R for MBA's- Scatter plot or Scatter diagram

R for MBA's- Scatter plot or Scatter diagram

Problem 1:

Draw a scatter diagram for the given data set: 

> x<-c(212,245,278,351,324)
> y<-c(256,211,295,331,405)

> plot(x,y)

Learn SPSS- Transposing the data.

R for MBA's- Bar charts using R

R for MBA's - Bar charts/Plots for MBA's

Problem 1:

> x<-c(143,175,156,187,195)

> barplot(x)

R for MBA's- correlation using R

Correlation using R

Problem 1: 

> x<-c(143,175,156,187,195)
> y<-c(132,191,111,156,175)
> cor(x,y)

Ans: [1] 0.7017061

R for MBA's - Calculating median using R

R for MBA's - Calculating median using R

> x<-c(14,16,18,20,22,26,28)

> median(x)

Ans :[1] 20

R for MBA's- Caclulating mean using R

R For MBA's Calculating mean

> x<-c(14,16,18,20,22,26,28)

> mean(x)

Ans: [1] 20.57143

Learn SPSS- Sorting of Data

Difference between Primary data and Secondary data

Difference Between

 Primary and

 Secondary data

Parameter	Primary data	Secondary data
Objective	To address the problem or opportunity of the research.	To support the problem or opportunity of other researchers.
Process	Researcher involvement is very high	Researcher collect information with little effort.
Cost	Primary data collection cost is very high	Secondary data collection cost is low.
Time	Duration to collect the primary data is long	Secondary data collected is less span of time.
Suitability	This type of data is suitable for the problem or opportunity of the researcher.	Secondary data may or may not suit the objectives of the research and problem or opportunity in general.
Originality	Original data collected from the researcher.	This data is borrowed from other researchers.
Validation	Data validation effort is very less	Data has to be thoroughly validated.
Sources	Surveys, Observations and Experiments	Internal records, Published sources and search engines.
Bias	The researcher has to eliminate the bias in the primary data	The previous researcher has already eliminated the bias , the current researcher need  not to work more on bias elimination.
Need of investigators	This type of data require a trained investigators.	There is no need of
Reliability	More reliable	Less reliable
Type of data	Quantitative in Nature	Qualitative in nature.
Control	The researcher has high degree of control	The researcher has less control
Ownership	The researcher has ownership of the data	The researcher has no ownership of the data
Relevance	The data is relevant to the problem or opportunity in the hand	The data may or may not be relevant to the problem or opportunity in the hand.

Python for MBA's- Image analysis

Example 1:

# image analysis using scikit

# image analysis using skiimage

import matplotlib.pyplot as plt

%matplotlib inline

from skimage import data,filters

       

image = data.coins()   # ... or any other NumPy array!  

edges = filters.sobel(image)  

plt.imshow(edges, cmap='gray')

 

Example 2:

import numpy as np

import matplotlib.pyplot as plt

from skimage import data

from skimage.feature import match_template

image = data.coins()

coin = image[170:220, 75:130]

result = match_template(image, coin)

ij = np.unravel_index(np.argmax(result), result.shape)

x, y = ij[::-1]

fig = plt.figure(figsize=(8, 3))

ax1 = plt.subplot(1, 3, 1)

ax2 = plt.subplot(1, 3, 2)

ax3 = plt.subplot(1, 3, 3, sharex=ax2, sharey=ax2)

ax1.imshow(coin, cmap=plt.cm.gray)

ax1.set_axis_off()

ax1.set_title('template')

ax2.imshow(image, cmap=plt.cm.gray)

ax2.set_axis_off()

ax2.set_title('image')

# highlight matched region

hcoin, wcoin = coin.shape

rect = plt.Rectangle((x, y), wcoin, hcoin, edgecolor='r', facecolor='none')

ax2.add_patch(rect)

ax3.imshow(result)

ax3.set_axis_off()

ax3.set_title('`match_template`\nresult')

# highlight matched region

ax3.autoscale(False)

ax3.plot(x, y, 'o', markeredgecolor='r', markerfacecolor='none', markersize=10)

plt.show()

 

Output: