Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
167 views8 pages

Presentation Exploratory Data Analysis

The document discusses exploratory data analysis techniques including descriptive statistics, correlations, and histograms. It explains that exploratory data analysis involves initial analysis of data before building models. Descriptive statistics provide measures like mean, median, and maximum. Correlations study relationships between variables, and histograms show frequency distributions of variables. These techniques help identify patterns, errors, and appropriate modeling methods.

Uploaded by

hayder nuredin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
167 views8 pages

Presentation Exploratory Data Analysis

The document discusses exploratory data analysis techniques including descriptive statistics, correlations, and histograms. It explains that exploratory data analysis involves initial analysis of data before building models. Descriptive statistics provide measures like mean, median, and maximum. Correlations study relationships between variables, and histograms show frequency distributions of variables. These techniques help identify patterns, errors, and appropriate modeling methods.

Uploaded by

hayder nuredin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

EXPLORATORY DATA ANALYSIS

BASIC CONCEPTS AND INTERPRETATION


OUTLINE

DESCRIPTIVE CORRELATIONS HISTOGRAMS


STATISTICS
Exploratory data analysis deals with initial analysis of the
data before building actual models

It is a good idea to carefully study your data first, which


includes descriptive statistics, correlations and various graphs
EXPLORATORY
DATA ANALYSIS In this way, you can identify potential relationship in the data,
locate errors and other issues with data and select the best
modeling technique

Data preparation and initial analysis can be time consuming


but there exist a few quick approaches which we consider in
this presentation
SUMMARY
STATISTICS

 We typically start by looking at


descriptive statistics which you
can obtain from Data > Data
Analysis > Descriptive
Statistics

 We can select multiple


variables for analyses in “Input
Range” and then tick next to
“Summary statistics

 Then we can look at the mean,


median, maximum etc
CORRELATION

 Similarly, we can select Correlation from Data >


Data Analysis to study potential relationships
between variables

 We can also use Home > Conditional Formatting >


Data Bars to highlight the strength of correlation

 Age and Balance have positive correlation with


"Exited" while Active Members and Number of
Products are negatively correlated with churn
HISTOGRAM
 Histogram shows frequency
distribution of the variable

 To construct a histogram click


on Data > Data Analysis >
Histogram

 Then select the Input Range,


tick Cumulative Percentage and
Chart Output
Frequency

100
150
200
250
300

0
50
350
360
370
380
390
400
410
420
HISTOGRAM

430
440
450
460
470
480
490
500
510
520
530
540
550
560
570
580
590
600
Bin
610
620
630
640
650
660
Histogram

670
680
690
700
710
720
730
740
750
760
770
780
790
800
810
820
830
840
More
0.00%
20.00%
40.00%
60.00%
80.00%
100.00%
120.00%

Frequency
Cumulative %
THANK YOU!

Front and back photo by Scott Graham on Unsplash

You might also like