array)
def predict_outcome(feature_matrix, weights):
weights=np.array(weights)
predictions = np.dot(feature_matrix, weights)
return predictions
def errors(output,predictions):
errors=predictions-output
return errors
def feature_derivative(errors, feature):
derivative=np.dot(2,np.dot(feature,errors))
return derivative
def regression_gradient_descent(feature_matrix, output, initial_weights, step_size, tolerance):
converged = False
#Initital weights are converted to numpy array
weights = np.array(initial_weights)
while not converged:
# compute the predictions based on feature_matrix and weights:
predictions=predict_outcome(feature_matrix,weights)
# compute the errors as predictions - output:
error=errors(output,predictions)
gradient_sum_squares = 0 # initialize the gradient
# while not converged, update each weight individually:
for i in range(len(weights)):
# Recall that feature_matrix[:, i] is the feature column associated with weights[i]
feature=feature_matrix[:, i]
# compute the derivative for weight[i]:
#predict=predict_outcome(feature,weights[i])
#err=errors(output,predict)
deriv=feature_derivative(error,feature)
# add the squared derivative to the gradient magnitude
gradient_sum_squares=gradient_sum_squares+(deriv**2)
# update the weight based on step size and derivative:
weights[i]=weights[i] - np.dot(step_size,deriv)
gradient_magnitude = math.sqrt(gradient_sum_squares)
stdout.write("\r%d" % int(gradient_magnitude))
stdout.flush()
if gradient_magnitude < tolerance:
converged = True
return(weights)
#Example of Implementation
#Importing Training and Testing Data
# train_data=pd.read_csv("kc_house_train_data.csv")
# test_data=pd.read_csv("kc_house_test_data.csv")
# simple_features = ['sqft_living', 'sqft_living15']
# my_output= 'price'
# (simple_feature_matrix, output) = get_numpy_data(train_data, simple_features, my_output)
# initial_weights = np.array([-100000., 1., 1.])
# step_size = 7e-12
# tolerance = 2.5e7
# simple_weights = regression_gradient_descent(simple_feature_matrix, output,initial_weights, step_size,tolerance)
# print simple_weights
就是这么简单
def mean(values):
return sum(values)/float(len(values))
def variance(values, mean):
return sum([(x-mean)**2 for x in values])
def covariance(x, mean_x, y, mean_y):
covar = 0.0
for i in range(len(x)):
covar+=(x[i]-mean_x) * (y[i]-mean_y)
return covar
def coefficients(dataset):
x = []
y = []
for line in dataset:
xi, yi = map(float, line.split(','))
x.append(xi)
y.append(yi)
dataset.close()
x_mean, y_mean = mean(x), mean(y)
b1 = covariance(x, x_mean, y, y_mean)/variance(x, x_mean)
b0 = y_mean-b1*x_mean
return [b0, b1]
dataset = open('trainingdata.txt')
b0, b1 = coefficients(dataset)
n=float(raw_input())
print(b0+b1*n)
参考：www.machinelearningmastery.com/implement-simple-linear-regression-scratch-python/