Day #39 - Useful Tool MyMediaLite for Recommendations

This post is based on learning's for assignment link1, link2

Input is User-Items file as listed below

Sample Execution Command

We will be supplying parameter 20 in user20.txt to identify recommendations for user 20. The recommender type is mentioned in the --recommender parameter

Happy Learning!!!

Day #38 - Python Matrix Operations Learnings

	#Python Exercises
	#Exercise #1
	#Save it to File test1.txt
	#Input
	#1 0 1 0 1
	#0 0 0 1 1
	#1 1 1 1 0
	#1 0 0 0 1
	#0 0 0 0 1
	#Output
	#1 1
	#1 3
	#1 5
	#2 4
	#2 5
	#3 1
	#3 2
	#3 3
	#3 4
	#4 1
	#4 4
	#5 5
	import pandas as pd
	import numpy as np
	file = open('test1.txt','r')
	filewrite = open('test1_output.txt','w')
	a = 0
	for line in file:
	a = a+1
	values = line.split('\t')
	b = 1
	for value in values:
	if(value=='1'):
	filewrite.write(str(a) + '\t'+ str(b) + '\n')
	b = b+1
	filewrite.close()
	#Exercise 2
	#Parse test1.txt and do matrix manipulation
	import pandas as pd
	import numpy as np
	data = pd.read_csv('test1.txt',header=None, sep = "\t")
	data_matrix = np.matrix(data)
	print(data_matrix.shape)
	print(data_matrix.shape[0])
	print(data_matrix.shape[1])
	#Exercise 3
	#Compute row and column sum
	import pandas as pd
	import numpy as np
	data = pd.read_csv('test1.txt',header=None, sep = "\t")
	data_matrix = np.matrix(data)
	print(data_matrix.shape)
	print(data_matrix.shape[0])
	print(data_matrix.shape[1])
	#Parse Matrix sum of each column
	for i in range(0,data_matrix.shape[0]):
	sum = 0
	for j in range(0,data_matrix.shape[1]):
	sum = sum+data_matrix[i,j]
	print('row -',i+1,'-sum ',sum)
	#Parse Matrix sum of each column
	for i in range(0,data_matrix.shape[1]):
	sum = 0
	for j in range(0,data_matrix.shape[0]):
	sum = sum+data_matrix[j,i]
	print('column-',i+1,'-sum ',sum)

view raw matrixops.py hosted with ❤ by GitHub

Happy Learning!!!

Day #37 - Numpy Learnings - Matrices

	import pandas as pd
	import numpy as np
	df = pd.DataFrame({'A':[1.1,2.2,3.1],'B':[5.2,6.1,7.1],'C':[5.4,6.6,7.4]})
	print(df)
	#Tip #1
	#Create matrix of float values
	data_intermediate = df.astype(float)
	data_matrix = np.matrix(data_intermediate)
	print('matrix')
	print(data_matrix)
	#Tip #2 Compute Transpose
	print('Transpose matrix')
	print(np.transpose(data_matrix))
	#Tip #3 - Matrix Inverse
	print('Inverse matrix')
	print(data_matrix.I)
	#Tip #4 - Identity Matrix
	print('Identity Matrix')
	print(np.identity(3))
	print('Identity Matrix X Data ')
	print(np.identity(3)*data_matrix)
	#Tip #5 - Eigen Values
	print('Eigen Values')
	print(np.linalg.eigvals(data_matrix))
	#Tip #6 - Eigen Vectors
	w, v= np.linalg.eig(data_matrix)
	print('Eigen Vector')
	print(v)
	#Tip #7 - svd
	print('SVD')
	print(np.linalg.svd(data_matrix))

view raw numpybasics.py hosted with ❤ by GitHub

Happy Learning!!!

Day #36 - Pandas Dataframe Learning's

	import numpy as np
	import pandas as pd
	#Tip #1
	#Data frame to matrix
	df = pd.DataFrame({'A':[1,2,3,4],'B':[5,6,7,8],'C':[5,6,7,8]})
	print(df)
	#Tip #2
	#Standardize value in columns
	df["A"] = (df["A"]-df["A"].mean())/np.std(df["A"])
	#Tip #3
	#Dynamically stardardize except last column
	for col in df.columns[:-1]:
	df[col] = (df[col] - df[col].mean())/ (np.std(df[col]))
	print(df)
	features = list(df.columns[:-1])
	#Tip #4 - Replance na values
	df = df.fillna(-9999)
	#Tip #5
	#Dynamically add columns
	for i in range(0,2):
	colname1 = str(5+i)
	col1 = i
	col2 = i+1
	print('colname', colname1)
	print('col1', col1)
	print('col2', col2)
	if(col2 < 2):
	df[colname1] = df[features[col1]]*df[features[col2]]
	print('newly added columns')
	print(df)

view raw pandasbasics.py hosted with ❤ by GitHub

Happy Learning!!!

Day #35 - Bias Vs Variance

These are frequently occurring terms with respect to performance of model against training and testing data sets.

Classification error = Bias + Variance

Bias (Under-fitting)

• Bias is high if the concept class cannot model the true data  distribution well, and does not depend on training set size.
• High Bias will lead to under-fitting

How to identify High Bias

• Training Error will be high
• Cross Validation error also will be high (Both will be nearly the same)

Variance(Over-fitting)

• High Variance will lead to over-fitting

How to identify High Variance

• Training Error will be high
• Cross Validation error also will be Very Very High compared to training error

Hot to Fix ?
Variance decreases with more training data, and increases with more complicated classifiers

Happy Learning!!!

Day #34 - What is diffference between Logistics Regression and Naive Bayes

Both are probabilistic
Logistics

• Discriminative (Entire approach is purely discriminative)
• P(Y/X)
• Final Value lies between Zero and 1
• Formula given by exp(w0+w1x)/(exp(w0+ w1x)+1)
• Further can be expressed as 1/(1+(exp-(w0+ w1x))

Binary Logistic Regression - 2 class

Multinomial Logistic Regression - More than 2 class

Example - Link

	import math
	def sigmoid(x):
	a = []
	for item in x:
	a.append(1/(1+math.exp(-item)))
	return a
	import matplotlib.pyplot as plt
	import numpy as np
	x = np.arange(-70, 70,1)
	sig = sigmoid(x)
	plt.plot(x,sig)
	plt.title('Sigmoid Weight 1')
	plt.show()
	x = np.arange(-70, 70,5)
	sig = sigmoid(x)
	plt.title('Sigmoid Weight 5')
	plt.plot(x,sig)
	plt.show()
	x = np.arange(-70,70,100)
	sig = sigmoid(x)
	plt.title('Sigmoid Weight 100')
	plt.plot(x,sig)
	plt.show()

view raw Logistics_Different_Sigmoid.py hosted with ❤ by GitHub

	#3 class classifier
	import numpy as np
	import matplotlib.pyplot as plt
	from sklearn import linear_model, datasets
	iris = datasets.load_iris()
	#only two features taken
	X = iris.data[:,:2]
	Y = iris.target
	#step size in mesh
	h = 0.02
	logreg = linear_model.LogisticRegression(C=1e5)
	#create instance of classifier and fit data
	logreg.fit(X,Y)
	#plot decision boundary and assign color for it
	x_min, x_max = X[:,0].min()-0.5,X[:,0].max()+0.5
	y_min, y_max = X[:,1].min()-0.5,X[:,1].max()+0.5
	xx,yy = np.meshgrid(np.arange(x_min,x_max,h),np.arange(y_min,y_max,h))
	Z = logreg.predict(np.c_[xx.ravel(),yy.ravel()])
	#put the result to color plot
	Z = Z.reshape(xx.shape)
	plt.figure(1,figsize=(4,3))
	plt.pcolormesh(xx,yy,Z,cmap=plt.cm.Paired)
	#plot also training points
	plt.scatter(X[:,0],X[:,1],c=Y,edgecolors='k',cmap=plt.cm.Paired)
	plt.xlabel('Sepal Length')
	plt.ylabel('Sepal width')
	plt.xlim(xx.min(),xx.max())
	plt.ylim(yy.min(),yy.max())
	plt.xticks(())
	plt.yticks(())
	plt.show()

view raw LR.py hosted with ❤ by GitHub

Link - Ref
Logistic Regression

• Classification Model
• Probability of success as a sigmoid function of a linear combination of features
• y belongs to (0,1) - 2 Class problem
• p(yi) = 1 / 1+e-(w1x1+w2x2)
• Linear combination of features - w1x1+w2x2
• w can be found with max likelihood estimate- 

Naive Bayes

• Generative Model
• P(X/ Given Y) is Naive Bayes Assumption
• Distribution for each class

Happy Learning

Day #33 - Pandas Deep Dive

	import pandas as pd
	#Create Data Frame with few columns and list values
	df = pd.DataFrame({'A':[1,2,3,4],'B':[5,6,7,8]})
	print(df)
	#Drop a Column
	df = df.drop('A',1)
	print(df)
	#Create column with int column names
	df = pd.DataFrame({1:[1,2,3,4],2:[1,2,3,4],10:[1,2,3,4]})
	print(df)
	df = df.drop(1,1)
	print(df)
	#Sample two rows from data frame
	print(df.sample(n=2))
	#Create list with 56 values
	a = []
	for i in range(1,56):
	a.append(i)
	import random
	#Sample 15 random entries
	feature2 = random.sample(a,15)
	print('feature')
	print(df)
	#Find maximum occuring values row wise
	print(df.mode(axis=1))

view raw pandasin10mins.py hosted with ❤ by GitHub

Happy Learning!!!

Good Data Science Course Links

AI Lectures

Introduction to Machine Learning

Happy Learning!!!

Short Analytics Concept Videos

• Descriptive Analysis (Analysis of existing data, Trends and Patterns), 
• Diagnostic Analysis (Reasons / Patterns behind events)
• Predictive Analytics (Future how will it look like) 
• Prescriptive Analysis (How to be prepared / handle the future)

Great Compilation, Keep Learning!!!

Day #32 - Regularization in Machine Learning

A large coefficient will result in overfitting. To avoid we perform regularization. Regularization - To avoid overfitting

• L1 - Sum of values (Lasso - Least absolute shrinkage and selection operator). L1 will be meeting in co-ordinates and result in one of the dimensions zero. This would result in variable elimination. The features that minimally contribute will be ignored.
• L2 - Sum of squares of values (Ridge). L2 is kind of circle shaped. This will shrink all coefficient in same proportion but eliminate none
• Discriminative - In SVM we use hyperplane to classify the classes. This is example for discriminative approach
• Probabilistic - Generated by Gauss Distribution. This is again based on Central Limit Theorem. Infinite points will fit into a Normal distribution. Here we apply gauss distribution model
• Max Likelihood - Probability that the point p belongs to one distribution. 

Good Read for L2 - Indeed, using the L2 loss comes from the assumption that the data is drawn from a Gaussian distribution

Another Read -

• L1 Loss function minimizes the absolute differences between the estimated values and the existing target values. L1 loss function is more robust and is generally not affected by outliers
• L2 loss function minimizes the squared differences between the estimated and existing target values. L2 error will be much larger in the case of outliers 

Happy Learning!!!