DATA SCIENCE

PROJECT

WEATHER ANALYSIS AND PREDICTIONS

N A M E : N I T H I S H W A R A N . G

S U B M I S S I O N D A T E : 2 0 / 1 2 / 2 4
2.INTRODUCTION
Objective:

The aim of "Weather Patterns Analysis and Prediction"

is to study atmospheric trends and climatic conditions
enabling accurate forecasting.
This helps in disaster preparedness, resource
management, and supporting agriculture
DATA OVERVIEW:

it involves studying atmospheric data to identify

recurring trends, such as temperature, pressure,
and precipitation patterns.
TOOLS AND TECHNIQUES
canva
chatgpt
3.EXPLORATORY DATA THE DETIALS IS TAKEN FROM IIT WEBSITE PROJECT (DATA SET)}

ANALYSIS
KEY FINDINGS:
1. Temperature (°C): Visibility (km):
Maximum: 45.0°C Maximum: 55.0 km
Minimum: 12.0°C Minimum: 0.2 km
Average: 30.79°C Average: 2.42 km
Median: 32.0°C Median: 2.0 km
2. Humidity (%): Rain Presence:
Maximum: 100% Rainy Days: 18
Minimum: 6% Dry Days: 712
Average: 36.34% Most Frequent Values:
Median: 34.0% Weather Condition: Haze
3. Pressure (hPa): Wind Direction: WNW
Maximum: 1026 hPa (West-Northwest)
Minimum: 994 hPa
Average: 1007.74 hPa
Median: 1008.0 hPa
3.EXPLORATORY DATA
ANALYSIS
GRAPHICAL REPRESENTATION
4.METHODOLOGY
K-Nearest Neighbors (K-NN) Classification K-Means Clustering
Steps: Steps:
1. Distance Calculation: 1. Initialization:
Calculate the distance between the new data Randomly select k data points as initial cluster
point and each of the training data points. centroids.
Common distance metrics include Euclidean 2. Assignment:
distance, Manhattan distance, and Minkowski Calculate the distance between each data point
distance. and each cluster centroid.
2. Selecting Nearest Neighbors: Assign each data point to the cluster with the
Sort the training data points based on their closest centroid.
distance from the new data point. 3. Recomputation:
Select the k closest neighbors. Calculate the new cluster centroids by taking the
3. Predicting Outcomes: mean of all data points assigned to each cluster.
Determine the most frequent class label among Repeat steps 2 and 3 until the cluster
the k nearest neighbors. assignments no longer change or a maximum
Assign this class label to the new data point. number of iterations is reached. 1
4.METHODOLOGY

VISUAL REPRESENTATION
 5.RESULT

K-Nearest Neighbors (K-NN) Classification Results K-Means Clustering Results

Example: Example:

Explanation: Explanation:
Data Point A: The nearest neighbors are B, C, and D. Two of these neighbors have the Cluster 1: Data points A, B, and C are assigned to this cluster. The centroid of
outcome "Rain," so the predicted outcome for A is "Rain." this cluster is calculated as the average of the coordinates of these points.
Data Point B: The nearest neighbors are E, F, and G. All three of these neighbors have the Cluster 2: Data points D, E, and F are assigned to this cluster. The centroid of
outcome "No Rain," so the predicted outcome for B is "No Rain." this cluster is calculated as the average of the coordinates of these points.
Data Point C: The nearest neighbors are A, D, and H. Two of these neighbors have the
outcome "Rain," so the predicted outcome for C is "Rain."
5.RESULT

Linking Results to Methodology:

K-NN Classification: The predicted outcomes are based on the majority vote of the nearest neighbors. The
distances between data points are used to determine the nearest neighbors.
K-Means Clustering: The final cluster assignments and centroids are determined by an iterative process of
assigning data points to the nearest centroid and then recalculating the centroids.
6.INSIGHTS AND
LEARNING TRENDS AND PATTERNS:

THERE IS A CLEAR RELATIONSHIP BETWEEN THE NUMBER OF HOURS

STUDIED AND THE EXAM SCORE.
STUDENTS WHO STUDY MORE TEND TO GET HIGHER SCORES.
THERE IS A POSITIVE CORRELATION BETWEEN THE TWO VARIABLES.

UNIQUE INSIGHTS:

THE LINEAR REGRESSION MODEL SHOWS THAT FOR EVERY ADDITIONAL

HOUR STUDIED, THE EXAM SCORE INCREASES BY 0.5 POINTS.
THIS INFORMATION CAN BE USED TO PREDICT EXAM SCORES BASED ON THE
NUMBER OF HOURS STUDIED.

HOW THE ANALYSIS TOOLS OR MACHINE LEARNING TECHNIQUES CONTRIBUTED TO

SOLVING THE PROBLEM:

THE LINEAR REGRESSION MODEL IS A POWERFUL TOOL FOR MODELING THE

RELATIONSHIP BETWEEN TWO VARIABLES.
IT ALLOWED US TO IDENTIFY THE TREND IN THE DATA AND MAKE
PREDICTIONS ABOUT EXAM SCORES.
7. CHALLENGES AND
RECOMMENDATION
CHALLENGES

It is very hard to search and many things and consumes

more time to plot graph and to make pie chart /bar
chart/table .
RECOMMENDATIONS
the student cant understand the project it takes long
time , if you give a voice note or some auido to clear
the students in the upcomming batches , i hope u
understand this some students are preparing this ppt
in thier moblie it is very to do it in moblie please
persuvate the students to do the project in lap/pc.
 CONCLUSION

This project aimed to uncover the relationship between hours studied and
exam scores. We found a strong positive correlation, meaning more study
time leads to higher scores. This highlights the importance of consistent effort
in academic success. Data science and AI can be powerful tools for extracting
meaningful insights from large datasets, enabling data-driven decision-
making in various fields.
 CHAT GPT GEMINI OTHER
WEBSITIES

I USED IT TO IT GENERATE ME

REFERENCES
GENERATE SOME SOME TABLES , AND WEBSITIES :
TEXT THAT I CANT I USED IN THIS CONVERITO
TYPE IN PROPER PROJECT GOOGLE SHEETS
ENGLISH EXEL
POWER POINT
CANVA