added mean square gradient

Assignment1/main.py

 import numpy as np
 import argparse
 import csv
-
+import matplotlib.pyplot as plt
 ''' 
 You are only required to fill the following functions
 mean_squared_loss
@@ -21,22 +21,19 @@ Don't modify function declaration (arguments)
 '''
 
 def mean_squared_loss(xdata, ydata, weights):
-	'''
-	weights = weight vector [D X 1]
-	xdata = input feature matrix [N X D]
-	ydata = output values [N X 1]
-	Return the mean squared loss
-	'''
-	
+
+	guess = np.dot(xdata,weights)
+	samples = np.shape(guess)[0]
+	err = 0.5*samples*np.sum(np.square(ydata.T-guess))
+	return err
 	raise NotImplementedError
 
 def mean_squared_gradient(xdata, ydata, weights):
-	'''
-	weights = weight vector [D X 1]
-	xdata = input feature matrix [N X D]
-	ydata = output values [N X 1]
-	Return the mean squared gradient
-	'''
+
+	samples = np.shape(xdata)[0]
+	guess = np.dot(xdata,weights)
+	gradient = (1/samples)*np.dot(xdata.T,(guess-ydata.T))
+	return gradient
 
 	raise NotImplementedError
 
@@ -68,29 +65,25 @@ class LinearRegressor:
 
 	def __init__(self,dims):
 		
-		# dims is the number of the features
-		# You can use __init__ to initialise your weight and biases
-		# Create all class related variables here
+		self.dims = dims
+		self.W = np.zeros(dims) 
+		return
 
 		raise NotImplementedError
 
-	def train(self, xtrain, ytrain, loss_function, gradient_function, epoch=100, lr=1.0):
-		'''
-		xtrain = input feature matrix [N X D]
-		ytrain = output values [N X 1]
-		learn weight vector [D X 1]
-		epoch = scalar parameter epoch
-		lr = scalar parameter learning rate
-		loss_function = loss function name for linear regression training
-		gradient_function = gradient name of loss function
-		'''
-		# You need to write the training loop to update weights here
-		
+	def train(self, xtrain, ytrain, loss_function, gradient_function, epoch=100, lr=1):
+		errlog = []
+		samples = np.shape(xtrain)[0]
+		for iterations in range(epoch):
+			self.W = self.W - lr*gradient_function(xtrain,ytrain,self.W)
+			errlog.append(loss_function(xtrain,ytrain,self.W))
+		return errlog
 		raise NotImplementedError
 
 	def predict(self, xtest):
 		
 		# This returns your prediction on xtest
+		return np.dot(xtest,self.W)
 		raise NotImplementedError
 
 
@@ -120,18 +113,14 @@ def read_dataset(trainfile, testfile):
 	return np.array(xtrain), np.array(ytrain), np.array(xtest)
 
 def preprocess_dataset(xdata, ydata=None):
-	'''
-	xdata = input feature matrix [N X D] 
-	ydata = output values [N X 1]
-	Convert data xdata, ydata obtained from read_dataset() to a usable format by loss function
-
-	The ydata argument is optional so this function must work for the both the calls
-	xtrain_processed, ytrain_processed = preprocess_dataset(xtrain,ytrain)
-	xtest_processed = preprocess_dataset(xtest)	
-	
-	NOTE: You can ignore/drop few columns. You can feature scale the input data before processing further.
-	'''
-
+	xdata = xdata[:,[2,3,4,7,9]]
+	xdata = xdata.astype('float32') 
+	bias = np.ones((np.shape(xdata)[0],1))
+	xdata = np.concatenate((bias,xdata),axis=1)
+	if ydata is None:
+		return xdata
+	ydata = ydata.astype('float32')
+	return xdata,ydata
 	raise NotImplementedError
 
 dictionary_of_losses = {
@@ -147,17 +136,20 @@ def main():
 	# Uncomment the below lines and pass the appropriate value
 
 	xtrain, ytrain, xtest = read_dataset(args.train_file, args.test_file)
-	# xtrainprocessed, ytrainprocessed = preprocess_dataset(xtrain, ytrain)
-	# xtestprocessed = preprocess_dataset(xtest)
-
-	# model = LinearRegressor(FILL HERE)
+	xtrainprocessed, ytrainprocessed = preprocess_dataset(xtrain, ytrain)
+	xtestprocessed = preprocess_dataset(xtest)
+	
+	model = LinearRegressor(np.shape(xtrainprocessed)[1])
 
 	# The loss function is provided by command line argument	
 	loss_fn, loss_grad = dictionary_of_losses[args.loss]
 
-	# model.train(xtrainprocessed, ytrainprocessed, loss_fn, loss_grad, args.epoch, args.lr)
-
-	# ytest = model.predict(xtestprocessed)
+	errlog = model.train(xtrainprocessed, ytrainprocessed, loss_fn, loss_grad, args.epoch, args.lr)
+	ytest = model.predict(xtestprocessed)
+	ytest = ytest.astype('int')
+	output = [(i,np.absolute(ytest[i])) for i in range(len(ytest))]
+	np.savetxt("output.csv",output,delimiter=',',fmt="%d",header="instance (id),count",comments='')
+	np.savetxt("error.log",errlog,delimiter='\n',fmt="%f")
 
 
 if __name__ == '__main__':