MACHINE LEARNING USING PYTHON

A PROJECT REPORT ON
WEATHER FORECASTING
SUBMITTED BY;

RUDRA NARYAN SAHU 233001220001

SWAYAM TRIPATHY 233001220002

SUBHRA SUMAN NAYAK 233001220003

SUSHANT KUMAR 233001220004

In partial fulfilment for the

award of the degree of

BACHELOR OF TECHNOLOGY

In

DAIRY

SCHOOL OF AGRICULTURAL AND BIO ENGINEERING

PARALAKHEMUNDI CAMPUS

CENTURION UNIVERSITY OF TECHNOLY OF MANAGEMENT

ODISHA

DEPARTMENT OF DAIRY TECHNOLOGY

PARALAKEMUNDI CAMPUS

SEPTEMBER 2024

i
 DEPARTMENT OF DAIRY TECHNOLOGY CENTURION UNIVERSITY OF
TECHNOLOGY&MANAGEMENT,
PARALAKHEMUNDI-761211

BONAFIDE CERTIFICATE

Certified that this project report “Restaurant Management System” is the

Bonafide work of “ SWAYAM TRIPATHY ” who carried out the project
work under my supervision. This is to further certify to the best of my
knowledge, that this project has not been carried out earlier in this institute
and the university.

SIGNATURE
(Prof. Pragnya das)
Asstt. Professor of School of Engineering

SIGNATURE
(Dr. Prasanta Kumar Choudhury)
HEAD OF THE DEPARTMENT
DAIRY TECHNOLOGY
SCHOOL OF AGRICULTURE & BIO- ENGINEERING

PARALAKHEMUNDI CAMPUS

DEPARTMENT SEAL

ii
 DECLARATION

I hereby declare that the project entitled “WEATHER FORECASTING”

submitted for the “Project” of 3th semester B. Tech in Dairy Technology is my
original work and the project has not formed the basis for the award of any
Degree / Diploma or any other similar titles in any other University / Institute.

Name of the Student: Swayam Tripathy

Signature of the Student:

Registration No: 233001220002

Place: Paralakhemundi

Date:

iii
 ACKNOWLEDGEMENTS
I wish to express my profound and sincere gratitude to Prof .Pragnya das, School of
Engineering CUTM, Paralakhemundi Campus, who guided me into the intricacies of this
project nonchalantly with matchless magnanimity.

I thank Dr. Prasanta Kumar Choudhury, Head of the Dept. of Department of Dairy
Technology, SOABE, Paralakhemundi Campus and Dr. Korla Harshwardhan, School of
Agriculture & Bio-Engineering, Paralakhemundi Campus for extending their support during
Course of this investigation.

Name of the Student: Swayam Tripathy

Signature of the Student:

Registration No:233001220002

Place: Paralakhemundi

Date:

iv
 TABLE OF CONTENTS

CHAPTERS PAGE NO

ABSTRACT 1
2
CHAPTER 1: INTRODUCTION
1.1 INTRODUCTION 2
1.2 PROBLEM DEFINITION 2
1.3 SCOPE 3
1.4 PURPOSE 3
1.5 PROBLEM AND EXISTING 4
TECHNOLOGY

1.6 PROPOSED SYSTEM 4

CHAPTER 2: REQIUREMENTS & ANALYSIS 5

2.1 PLATFORM REQUIREMENTS 5

2.2 MODULE DESCRIPTION 5

CHAPTER 3: DESIGN & IMPLEMENTATION 12

3.1 ALGORITHMS 12
3.2 PSEUDO CODE 12
CHAPTER 4: SCREENSHOTS 19

CHAPTER 5: CONCLUSION 21

CHAPTER 6: REFERENCES 21

v
 ABSTRACT

Weather forecasting is the application of science and technology to predict the

state of the atmosphere for a given location.Ancient weather forecasting methods
usually relied on observed patterns of events, also termed pattern recognition. For
example, it might be observed that if the sunset was particularly red, the following
day often brought fair weather.However, not all of these predictions prove reliable.

Here this system will predict weather based on parameters such as

temperature, humidity and wind. User will enter current temperature; humidity and
wind, System will take this parameter and will predict weather(rainfall in inches)
from previous data in database(dataset). The role of the admin is to add previous
weather data in database, so that system will calculate weather(estimated rainfall in
inches) based on these data. Weather forecasting system takes parameters such as
temperature, humidity, and wind and will forecast weather based on previous record
therefore this prediction will prove reliable. This system can be used in Air Traffic,
Marine, Agriculture, Forestry, Military, and Navy etc.

Page 2
 1.INTRODUCTION

• Data Warehousing

Data Warehouse is electronic storage of a large amount of information by

a business which is designed for query and analysis instead of transaction
processing. It is a process of transforming data into information and making it
available to users for analysis.

• Data Mining

Data mining is looking for hidden, valid, and potentially useful patterns in
huge data sets. Data Mining is all about discovering unsuspected/ previously
unknown relationships amongst the data.It is a multi-disciplinary skill that uses
machine learning, statistics, AI and database technology.

1.1. Introduction

Rainfall Prediction is the application of science and technology to predict the amount
of rainfall over a region. It is important to exactly determine the rainfall for effective
use of water resources, crop productivity and pre-planning of water structures.

In this project, we used Linear Regression to predict the amount of rainfall. Linear
Regression tells us how many inches of rainfall we can expect.

1.2 Problem Definition

It is important to exactly determine the rainfall for effective use of water resources,
crop productivity and pre-planning of water structures.

Page 2
1.3 Scope
It tells us how many inches of rainfall we can expect.
1.4 Purpose
There are several reasons why weather forecasts are important. They would certainly
be missed if they were not there. It is a product of science that impacts the lives of
many people. The following is a list of various reasons why weather forecasts are
important:

1. Helps people prepare for how to dress (i.e. warm weather, cold weather, windy
weather, rainy weather)
2. Helps businesses and people plan for power production and how much power to
use (i.e. power companies, where to set thermostat)
3. Helps people prepare if they need to take extra gear to prepare for the weather (i.e.
umbrella, rain coat, sun screen)
4. Helps people plan outdoor activities (i.e. to see if rain/storms/cold weather will
impact outdoor event)
5. Helps curious people to know what sort of weather can be expected (i.e. a snow
on the way, severe storms)
6. Helps businesses plan for transportation hazards that can result from the weather
(i.e. fog, snow, ice, storms, clouds as it relates to driving and flying for example)
7. Helps people with health related issues to plan the day (i.e. allergies, asthma, heat
stress)
8. Helps businesses and people plan for severe weather and other weather hazards
(lightning, hail, tornadoes, hurricanes, ice storms)
9. Helps farmers and gardeners plan for crop irrigation and protection (irrigation
scheduling, freeze protection)

Page 3
1.5 Problem and Existing Technology

The traditional forecast process employed by most NMHSs involves forecasters

producing text-based, sensible, weather-element forecast products (e.g.
maximum/minimum temperature, cloud cover) using numerical weather prediction
(NWP) output as guidance. The process is typically schedule-driven, product-
oriented and labour-intensive. Over the last decade, technological advances and
scientific breakthroughs have allowed NMHSs’ hydrometeorological forecasts and
warnings to become much more specific and accurate.

As computer technology and high-speed dissemination systems evolved (e.g.

Internet), National Weather Service (NWS) customers/partners were demanding
detailed forecasts in gridded, digital and graphic formats. Traditional NWS text
forecast products limit the amount of additional information that can be conveyed to
the user community. The concept of digital database forecasting provides the
capability to meet customer/partner demands for more accurate, detailed
hydrometeorological forecasts. Digital database forecasting also offers one of the
most exciting opportunities to integrate PWS forecast dissemination and service
delivery, which most effectively serves the user community.

1.6 Proposed System

User will enter current temperature; humidity and wind, System will take this
parameter and will predict weather from previous data in database. The role of the
admin is to add previous weather data in database, so that system will calculate
weather based on these data. Weather forecasting system takes parameters such as
temperature, humidity, and wind and will forecast weather based on previous record
therefore this prediction will prove reliable.

Page 4
 2. REQUIREMENTS

2.1. Platform Requirements

Hardwar
e/Softwa Hardware / Software element Specification /version
re

Hardwar Processor i3
e
RAM 2GB

Hard Disk 250GB

Software OS Windows,Linux.

Python IDE Jupyter

NoteBook.
Microsoft Azure
Python 3.

2.2. Modules Description

In this project we have Two modules

1) Data gathering and pre - processing.

2) Applying Algorithm for prediction .

Page 5
Explanation:
1) In this module we first gather the data(dataset) for our prediction model.Data
comes in all forms, most of it being very messy and unstructured. They rarely come
ready to use. Datasets, large and small, come with a variety of issues- invalid fields,
missing and additional values, and values that are in forms different from the one we
require. In order to bring it to workable or structured form, we need to “clean” our
data, and make it ready to use. Some common cleaning includes parsing, converting
to one-hot, removing unnecessary data, etc.

In our case, our data has some days where some factors weren’t recorded. And the
rainfall in cm was marked as T if there was trace precipitation. Our algorithm
requires numbers, so we can’t work with alphabets popping up in our data. so we
need to clean the data before applying it on our model.

2)Once the data is cleaned, In this module that cleaned data can be used as an input
to our Linear regression model. Linear regression is a linear approach to form a
relationship between a dependent variable and many independent explanatory
variables. This is done by plotting a line that fits our scatter plot the best, ie, with the
least errors. This gives value predictions, ie, how much, by substituting the
independent values in the line equation.

We will use Scikit-learn’s linear regression model to train our dataset. Once the
model is trained, we can give our own inputs for the various columns such as
temperature, dew point, pressure, etc. to predict the weather based on these
attributes.

Page 6
Module Outcomes:
1) By the end of the first module the fully cleaned and useful data is available for
the apply the algorithm for the prediction.
1) By the end of the second module the actual prediction will be happen the outcome
is the amount of rainfall in inches based upon the users input.

Algorithm:

Linear Regression is a machine learning algorithm based on supervised learning. It

performs a regression task. Regression models a target prediction value based on
independent variables. It is mostly used for finding out the relationship between
variables and forecasting. Different regression models differ based on – the kind of
relationship between dependent and independent variables, they are consideringand
the number of independent variables being used.

Page 7
Linear regression performs the task to predict a dependent variable value (y) based
on a given independent variable (x). So, this regression technique finds out a linear
relationship between x (input) and y(output). Hence, the name is Linear Regression.
In the figure above, X (input) is the work experience and Y (output) is the salary of
a person. The regression line is the best fit line for our model.

Hypothesis function for Linear Regression :

y=mx+c

Where

y is the response variable.

x is the predictor variable.

m and c are constants which are called the coefficients.

Page 8
2.3. Data Set

The dataset is a public weather dataset from Austin, Texas available on Kaggle.

austin_weather.csv

Columns:

Date-

The date of the collection (YYYY-MM-DD)

TempHighF-

High temperature, in degrees Fahrenheit

TempAvgF-

Average temperature, in degrees Fahrenheit

TempLowF-

Low temperature, in degrees Fahrenheit

DewPointHighF-

High dew point, in degrees Fahrenheit

DewPointAvgF-

Average dew point, in degrees Fahrenheit

DewPointLowF-

Low dew point, in degrees Fahrenheit

HumidityHighPercent-

High humidity, as a percentage

Page 9
HumidityAvgPercent-

Average humidity, as a percentage

HumidityLowPercent-

Low humidity, as a percentage

SeaLevelPressureHighInches-

High sea level pressure, in inches of mercury

SeaLevelPressureAvgInches-

Average sea level pressure, in inches of mercury

SeaLevelPressureLowInches-

Low sea level pressure, in inches of mercury

VisibilityHighMiles-

High visibility, in miles

VisibilityAvgMiles-

Average visibility, in miles

VisibilityLowMiles-

Low visibility, in miles

WindHighMPH-

High wind speed, in miles per hour

WindAvgMPH-

Average wind speed, in miles per hour

Page 10
WindGustMPH-

Highest wind speed gust, in miles per hour

PrecipitationSumInches-

Total precipitation, in inches ('T' if trace)

Events-

Adverse weather events (' ' if None)

Page 11
3.DESIGN AND IMPLEMENTATION
3.1 Algorithms:
Linear Regression:
Module-1 :Data gathering and pre - processing.

Module-2: Applying Algorithm for prediction .

3.2Source Code
# importing libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# read the data in a pandas dataframe

data = pd.read_csv("C:/Users/TEMP.SANDEEP/Desktop/austin_weather.csv")

#seeing head values

data.head(5)
#seeing shape of the dataset
data.shape

#filling missing NULL values by column means

data.fillna(data.mean())

# drop or delete the unnecessary columns in the data.

data = data.drop(['Events', 'Date', 'SeaLevelPressureHighInches',
'SeaLevelPressureLowInches'], axis = 1)

# some values have 'T' which denotes trace rainfall

Page 12
# we need to replace all occurrences of T with 0
# so that we can use the data in our model
data = data.replace('T', 0.0)

# the data also contains '-' which indicates no

# or NIL. This means that data is not available
# we need to replace these values as well.
data = data.replace('-', 0.0)

# dataframe created with

# the above data array
df = pd.DataFrame(data)

# create histogram for numeric data

df.hist()

# show plot
plt.show()
#basic static

# save the data in a csv file

data.to_csv('C:/Users/TEMP.SANDEEP/Desktop/austin_final_final.csv')

# importing libraries
import pandas as pd
import numpy as np

Page 13
import sklearn as sk
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

# read the cleaned data

data = pd.read_csv("C:/Users/TEMP.SANDEEP/Desktop/austin_final_final.csv")

# the features or the 'x' values of the data

# these columns are used to train the model
# the last column, i.e, precipitation column
# will serve as the label
X = data.drop(['PrecipitationSumInches'], axis = 1)

# the output or the label.

Y = data['PrecipitationSumInches']
# reshaping it into a 2-D vector
Y = Y.values.reshape(-1, 1)

# consider a random day in the dataset

# we shall plot a graph and observe this
# day
day_index = 798
days = [i for i in range(Y.size)]

# initialize a linear regression classifier

clf = LinearRegression()

Page 14
# train the classifier with our
# input data.
clf.fit(X, Y)

# give a sample input to test our model

# this is a 2-D vector that contains values
# for each column in the dataset.
inp = np.array([[74], [60], [45], [67], [49], [43], [33], [45],
[57], [29.68], [10], [7], [2], [0], [20], [4], [31]])
inp = inp.reshape(1, -1)

# print the output.

print('The precipitation in inches for the input is:', clf.predict(inp))

# plot a graph of the precipitation levels

# versus the total number of days.
# one day, which is in red, is
# tracked here. It has a precipitation
# of approx. 2 inches.
print("the precipitation trend graph: ")
plt.scatter(days, Y, color = 'g')
plt.scatter(days[day_index], Y[day_index], color ='r')
plt.title("Precipitation level")
plt.xlabel("Days")
plt.ylabel("Precipitation in inches")

Page 15
plt.show()
x_vis = X.filter(['TempAvgF', 'DewPointAvgF', 'HumidityAvgPercent',
'SeaLevelPressureAvgInches', 'VisibilityAvgMiles',
'WindAvgMPH'], axis = 1)

# plot a graph with a few features (x values)

# against the precipitation or rainfall to observe
# the trends

print("Precipitation vs selected attributes graph: ")

for i in range(x_vis.columns.size):
plt.subplot(3, 2, i + 1)
plt.scatter(days, x_vis[x_vis.columns.values[i][:100]],
color = 'g')

plt.scatter(days[day_index],
x_vis[x_vis.columns.values[i]][day_index],
color ='r')

plt.title(x_vis.columns.values[i])

plt.show()

OUTPUT:

Page 16
The precipitation in inches for the input is: [[1.33868402]]

Graphs:
1) Histogram for Temp

2)The precipitation trend graph:

Page 17
A day (in red) having precipitation of about 2 inches is tracked across multiple
parameters (the same day is tracker across multiple features such as temperature,
pressure, etc). The x-axis denotes the days and the y-axis denotes the magnitude of
the feature such as temperature, pressure, etc. From the graph, it can be observed
that rainfall can be expected to be high when the temperature is high and humidity
is high.

Page 18
3. SCREENSHOTS

Page 19
4. CONCLUSION

We successfully predicted the rainfall using the linear regression but here this is not
very accurate only some times any way it depends upon the climate changes to
season to season.Here we are taking only summer season weather data set it only
useful to predict rainfall in summer season.

5. REFERENCES

Textbooks:-

1. Data Mining: The Textbook 2015 Edition, Kindle Editionby Charu C.

Aggarwal .

2. Data Mining: Concepts and TechniquesBy Jiawei Han, Jian Pei, Micheline
Kamber.

Page 20
Weblinks:-

1) https://towardsdatascience.com/introduction-to-machine-learning-algorithms-
linear-regression-14c4e325882a

2) https://www.kaggle.com/grubenm/austin-weather

Page 21