python - पायथन में सरल रैखिक रिग्रेशन




numpy machine-learning (2)

मैं एकल चर के लिए अवरोध और ढलान खोजने के लिए इस एल्गोरिदम को लागू करने की कोशिश कर रहा हूं:

इंटरसेप्ट और ढलान को अद्यतन करने के लिए मेरा पायथन कोड यहां दिया गया है। लेकिन यह अभिसरण नहीं है। आरएसएस घटने के बजाय इटरेशन के साथ बढ़ रहा है और कुछ पुनरावृत्ति के बाद यह अनंत हो रहा है। मुझे एल्गोरिदम लागू करने में कोई त्रुटि नहीं मिल रही है। मैं इस समस्या को कैसे हल कर सकता हूं? मैंने सीएसवी फ़ाइल भी संलग्न की है। कोड यहाँ है।

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 सीएसवी फ़ाइल है।


मैंने अपनी समस्या हल कर ली है!

हल रास्ता है।

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

यह बहुत आसान है

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)

संदर्भ: www.machinelearningmastery.com/implement-simple-linear-regression-scratch-python/





gradient-descent