Practical Exam Work

Id No:18IT019

Name : Vandita Hanishkumar Chapadia

Subject: Data Science (IT441)

Dataset: https://archive.ics.uci.edu/ml/machine-learning-databases/00475/

Task 1:

Dataset Description using Orange tool.
What is need to be done to improve the accuracy of classification result of the given dataset? Get the maximum classification accuracy possible by performing following methods.
→Pre-processing
o Encoding
o Normalization
o Missing value handling
o Feature Selection

Compare your accuracy with and without applying pre-processing steps. Perform the Classification and visualize accuracy before and after preprocessing in Orange/Python.

Orange Tool:

Orange tool is open source data visualization ,machine learning and data mining toolkit.

Load data set

Data Table which contain 776 instance and 27 features

scatter plot of given data set

using select columns choose target variable

Preprocess data using Normalization, random features and impute missing values

add test and score to check accuracy of various classification like KNN, Naive Bayers, Logistic Regression and Neural network with pre processing and without pre processing and also implement confusion matrix to measure strength of the classifier.

Test Score with Pre processing and without pre processing

Here we have seen that the difference of with pre processing and without pre pocessing and test score of classification .

confusion matrix for given classifiers

data flow

Task-2:
Generate the Dashboard of preprocessed dataset from task-1.
Find the Maximum data insights by plotting Bar chart, Boxplot, Pie Plot, Stack Plot using PowerBI dashboard visualization.

Power BI:

Power BI is a business analytics service by Microsoft. It aims to provide interactive visualization and business intelligence capability with simple interface for end user to create own dashboard and report based on their analysis purpose.

Load CSV file into the Power-BI desktop using get data option

Dataset features

Type of Risks

bar graph of respective parameters

Pie chart of accounted Risk

stacked graph

score of different parameters

District Loss, Score and total

Open in Power BI workspace after publish

After generating individual report ,select publish and log in with https://app.powerbi.com/home where you can find workspace which publish and combine all report and pinned in to dashboard.

create new dashboard

Now Dashboard is ready,

Power BI dashboard for Audit Analysis 1

Power BI dashboard for Audit Analysis 2

visit the link to check dashboard:

https://app.powerbi.com/groups/me/dashboards/a25edcad-08fa-48a4-908d-59f863074821