Data Analysis and Forecasting: Humidity in London - Nov 2019

This report presents a comprehensive analysis of London's humidity data over a ten-day period in November 2019. The analysis begins with data representation in both tabular and chart formats (bar and column charts). The report then delves into the calculation of key statistical measures including mean, median, mode, range, and standard deviation. Furthermore, the report applies a linear model to forecast humidity percentages for the 15th and 20th days, providing detailed calculations for the values of 'm' and 'c' used in the forecasting. The report concludes with a summary of the findings, emphasizing the practical application of data analysis techniques for informed decision-making and forecasting.

Numeracy and Data
Analysis

Table of Contents
INTRODUCTION ..........................................................................................................................3
MAIN BODY...................................................................................................................................3
1. Representation of data in tabular form:...................................................................................3
2. Dara representation in charts:..................................................................................................3
3. Calculations of mean, median, mode, standard deviation and range:......................................4
4. Calculating values of m, c and humidity forecast of day 15 and 20........................................7
CONCLUSION ...............................................................................................................................8
REFERENCES................................................................................................................................9

INTRODUCTION
Data analysis is a systematic process of collecting data from various sources and after
that making detailed analysis by help of vital range of techniques. This analysed data, helps to
business entities in order to make accurate decisions (Tsilimigras and Fodor, 2016). The project
report is based on analysing of data regards to humidity percentage of London city of ten days
(Humidity data of London, 2019). Report covers detailed calculation of different terms such as
mean-mode-median etc. In the end part of report, forecasting of humidity percentage is done by
help of linear model.
MAIN BODY
1. Representation of data in tabular form:
In this task of report, humidity data of London city for ten days has been presented in
format of table in below mentioned manner:
Days (Date) Humidity (values in %)
1st of November, 2019 98
2nd of November, 2019 89
3rd of November, 2019 89
4th of November, 2019 96
5th of November, 2019 98
6th of November, 2019 95
7th of November, 2019 94
8th of November, 2019 95
9th of November, 2019 98
10th of November, 2019 91

2. Dara representation in charts:
Bar chart- It is a type of graph or chart that presents monetary data in the form of rectangular
bars that contains heights proportional to values. Herein, below a bar chart is prepared that
includes information about humidity percentage of ten days:
1st of November, 2019
2nd of November, 2019
3rd of November, 2019
4th of November, 2019
5th of November, 2019
6th of November, 2019
7th of November, 2019
8th of November, 2019
9th of November, 2019
10th of November, 2019
84 86 88 90 92 94 96 98 100
98
89
89
96
98
95
94
95
98
91
Humidity (values in %)
Column chart- It is a type of graph or chart that presents monetary data in the form of vertical
bars that contains values horizontally (Wang and Sun, 2015). Herein, below a bar chart is
prepared that includes information about humidity percentage of ten days:
1st of November, 2019
4th of November, 2019
7th of November, 2019
10th of November, 2019
84
86
88
90
92
94
96
98
100
98
89 89
96
98
95 94 95
98
91 Humidity (values in %)

3. Calculations of mean, median, mode, standard deviation and range:
Days (Date) Humidity (values in %)
1st of November, 2019 98
2nd of November, 2019 89
3rd of November, 2019 89
4th of November, 2019 96
5th of November, 2019 98
6th of November, 2019 95
7th of November, 2019 94
8th of November, 2019 95
9th of November, 2019 98
10th of November, 2019 91
∑X 943
Mean 94.3
Mode 98
Median 95
Range 9
Maximum 98
Minimum 89
Mean- The term mean can be defined as a type of value that is computed by dividing addition of
all numbers by number of value. Herein, below formula to calculate mean is mentioned in such
manner:
Mean= ∑N/ N
N= 10
∑N= 943
Mean= 943/10
= 94.3
Mode- There is no any specific formula to compute mode in the case of individual data series
(Greenacre, 2017). This can derived by checking frequency of numbers in a data series and if a

number whose frequency is higher then it will be considered as mode. Such as in the above
mentioned data series, value of mode is 98 because its frequency is three that is higher among all
numbers.
Median- It is a mid value in a data series. This can be computed as per the nature of data like if
number of data are odd then formula will be as: M = N+1/2th item. While if number of data are
even then M = (N/2th item+N/2th item + 1)/2. Before applying this formula, it is necessary to
arrange all data in ascending order. Herein, below calculation of median of humidity data is done
in such manner:
S.
No.
Humidity (in terms of
%)
1 89
2 89
3 91
4 94
5 95
6 95
7 96
8 98
9 98
10 98
N = 10 (Even)
M = (N/2th item+N/2th item + 1)/2
= (10/2+10/2+1)2
= (5th item+6th item) / 2

= (95+95) / 2
= 95
Range- It is defined by making variation between maximum and minimum values among group
of numbers (Fisher, 2017). Such as in the above mentioned data of humidity, higher number is
98 and lower number is 89. So value of range is 9 (98-89).
Standard deviation- This may be defined as calculation of value of variation in any particular
data series. Herein, underneath calculation of standard-deviation is done below in such manner:
Days (Date) Humidity (values in %) (x- mean) (x-mean)2
1st of November, 2019 98 3.7 13.69
2nd of November, 2019 89 -5.3 28.09
3rd of November, 2019 89 -5.3 28.09
4th of November, 2019 96 1.7 2.89
5th of November, 2019 98 3.7 13.69
6th of November, 2019 95 0.7 0.49
7th of November, 2019 94 -0.3 0.09
8th of November, 2019 95 0.7 0.49
9th of November, 2019 98 3.7 13.69
10th of November, 2019 91 -3.3 10.89
112.1
Variance = [ ∑(x – mean) 2 / N ]
= 112.1/10
= 11.21
Standard deviation = √ ( variance )
= √ 11.21
= 3.35
4. Calculating values of m, c and humidity forecast of day 15 and 20.
Days (Date) Humidity (values in %) X2 ∑XY
1 98 1 98

2 89 4 178
3 89 9 267
4 96 16 384
5 98 25 490
6 95 36 570
7 94 49 658
8 95 64 760
9 98 81 882
10 91 100 910
∑X= 55 ∑Y= 943 ∑X2 = 385 ∑XY= 5197
1. Calculation of value of M-
M = N * ∑xy - ∑x * ∑y / N*∑x2 - ( ∑x )2
= 10*5197-55*943/10*385-(55)2
= 51970- 51865/3850-3025
= 105/825
= 0.13
2. Calculation of value of c:
C = ∑y- m ∑x/ N
= 943- 0.13* 55/10
= 943-0.715
= 942.28
3. Forecasting for 15th
Y= mx+c
= 0.13*15+942.28
= 944.23 or 94.44%
For 20th day
= 0.13*20+942.28

= 2.6+942.28
= 944.28 or 94.44%
CONCLUSION
On the basis of above project report, it has been concluded that data analysis contributes
effectively in order to make accurate judgements. Report concludes about computation of mean-
mode-median as per the given data set. As well as in further part of report, forecasting of
humidity is done for 15th and 20th day.

REFERENCES
Books and journal:
Tsilimigras, M .C. and Fodor, A .A., 2016. Compositional data analysis of the microbiome:
fundamentals, tools, and challenges. Annals of epidemiology. 26(5). pp.330-335.
Wang, D. and Sun, Z., 2015. Big data analysis and parallel load forecasting of electric power
user side. Proceedings of the CSEE. 35(3). pp.527-537.
Fisher, M., 2017. Qualitative computing: using software for qualitative data analysis. Routledge.
Greenacre, M., 2017. Correspondence analysis in practice. Chapman and Hall/CRC.
Online
Humidity data of London. 2019. [Online]. Available through:
<https://www.timeanddate.com/weather/uk/london/historic>