Day #17 - Python Basics

	#Example #1 - numpy version
	import numpy as np
	np.version.version
	#Shift+Enter Command
	#Example #2 - Vector of 10 null elements
	import numpy as np
	x = np.zeros(10)
	x
	#Example #3 - one element not null
	import numpy as np
	x = np.zeros(10)
	x[4] = 1
	x
	#Example #4 - vector of range of values
	import numpy as np
	x = np.arange(10,49,1)
	x
	#Example #5 - Reverse Vector
	import numpy as np
	x = np.arange(10,49,1)
	xrev = x[::-1]
	xrev
	#Example #6 - 3 x 3 matrix
	#[0..8]
	import numpy as np
	a = np.matrix('0,1,2;3,4,5;6,7,8')
	a
	#Example #7 - Indices of non zero elements
	import numpy as np
	a = [1,2,0,0,4,0]
	aval = np.nonzero(a)[0]
	print(aval)
	#Example #8 - 3 x 3 Identity matrix
	import numpy as np
	a = np.eye(3, dtype=int)
	a
	#Example #9 - 3 x 3 x 3 array of random values
	import random
	import numpy as np
	n = 3
	a = np.random.random((n,n,n))
	a
	#Also found this link are doing the exercise - http://www.labri.fr/perso/nrougier/teaching/numpy.100/

view raw pythonexamples.py hosted with ❤ by GitHub

	import matplotlib.pyplot as plt
	#Declare Dictionary
	result = {}
	#Populate Data
	for i in range(1,100,1):
	result[i] = (i,i*9)
	#Approach #1
	print 'Approach #1'
	for i in range(1,100,1):
	(key,value) = result[i]
	print(key)
	print(value)
	#Approach #2
	print 'Approach #2'
	for key, value in result.iteritems():
	print key
	print value[1]
	#Plot the line
	def plotgraph(result):
	for key, value in result.iteritems():
	print key
	print value[1]
	plt.plot(key, value[1],'-o')
	plt.xlabel("x Values")
	plt.ylabel("Y Value")
	plt.title("Plot Graph")
	plt.show()
	plotgraph(result)

view raw DictionaryExample.py hosted with ❤ by GitHub

Happy Learning!!!

Neural Networks Basics

Notes from Session

• Neurons - Synapses. Model brain at high level
• Machine Learning  - Algorithms for classification and prediction
• Mimic brain structure in technology
• Recommender engines use neural networks
• With more data we can increase accuracy of models
• Linear Regression, y = mx + b. Fit data set with little error possible.

Neural Network

• Equation starts from neuron
• Multiply weights to inputs (Weights are coefficients)
• Apply activation function (Depends on problem being solved)

Basic Structure

• Input Layer
• Hidden Layer (Multiple hidden layers) - Computation done @ hidden layer
• Output Layer
• Supervised learning (Train & Test)
• Loss function determines how error looks like
• Deep Learning - Automatic Feature Detection

Happy Learning!!!

Basics - SUPPORT VECTOR MACHINES

Good Reading from link

Key Notes

• Allow non-linear decision boundaries
• SVM - Out of box supervised learning technique
• Feature Space - Finite dimensional vector space
• Each dimension represents feature
• Goal of SVN - Train a model that assigns unseen objects into particular category
• Creates linear partition of feature space
• Based on features it places above or below separation linear
• No stochastic element involved (No involvement of any previous state status)
• support vector classifiers or soft margin classifiers - allows some observations to be on in-correct side of hyperplane allowing soft margin

Advantage

• High Dimensionality, Memory Efficiency, Versatility

Disadvantages

• Non probabilistic

More Reads

Guide to Machine Learning

Happy Learning!!!

Day #16 - Python Basics

	#Try from link https://try.jupyter.org/
	#Ref Tutorial - https://www.youtube.com/watch?v=1I2Bz0qbMsc
	#Example #1 - python variables
	#boolean
	a = True
	#int
	b = 4
	#float
	c = 3.45
	#complex
	e = 7j
	print(c)
	print(e)
	print(a)
	print(b)
	#Example 2
	name = "Siva"
	print(name)
	agelist=[1,2,3,4,5]
	print(agelist)
	agelist.append(10)
	print(agelist)
	dict_example={"name":"siva","credit":100}
	print(dict_example["name"])
	dict_example.values()
	#Example 3 - Integer Array
	import numpy as np
	a = np.arange(1,10)
	a
	#Example 4 - Integer Array
	import numpy as np
	ds = np.arange(1.2,10,2,dtype=np.float64)
	ds
	#Example 5 shape of array
	import numpy as np
	ds = np.arange(1.2,10,2,dtype=np.float64)
	ds.shape
	ds
	#Example 6 Parsing list
	agelist=[1,2,3,4,5,6,7,8,9,10]
	#print first element
	print(agelist[0])
	#print from 0 to 2
	print(agelist[0:2])
	#print from 2 onwards
	print(agelist[2:])
	#print last element
	print(agelist[-1])
	#print last two elements
	print(agelist[-2:])
	#print start to last-1
	print(agelist[0:-1])
	#Example 7
	a = 10
	b = 3
	#Float result
	print(a/b)
	#Int result
	print(a//b)
	#Example 8
	#For loop
	for counter in range(1,50,1):
	print(counter)
	#Example 9
	#While Loop
	counter=1
	while counter<100:
	print(counter)
	counter=counter+1
	#Example 10
	#If conditions
	a=9
	if a>10:
	print("a > 10")
	elif a<10:
	print("a <10")
	else:
	print("a=10")
	#Example 11 Functions
	def computesquare(n):
	return n*n
	print(computesquare(10))

view raw Pythonbasics.py hosted with ❤ by GitHub

Happy Learning!!!

Probability Tips

• Discrete random variables are things we count
• A discrete variable is a variable which can only take a countable number of values
• Probability mass function (pmf) is a function that gives the probability that a discrete random variable is exactly equal to some value.
• Continuous random variables are things we measure
• A continuous random variable is a random variable where the data can take infinitely many values.
• Probability density function (PDF), or density of a continuous random variable, is a function that describes the relative likelihood for this random variable to take on a given value
• Bernoulli process is a finite or infinite sequence of binary random variables
• Markov Chain - stochastic model describing a sequence of possible events in which the probability of each event depends only on the state attained in the previous event

Let's Continue Learning!!!

Day #15 - Data Science - Maths Basics

Day #15 - Mathematics Basics

Sets Basics

• Cardinality - Number of distinct elements in Set (For a Finite Set)
• For Real numbers cardinality infinite

Rational Numbers - Made of Ratio of two numbers
Fibonacci series was introduced in 1201 - Amazing :)

Functions

• Represents relationship between mathematical variables
• Spread of all possible output is called range
• Function that maps from A to B. A is referred as (Domain), B is referred as co-domain

Matrix

• Rows and columns define matrix 
• 2D array of numbers 
• Eigen Values - Scalars, Eigen Vector - Vectors special set of values associated with Matrix M
• Eigen Vectors - Those directions remain unchanged by action of matrix M
• Trace - Sum of diagonal elements
• Rank of Matrix - Number of linearly independent vectors

Determinant

• Can be computed only for square matrix

Vector

• Vectors have magnitude, length and direction
•  Magnitude and cost of angle will give you direction
• Vector product non-commutative
•  Dot product commutative
•  Vector is linearly independent if none of vectors can be written as sum of multiple of other vectors

 Happy Learning!!!

Day #14 - R Working Tips

	#Tip #1 - R - Case Sensitive
	#Tip #2 - R - Data Stored in memory
	#Tip #3 - Assigning variables
	var2 <-3
	var2
	var2 <-"Test"
	var2
	#Tip #4 - Working with Dates
	#Convert character to date using as.Date function
	as.Date('2016-04-16')
	#Tip #5 - Function to remove non available values (Missing Data)
	na.rm = TRUE
	#Test for Missing Data
	is.na(VariableName)
	#Tip #6
	#Vectors - Basic Data Structures One Dimensional Arrays
	#Created using c command
	a_vector <- c(1,2,3,4,5)
	a_vector
	#Index starts with 1
	a_vector[1]
	b_vector <- c("Apple","Orange","Banana")
	b_vector
	b_vector[2]
	#Negate - Ignore particular value, Return everything except 1
	b_vector[-1]
	#Tip #7 - Vector Operations
	v1 <- c(2,3,4)
	v2 <- c(10,11,12)
	v1+v2
	#Tip #8 - Lists
	#Can hold different data types
	emp_details_1 <- list(01,'Siva','India')
	emp_details_1
	emp_details_2 <- list(02,'TOM','USA')
	emp_details_2
	#Tip #9 - Data Frame (Store Rows and Columns)
	#Row bind
	df1 = rbind(emp_details_1,emp_details_2)
	df1
	#Column bind
	df2 = cbind(v1,v2)
	df2
	#Tip #10 - Empty vector and append elements
	a <- vector(mode="numeric", length=0)
	b <- vector(mode="numeric", length=0)
	a <- c(a,1)
	b <- c(b,2)
	a
	b
	#Tip #11 - Merge function - merge based on particular column
	#Tip #12 - Factors
	# R automatically recognizes
	#as.factor converts into factor
	#classification uses factors
	gender <- c("Male","Female")
	gender_cf <- as.factor(gender)
	gender_cf
	#Matrix Basics
	xx <- matrix(c(0.4, 0.6, 0.3, 0.7))
	xx
	xx <- matrix(c(0.4, 0.6, 0.3, 0.7), nrow=2)
	xx
	xx <- matrix(c(0.4, 0.6, 0.3, 0.7), nrow=2)
	xx <- t(xx)
	xx
	xx %*% xx

view raw RBasics.R hosted with ❤ by GitHub

Happy Learning!!!

Day #13 - Maths and Data Science

• Recommender Systems - Pure matrix decomposition problem
• Deep Learning - Matrix Calculus
• Google Search - Page Rank, Social Media Graph Analysis - Eigen Decomposition

Happy Learning!!!

Ensemble

• Combine many predictors and provide weighted average
• Use single kind of learner but multiple instances
• Collection of "Ok" predictors and combine them making them powerful
• Learn Predictors and combine them using another new model 
• One layer of predictors providing features for next layer 

Happy Learning!!!