Practical_Exam_18IT031

3 min readNov 18, 2021

TASK:

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

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.

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.

Following answers need to be submitted in a single PDF file:
1. Provide a screen shot of data description and explain in brief.
2. Provide screen shot(s) of data pre-processing steps showing its significance.
3. Provide a screen shot showing accuracy before and after pre-processing.
4. Provide a screen shot of PowerBI dashboard with description.

SOLUTION:

First we have to convert .data file to proper csv file so we use colab

ANS 1). Here provide cylinder-bands dataset with different parameter like hardner , current desity, link temper etc

ANS 2).now we will preprocess data using orange tool present in anaconda navigator and do impute missing value , normalization feature , and feature selection for pre processing here is flow .

After preprocessing step, our dataset is more feasible for classification , first we need unwanted column and using same widget we will assign target variable.

Next step we send data to data sampler which divide data into 71%.

Now without preprocessing

Ans 3) Now we see difference between simple data flow which is not pre procced in left hand side and pre procced data in right hand side. It clearly visible that CA ,F1-score and recall better and Pre procced data.