Update Day2_Simple_Linear_Regression.md , used python oops concept and other basic libraries.

Code/Day2_Simple_Linear_Regression.md

@@ -11,34 +11,71 @@
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
+import sys
 
 dataset = pd.read_csv('studentscores.csv')
 X = dataset.iloc[ : ,   : 1 ].values
 Y = dataset.iloc[ : , 1 ].values
-
-from sklearn.cross_validation import train_test_split
-X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size = 1/4, random_state = 0) 
 ```
-
-# Step 2: Fitting Simple Linear Regression Model to the training set
- ```python
- from sklearn.linear_model import LinearRegression
- regressor = LinearRegression()
- regressor = regressor.fit(X_train, Y_train)
- ```
- # Step 3: Predecting the Result
+# Step 2: Creating regression class
  ```python
- Y_pred = regressor.predict(X_test)
+class Gradient_descent:
+
+	def __init__(self,train_data,train_labels):
+		self.train_data = train_data
+		self.train_labels = train_labels
+		self.new_train_data = np.insert(self.train_data,0,1,axis=1)		
+		self.weights = np.zeros((2,1))		
+		self.epochs = 1500
+		self.alpha = 0.01
+
+	def hypothesis(self):
+		return np.dot(self.new_train_data,self.weights)	
+
+	def cost(self):
+		cost = (1/(2*np.size(self.train_labels)))*np.sum((self.hypothesis()-self.train_labels)**2)
+		return cost		
+
+	def derivative(self):
+		return (1/np.size(self.train_labels))*np.dot(self.new_train_data.T,(self.hypothesis()-self.train_labels))
+
+	def train(self):
+		self.loss = []		
+		for i in range(self.epochs):
+			cost = self.cost()					
+			self.weights = self.weights - (self.alpha) * self.derivative()
+			self.loss.append(cost)
+
+		plt.plot(self.loss)
+		plt.show()	
+		return self.weights,np.array(self.loss)
+
+	def predict(self,data):
+		return np.dot(data,self.weights)	
+
+	def visualize(self,data):
+		data = self.hypothesis()
+		plt.xlabel('population of city in 10,000s')
+		plt.ylabel('profit in $10,000')		
+		plt.scatter(self.train_data,self.train_labels,marker='x',color='red',label='Training data')
+		plt.plot(self.new_train_data[:,1],data,label='Linear regression')
+		plt.legend(loc='lower right')
+		plt.show()						
  ```
-
- # Step 4: Visualization 
- ## Visualising the Training results
+ # Step 3: Making use of the newly created class
  ```python
- plt.scatter(X_train , Y_train, color = 'red')
- plt.plot(X_train , regressor.predict(X_train), color ='blue')
+ if __name__ == '__main__':
+	data = pd.read_csv('ex1data1.txt')
+	train_data = np.array(data.iloc[:,:1])
+	train_labels = np.array(data.iloc[:,1:])			
+
+	gd = Gradient_descent(train_data,train_labels)	
+	print('older cost: ',gd.cost())
+	result = gd.train()
+	print('updated theta: \n',result[0])
+	print('final cost: ',gd.cost())
+
+	# new_prediction = gd.predict(np.array([1,7]))	
+	# print(new_prediction)
+	gd.visualize(gd.hypothesis())	
  ```
- ## Visualizing the test results
- ```python
- plt.scatter(X_test , Y_test, color = 'red')
- plt.plot(X_test , regressor.predict(X_test), color ='blue')
- ```