HOUSE PRICE PREDICTION USING MACHINE

LEARNING
A SUMMER SKILL ENHANCEMENT COURSE REPORT
Submitted by
HARI OM
Enrollment Number: 02214812722
in partial fulfilment of Summer Skill Course for the award of the degree
of

BACHELOR OF TECHNOLOGY

IN

COMPUTER SCIENCE AND TECHNOLOGY

MAHARAJA AGRASEN INSTITUTE OF TECHNOLOGY

ROHINI, NEW DELHI

 MAHARAJA AGRASEN INSTITUTE OF TECHNOLOGY

To Whom It May Concern

I, HARI OM, Enrolment no. 02214812722, a student of Bachelor of Technology (CST), a class
of 2022-2026, Maharaja Agrasen Institute of Technology, Rohini, New Delhi hereby declare
that the Summer Training Project report entitled “HOUSE PRICE PREDICTION USING
MACHINE LEARNING” is an original work and the same has not been submitted to any other
Institute for the award of any other degree.

Date:
Place:

HARI OM
Enrollment Number: 02214812722
Computer Science & Technology
5CST123
 ACKNOWLEDGEMENT

I would like to express my special thanks to Dr. POOJA GUPTA, HOD of department of Computer
Science and Technology, and Dr. NAVNEET YADAV, counsellor teacher, for their able guidance
and support in completion of my project, “HOUSE PRICE PREDICTION USING MACHINE
LEARNING” using Flask, NumPy, Pandas, Pickle in python. I would also like to thank 365
Careers and Udemy for providing the Data Science Course 2024 to acquire the required knowledge
and learnings of Data Science and the project.

I would also like to extend my gratitude my college “MAHARAJA AGRASEN INSTITUTE OF

TECHNOLOGY” for providing with the knowledge and support required for the project.

Thank You

HARI OM
02214812722
5CST123/CST2
 ABOUT THE DATA SCIENCE BOOTCAMP COURSE
BY 365 CAREERS

The Data Science Bootcamp course by 365 Careers on Udemy is a comprehensive program
designed to equip learners with the foundational skills needed for a career in data science. This
course covers a wide range of topics, including:

• Python Programming: Learn the essentials of Python, focusing on data manipulation with
libraries like Pandas and NumPy.
• Data Visualization: Gain skills in creating effective visualizations using Matplotlib and
Seaborn.
• Statistical Analysis: Understand key statistical concepts necessary for data interpretation
and analysis.
• Machine Learning: Explore machine learning algorithms and their applications through
practical exercises using Scikit-learn.
• Real-World Projects: Apply your knowledge through hands-on projects that simulate real
data science challenges, helping to build a portfolio.

The aim of the course is to provide learners with a comprehensive foundation in data science,
enabling them to:

1. Acquire Essential Skills: Learn programming, data analysis, visualization, and machine
learning techniques using Python and relevant libraries.
2. Understand Data Science Concepts: Gain a solid grasp of key statistical and
mathematical concepts that underpin data analysis and modeling.
3. Apply Knowledge Practically: Engage in hands-on projects that allow learners to apply
theoretical knowledge to real-world scenarios, enhancing their problem-solving abilities.
4. Build a Portfolio: Develop a portfolio of projects that showcase skills and expertise to
potential employers, increasing job readiness in the data science field.
5. Prepare for Career Opportunities: Equip participants with the knowledge and skills
needed to pursue entry-level positions in data science, analytics, or related fields.

Overall, the course aims to transform beginners into competent data scientists ready to tackle data-
driven challenges in various industries.
 ABSTRACT

This project focuses on developing a machine learning model for predicting house prices based on
various features, such as location, size, number of bedrooms, and other characteristics. Using a
dataset sourced from [insert source, e.g., Kaggle], we performed extensive data preprocessing,
including cleaning, normalization, and feature encoding. Through exploratory data analysis, we
identified key trends and relationships that informed our modeling approach. We employed several
machine learning algorithms, including Linear Regression, Decision Trees, and Random Forests,
evaluating their performance using metrics such as Mean Absolute Error (MAE) and R-squared.
The Random Forest model emerged as the most accurate, demonstrating its effectiveness in
capturing the complexities of the housing market. This project underscores the potential of
machine learning to assist stakeholders in making informed decisions in real estate by providing
reliable price predictions.

The Linear Regression model served as a foundational benchmark, offering valuable insights into
the relationships between independent variables and the target price. While it provided a
straightforward interpretation of how each feature contributed to price predictions, its
assumptions—such as linearity and homoscedasticity—were tested against more complex models.
Despite its limitations in capturing nonlinear relationships, Linear Regression offered a baseline
that highlighted the effectiveness of more advanced models.
 CERTIFICATE OF COMPLETION

Videos Length: 32 Hours

Coding Exercise: 137
Articles: 93
Quizzes: 100+
Downloadable Resources: 541
 TABLE OF CONTENTS
S.No. Chapter Page No.

1 INTRODUCTION
1.1 Data Science 1
1.2 Evolution of Data Science 2
1.3 Machine Learning 3
1.4 Types of Machine Learning 3
1.5 Linear Regression 5

2 BRIEF AND OBJECTIVE

2.1 Project Brief 8
2.2 Objective 8

3 TECHNOLOGIES & TOOLS USED

3.1 Programming Language 10
3.2 Libraries 10
3.3 Tools 12

4 METHODOLOGY
4.1 Data Collection 17
4.2 Data Preprocessing 17
4.3 Feature Engineering 18
4.4 Data Splitting 18
4.5 Applying Linear Regression 18
4.6 Pipeline Creation 18
4.7 Model Evaluation 19
4.8 Model Deployment 19

5 IMPLEMENTATION & OUTCOMES

5.1 Codes 20
5.2 Web Interface 31
5.3 Outcomes 32

6 CONCLUSION 34
7 REFERENCES 35
 LIST OF FIGURES
S.No. Figure No. Description Page No.

1 Figure 1 Example of Linear and Non-Linear 6

2 Figure 2 Homoscedasticity Residual Plot 7
3 Figure 3 Pipeline for Linera Regression 19

LIST OF IMAGES
S.No. Image No. Description Page No.

1 Image 5.1 Link for Web 31

2 Image 5.2 Web Interface 31
3 Image 5.3 First Input 32
4 Image 5.4 First Output 32
5 Image 5.5 Second Input 33
6 Image 5.6 Second Output 33

LIST OF TABLES
S.No. Table No. Description Page No.

1 Table 1 Dataset Used 30

 CHAPTER 1
INTRODUCTION
1.1 Data Science

Data science is an interdisciplinary field that combines statistics, mathematics, programming, and
domain expertise to extract meaningful insights and knowledge from structured and unstructured
data. As the volume of data generated globally continues to grow exponentially, the demand for
data-driven decision-making has surged across industries, making data science a critical area of
study and application[1].

At its core, data science involves the following key components:

1. Data Collection: Gathering data from various sources, including databases, online
platforms, and sensors. This can involve both qualitative and quantitative data.
2. Data Cleaning and Preparation: Preprocessing data to handle missing values, outliers,
and inconsistencies, ensuring it is in a suitable format for analysis.
3. Exploratory Data Analysis (EDA): Analyzing datasets to uncover patterns, trends, and
relationships through visualization and statistical techniques.
4. Model Building: Applying machine learning algorithms and statistical methods to develop
predictive models that can forecast outcomes or classify data.
5. Validation and Evaluation: Testing model performance using various metrics to ensure
accuracy and reliability before deployment.
6. Communication of Insights: Presenting findings through visualizations, reports, or
dashboards, making complex data understandable to stakeholders.

Data science finds applications in various domains, including finance (risk assessment, fraud
detection), healthcare (patient outcome predictions, personalized medicine), marketing (customer
segmentation, targeted advertising), and many others. By leveraging data, organizations can
optimize operations, enhance customer experiences, and drive innovation.

As technology continues to evolve, the field of data science is rapidly expanding, offering exciting
career opportunities for those skilled in data analysis, machine learning, and statistical modeling.
With its capacity to transform raw data into actionable insights, data science plays a pivotal role
in shaping the future of industries and society as a whole.
1.2 Evolution of Data Science

The evolution of data science has been shaped by advancements in technology, computing power,
and the increasing importance of data-driven decision-making. Here’s a brief overview of its key
stages:

1. Early Beginnings (1960s - 1980s)

• Statistics and Data Analysis: The roots of data science can be traced back to traditional
statistics and data analysis. During this period, statisticians developed methods for
analyzing data, focusing on hypothesis testing and descriptive statistics.
• Emergence of Computers: The advent of computers allowed for more complex
calculations and data management, paving the way for more sophisticated analyses[2].

2. Rise of Data Mining (1990s)

• Data Warehousing: Businesses began to collect large amounts of data, leading to the
development of data warehousing. This allowed for centralized storage and retrieval of
data.
• Data Mining Techniques: The term "data mining" emerged, referring to the extraction of
patterns and knowledge from large datasets. Techniques like clustering, classification, and
association rules became popular[3].

3. Introduction of Machine Learning (2000s)

• Algorithmic Advances: Machine learning gained traction as algorithms like decision trees,
support vector machines, and neural networks were developed, allowing computers to learn
from data without explicit programming.
• Open Source Tools: The rise of open-source programming languages like R and Python,
along with libraries such as scikit-learn and TensorFlow, made it easier for practitioners to
apply machine learning techniques[4].

4. Big Data Revolution (2010s)

• Volume, Variety, Velocity: The explosion of data from various sources (social media, IoT,
etc.) gave rise to the concept of "big data." Tools like Hadoop and Spark emerged to handle
large-scale data processing.
• Data Science as a Discipline: Data science began to be recognized as a distinct field,
combining statistics, computer science, and domain expertise. The role of the data scientist
emerged, blending skills in programming, statistics, and analytical thinking[5].
5. AI and Deep Learning (2015 - Present)
• Deep Learning: Advances in neural networks, particularly deep learning, revolutionized
fields like image recognition, natural language processing, and speech recognition.
Frameworks like PyTorch and Keras made it accessible.
• Integration into Business: Organizations increasingly integrate data science into their
decision-making processes, using predictive analytics and real-time insights to drive
strategy[6].

6. Future Trends
• Ethics and Responsible AI: As data science becomes more pervasive, ethical
considerations around data privacy, bias, and accountability are gaining attention.
• Automated Machine Learning (Auto ML): Tools that automate model selection, training,
and evaluation are emerging, making data science more accessible to non-experts.
• Interdisciplinary Collaboration: Data science continues to evolve through collaboration
with fields like biology, economics, and social sciences, leading to innovative applications
and research[7].

1.3 Machine Learning

Machine learning (ML) is a subset of artificial intelligence (AI) that enables systems to learn from
data, identify patterns, and make decisions with minimal human intervention. Unlike traditional
programming, where explicit rules are coded to perform tasks, machine learning algorithms
improve their performance as they are exposed to more data over time. This adaptability makes
ML particularly powerful for handling complex problems across various domains, from finance to
healthcare to marketing.

1.4 Types of Machine Learning

Machine learning can be broadly categorized into three main types:

1. Supervised Learning:
In supervised learning, the model is trained on a labeled dataset, meaning that the input
data comes with corresponding output labels. The goal is for the model to learn the
relationship between the input and output so it can make accurate predictions on unseen
data[8].
Examples:
a. Classification tasks (e.g., spam detection in emails, sentiment analysis)
b. Regression tasks (e.g., predicting house prices, stock prices)
2. Unsupervised Learning:
 Unsupervised learning deals with unlabeled data, where the model seeks to identify
patterns or groupings within the data without predefined outcomes. The objective is to
explore the data and extract meaningful insights[9].
Examples:
a. Clustering (e.g., customer segmentation, grouping similar items)
b. Dimensionality reduction (e.g., PCA for feature reduction, visualizing high-
dimensional data)

3. Reinforcement Learning:
In reinforcement learning, an agent learns to make decisions by taking actions in an
environment to maximize cumulative rewards. The agent receives feedback in the form of
rewards or penalties, guiding it toward optimal behavior over time[10].
Examples:
a. Game playing (e.g., AlphaGo, chess)
b. Robotics (e.g., teaching robots to navigate or perform tasks)

Machine learning is transforming industries by enabling data-driven decision-making and

automation. Each type of machine learning serves unique purposes and is suited for different
types of problems, making it a versatile tool in the modern technological landscape. As data
continues to grow, the importance of machine learning in analyzing and extracting insights
from this information will only increase.

1.4.1 Types of Supervised Learning

Supervised learning can be primarily divided into two main types based on the nature of the output
variable: classification and regression. Here’s a closer look at each type:

1. Classification

Classification involves predicting a discrete label or category for a given input. The model is
trained on a dataset containing input-output pairs, where the outputs are categorical[11].

Examples:
• Binary Classification: Distinguishing between two classes (e.g., spam vs. not spam in
email filtering).
• Multi-Class Classification: Assigning inputs to one of three or more classes (e.g.,
classifying images of animals into categories like dog, cat, or bird).
• Multi-Label Classification: Assigning multiple labels to each input (e.g., tagging an
article with multiple topics).
Algorithms: Logistic Regression, Decision Trees, Random Forests, Support Vector Machines,
Neural Networks.
2. Regression

Regression is used for predicting a continuous numeric value based on input features. The goal is
to model the relationship between the input variables and the continuous output variable[12].

Examples:
• Predicting house prices based on features like size, location, and number of bedrooms.
• Estimating sales revenue based on advertising spend and market conditions.
• Forecasting stock prices or other financial metrics.
Algorithms: Linear Regression, Polynomial Regression, Decision Trees, Random Forests,
Support Vector Regression.

1.5 Linear Regression

Linear regression is a statistical method used to model the relationship between a dependent
variable (target) and one or more independent variables (predictors). The main objective is to find
the linear equation that best describes the relationship, allowing for predictions of the target
variable based on new input data.

Key Features:

1. Simple vs. Multiple Linear Regression:

a. Simple Linear Regression: Involves one independent variable and one dependent
variable, represented by the equation y=mx+b, where m is the slope and b is the
intercept.
b. Multiple Linear Regression: Involves multiple independent variables, represented
by the equation y=b0+b1x1+b2x2+...+bnxn.

2. Applications:
a. Used in various fields, including economics (predicting sales), real estate
(estimating property prices), and health sciences (forecasting outcomes).

3. Advantages:
a. Simple to implement and interpret.
b. Computationally efficient, requiring minimal resources.

4. Limitations:
a. Sensitive to outliers, which can skew results.
 b. Assumes a linear relationship, which may not hold true for complex datasets.

1.5.1 Assumptions for Simple Linear Regression

Linearity: The independent and dependent variables have a linear relationship with one
another. This implies that changes in the dependent variable follow those in the
independent variable(s) in a linear fashion.

Figure 1: Example of Linera and Non-Linear.

Independence: The observations in the dataset are independent of each other. This means that the
value of the dependent variable for one observation does not depend on the value of the dependent
variable for another observation. If the observations are not independent, then linear regression
will not be an accurate model.

Normality: The residuals should be normally distributed. This means that the residuals should
follow a bell-shaped curve. If the residuals are not normally distributed, then linear regression will
not be an accurate model.

Homoscedasticity: Across all levels of the independent variable(s), the variance of the errors is
constant. This indicates that the amount of the independent variable(s) has no impact on the
variance of the errors. If the variance of the residuals is not constant, then linear regression will
not be an accurate model.
Figure 2: Homoscedasticity Residual Plot.
 CHAPTER 2
BRIEF AND OBJECTIVE
2.1 Project Brief

The house price prediction project is a practical application of data science and machine learning
techniques aimed at estimating the selling price of residential properties based on various features.
With the growing significance of real estate in economics, accurate price predictions can benefit
buyers, sellers, and real estate professionals alike.

In this project, historical data about houses—such as the number of bedrooms, square footage,
location, and amenities—is analyzed to identify patterns and relationships that influence property
values. By employing machine learning algorithms, the project aims to create a model that can
predict house prices with high accuracy, allowing stakeholders to make informed decisions.

This project not only highlights the use of data preprocessing, exploratory analysis, and modeling
but also showcases the importance of data-driven insights in the real estate market. It serves as a
valuable learning experience for those looking to deepen their understanding of predictive
analytics and its real-world applications.

2.2 Objective

1. Accurate Price Estimation: To create a model that accurately predicts house prices based
on key features, providing reliable estimates for buyers, sellers, and real estate agents.

2. Understanding Feature Impact: To analyze and quantify the influence of various factors
(e.g., location, size, number of bedrooms) on house prices, helping stakeholders make
informed decisions.

3. Benchmarking Model Performance: To establish a baseline using linear regression,

which can be compared against more complex models in future analyses.

4. Facilitating Data-Driven Decisions: To assist buyers, sellers, and investors in making

informed decisions by providing actionable insights derived from data analysis

5. Market Trend Analysis: To identify and explore trends in the real estate market,
contributing to a better understanding of pricing dynamics.

6. Identifying Outliers: To detect anomalies or outliers in house prices that could indicate
unique market conditions or data issues.
 7. Foundation for Advanced Models: To lay the groundwork for future research and the
development of more sophisticated predictive models that may incorporate non-linear
relationships or additional data sources.

By achieving these objectives, the model aims to enhance understanding and decision-making in
the real estate market.
 CHAPTER 3
TECHNOLOGIES & TOOLS USED
3.1 Programming Language

Python is a high-level, interpreted programming language renowned for

its clear syntax and readability. Developed by Guido van Rossum and
released in 1991, Python emphasizes simplicity and efficiency, making
it an ideal choice for beginners as well as experienced programmers. Its
versatility allows it to be used in various domains, including web
development, data analysis, artificial intelligence, scientific computing,
automation, and more[13].

Key features of Python include:

• Ease of Learning: Python's straightforward syntax makes it accessible for newcomers.

• Rich Ecosystem: It boasts a vast collection of libraries and frameworks, such as NumPy,
pandas, TensorFlow, and Django, which facilitate a wide range of applications.

• Cross-Platform: Python runs on multiple operating systems, including Windows, macOS,

and Linux.

• Strong Community Support: A large and active community provides resources, tutorials,
and libraries, fostering collaboration and knowledge sharing.

Python's combination of simplicity, versatility, and community support has established it as one
of the most popular programming languages in the world.

3.2 Libraries

1. Flask

Flask is a lightweight and flexible web framework for Python, designed to help developers build
web applications quickly and easily. It follows the WSGI (Web Server Gateway Interface)
standard and is often described as a micro-framework because it does not include many built-in
features found in larger frameworks like Django. Instead, Flask provides the essential tools for
routing, templating, and handling requests, allowing developers to choose additional libraries and
extensions as needed[14].

• Key Features:
 o Simplicity: Flask’s minimalist approach makes it easy to get started and build small
to medium-sized applications.
o Modular Design: Developers can easily add functionality through extensions, such
as Flask-SQLAlchemy for database integration or Flask-Login for user
authentication.
o Built-in Development Server: Flask includes a simple web server for development
purposes, making it easy to test applications locally.
o Templating with Jinja2: Flask uses Jinja2 for templating, enabling dynamic
HTML generation with placeholders and control structures.
• Use Cases: Flask is often used for developing RESTful APIs, web applications, and
dashboards, particularly in data science and machine learning projects.

2. Pickle

Pickle is a Python module used for serializing and deserializing Python objects. Serialization (or
"pickling") converts an object into a byte stream that can be saved to a file or transmitted over a
network, while deserialization (or "unpickling") restores the object from the byte stream[15].

• Key Features:
o Easy to Use: Pickle provides simple functions (pickle.dump() and pickle.load())
for saving and loading objects.
o Support for Complex Objects: It can handle various Python data types, including
lists, dictionaries, and user-defined classes.
o Versioning: Pickle supports versioning, allowing compatibility across different
versions of Python.
• Use Cases: Pickle is commonly used for saving machine learning models, caching data, or
storing configurations, enabling easy restoration of objects during future sessions.

3. Pandas

Pandas is a powerful data manipulation and analysis library for Python, designed to make working
with structured data more accessible and efficient. It provides two primary data structures: Series
(1D) and DataFrame (2D), which allow for flexible data handling and analysis[16].

• Key Features:
o Data Alignment: pandas automatically aligns data for arithmetic operations,
making it easy to work with datasets.
o Data Cleaning and Transformation: It offers extensive tools for cleaning,
transforming, and aggregating data, making preprocessing straightforward.
o Time Series Support: pandas includes robust support for handling time series data,
allowing for resampling, shifting, and time-based indexing.
 o Integration with Other Libraries: It works well with libraries like NumPy and
Matplotlib for numerical computations and data visualization.
• Use Cases: pandas is widely used in data analysis, exploratory data analysis (EDA), and
data preprocessing in machine learning workflows.

4. NumPy

NumPy (Numerical Python) is a fundamental library

for numerical computing in Python. It provides
support for large, multi-dimensional arrays and
matrices, along with a wide array of mathematical
functions to operate on these data structures[17].

• Key Features:
o N-dimensional Arrays: NumPy’s ndarray is a fast and flexible container for large
datasets in Python.
o Broadcasting: It supports broadcasting, allowing operations on arrays of different
shapes without the need for explicit replication.
o Performance: NumPy operations are implemented in C, providing significant
performance improvements over standard Python lists.
o Mathematical Functions: It includes a comprehensive collection of mathematical
functions for array operations, linear algebra, and random number generation.
• Use Cases: NumPy is commonly used in scientific computing, data analysis, and machine
learning, providing the foundation for many other libraries, including pandas and scikit-
learn.

5. Scikit-learn

Scikit-learn is a powerful and widely-used machine learning library for Python. It provides simple
and efficient tools for data mining and data analysis, with a focus on usability and performance.
Built on top of NumPy, SciPy, and Matplotlib, scikit-learn offers a rich collection of algorithms
for classification, regression, clustering, and dimensionality reduction[18].

• Key Features:
 o Wide Range of Algorithms: It includes numerous algorithms, such as decision
trees, support vector machines, and neural networks, making it versatile for various
ML tasks.
o Easy to Use: The library follows a consistent API, making it easy to switch between
different algorithms and pipelines.
o Model Evaluation: It provides utilities for model evaluation and selection,
including cross-validation and performance metrics.
o Pipelines: scikit-learn allows the creation of pipelines to streamline the process of
data preprocessing, model fitting, and evaluation.
• Use Cases: scikit-learn is used in various machine learning applications, from basic
predictive modeling to complex data science projects, making it a go-to library for
practitioners and researchers.
3.3 Tools

1. Jupyter Notebook

Jupyter Notebook is an open-source web application that allows users to create and share
documents containing live code, equations, visualizations, and narrative text. It supports various
programming languages, including Python, R, and Julia, making it a versatile tool for data analysis,
scientific computing, and machine learning[19].

Key Features:

• Interactive Coding: Users can run code snippets in real-time, making it easy to test and
debug.
• Rich Media Support: Jupyter Notebooks support various output formats, including graphs,
charts, and interactive visualizations, enhancing the presentation of data analysis.
• Markdown Support: Users can write formatted text using Markdown, allowing for
comprehensive documentation alongside code.
• Integration with Libraries: It seamlessly integrates with popular libraries such as NumPy,
pandas, and Matplotlib, facilitating data exploration and visualization.

Use Cases: Jupyter Notebooks are widely used in data science for exploratory data analysis,
machine learning model development, and academic research presentations.

2. Anaconda

Anaconda is a distribution of Python and R specifically

designed for scientific computing, data science, and machine
learning. It simplifies package management and deployment,
making it easier for users to install, manage, and share
libraries and environments[20].

Key Features:

• Package Management: Anaconda includes the conda package manager, which simplifies
the installation and management of libraries, dependencies, and environments.
• Environment Management: Users can create isolated environments for different projects,
ensuring that dependencies do not conflict.
• Anaconda Navigator: A graphical user interface that allows users to manage packages,
environments, and launch applications like Jupyter Notebook without using the command
line.
• Pre-installed Libraries: Anaconda comes with many popular libraries pre-installed,
including pandas, NumPy, and scikit-learn, reducing setup time for data science projects.
Use Cases: Anaconda is commonly used by data scientists, researchers, and developers to
streamline their workflow and manage complex projects efficiently.

3. HTML (HyperText Markup Language)

HTML is the standard markup language used for creating web pages. It defines the structure and
content of a webpage using a series of elements, represented by tags. HTML is the backbone of
web development and is essential for anyone looking to create websites[21].

Key Features:

• Structure and Semantics: HTML allows developers to structure content using elements
like headings, paragraphs, lists, links, images, and forms.
• Hyperlinking: HTML enables the creation of hyperlinks, allowing users to navigate
between different pages and resources on the web.
• Compatibility: HTML is supported by all web browsers, ensuring that web pages render
correctly across different platforms.

Use Cases: HTML is used in every website to create and structure content, making it a fundamental
skill for web developers and designers.

4. CSS (Cascading Style Sheets)

CSS is a stylesheet language used to control the presentation and layout of HTML documents. It
allows developers to apply styles to web elements, including colors, fonts, spacing, and
positioning[22].

Key Features:

• Separation of Content and Design: CSS enables the separation of HTML content from
its visual presentation, making it easier to maintain and update.
• Responsive Design: CSS supports media queries, allowing developers to create responsive
designs that adapt to different screen sizes and devices.
• Advanced Styling: CSS provides advanced features like animations, transitions, and grid
layouts, enabling developers to create visually appealing web applications.

Use Cases: CSS is used to enhance the visual presentation of websites, making it essential for web
design and user experience.
5. JavaScript

JavaScript is a high-level, dynamic programming language that adds interactivity and functionality
to web pages. It is a core technology of the web, alongside HTML and CSS, and is essential for
modern web development[23].

Key Features:

• Client-Side Scripting: JavaScript runs in the browser, allowing developers to create

interactive web applications without needing server-side processing.
• Dynamic Content: It enables the manipulation of HTML and CSS, allowing for real-time
updates to content and styles based on user interactions.
• Asynchronous Programming: JavaScript supports asynchronous operations, making it
possible to handle tasks like API requests and file uploads without blocking the user
interface.
• Frameworks and Libraries: JavaScript has a rich ecosystem of frameworks (like React,
Angular, and Vue.js) and libraries (like jQuery) that simplify web development and
enhance functionality.

Use Cases: JavaScript is widely used for creating dynamic and interactive web applications,
enhancing user experience, and developing server-side applications with frameworks like Node.js.
 CHAPTER 4
METHODOLOGY
4.1 Data Collection

Collect historical data on house prices. This data should include features such as:
• Size of the house
• Number of bedrooms and bathrooms
• Location (could be in the form of zip code or geographical coordinates)
• Price, etc.
Sources: Public records, real estate websites, or pre-existing datasets from kaggle.

4.2 Data Preprocessing

a. Handling Missing Values

Use SimpleImputer from sklearn.impute to fill in missing values. You can use strategies like filling
with the mean, median, or most frequent value.

b. Removing Outliers

Identify and eliminate outliers using statistical methods like Z-score or IQR (Interquartile
Range).

c. Standardization/Normalization

Standardize features using StandardScaler from sklearn.preprocessing to bring all features to a

similar scale.

from sklearn.linear_model import LinearRegression

from sklearn.preprocessing import StandardScaler
# X being feature matrix
scaler = StandardScaler(with_mean=False)
X_scaled = scaler.fit_transform(X)
lr = LinearRegression()
lr.fit(X_scaled, y)
4.3 Feature Engineering

a. Feature Selection

Select relevant features using methods such as correlation analysis, feature importance scores from
preliminary models, or automated methods like SelectKBest from sklearn.feature_selection.

b. Creating New Features

Generate new features if needed, such as polynomial features or interaction terms using
PolynomialFeatures from sklearn.preprocessing.

4.4 Data Splitting

Split the data into training and testing sets using train_test_split from sklearn.model_selection.

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,
test_size=0.2, random_state=0)

4.5 Applying Linear Regression

from sklearn.preprocessing import OneHotEncoder,
StandardScaler
column_trans = make_column_transformer((OneHotEncoder(),
['beds']), remainder='passthrough')
scaler = StandardScaler()
lr = LinearRegression()

4.6 Pipeline Creation

Create a pipeline to streamline and automate the entire preprocessing and model training process.
from sklearn.pipeline import make_pipeline
pipe = make_pipeline(column_trans,scaler, lr)
pipe.fit(X_train,y_train)
 Figure 3: Pipeline for Linear Regression.

4.7 Model Evaluation

Evaluate the model using metrics like R-squared, Mean Squared Error (MSE), and Root Mean
Squared Error (RMSE).

from sklearn.metrics import r2_score

y_pred_lr = pipe.predict(X_test)
r2_score(y_test,y_pred_lr)

4.8 Model Devlopment

Save and deploy your model for making predictions on new data.

import pickle
pickle.dump(pipe, open('linear.pkl','wb'))
 CHAPTER 5
IMPLEMENTATION & OUTCOMES
5.1 Codes

5.1.1 Python Code

from flask import Flask, render_template, request, jsonify

import pandas as pd
import pickle

app = Flask(__name__)
data = pd.read_csv(r'final_dataset.csv')
pipe = pickle.load(open("linear.pkl", 'rb'))

@app.route('/')
def index():
bedrooms = sorted(data['beds'].unique())
bathrooms = sorted(data['baths'].unique())
sizes = sorted(data['size'].unique())
zip_codes = sorted(data['zip_code'].unique())

return render_template('index.html', bedrooms=bedrooms, bathrooms=bathrooms, sizes=sizes,

zip_codes=zip_codes)

@app.route('/predict', methods=['POST'])
def predict():
bedrooms = request.form.get('beds')
bathrooms = request.form.get('baths')
size = request.form.get('size')
zipcode = request.form.get('zip_code')
 # Create a DataFrame with the input data
input_data = pd.DataFrame([[bedrooms, bathrooms, size, zipcode]],
columns=['beds', 'baths', 'size', 'zip_code'])

print("Input Data:")
print(input_data)

# Handle unknown categories in the input data

for column in input_data.columns:
unknown_categories = set(input_data[column]) - set(data[column].unique())
if unknown_categories:
# Handle unknown categories (e.g., replace with a default value)
input_data[column] = input_data[column].replace(unknown_categories,
data[column].mode()[0])

print("Processed Input Data:")

print(input_data)

# Predict the price

prediction = pipe.predict(input_data)[0]

return str(prediction)
from flask import Flask, render_template, request
import pandas as pd
import pickle

app = Flask(__name__)
data = pd.read_csv('final_dataset.csv')
pipe = pickle.load(open("linear.pkl", 'rb'))
@app.route('/')
def index():
bedrooms = sorted(data['beds'].unique())
bathrooms = sorted(data['baths'].unique())
sizes = sorted(data['size'].unique())
zip_codes = sorted(data['zip_code'].unique())

return render_template('index.html', bedrooms=bedrooms, bathrooms=bathrooms, sizes=sizes,

zip_codes=zip_codes)

@app.route('/predict', methods=['POST'])
def predict():
bedrooms = request.form.get('beds')
bathrooms = request.form.get('baths')
size = request.form.get('size')
zipcode = request.form.get('zip_code')

# Create a DataFrame with the input data

input_data = pd.DataFrame([[bedrooms, bathrooms, size, zipcode]],
columns=['beds', 'baths', 'size', 'zip_code'])

print("Input Data:")
print(input_data)

# Convert 'baths' column to numeric with errors='coerce'

input_data['baths'] = pd.to_numeric(input_data['baths'], errors='coerce')

# Convert input data to numeric types

input_data = input_data.astype({'beds': int, 'baths': float, 'size': float, 'zip_code': int})
 # Handle unknown categories in the input data
for column in input_data.columns:
unknown_categories = set(input_data[column]) - set(data[column].unique())
if unknown_categories:
print(f"Unknown categories in {column}: {unknown_categories}")
# Handle unknown categories (e.g., replace with a default value)
input_data[column] = input_data[column].replace(unknown_categories,
data[column].mode()[0])

print("Processed Input Data:")

print(input_data)

# Predict the price

prediction = pipe.predict(input_data)[0]

return str(prediction)

if __name__ == "__main__":
app.run(debug=True, port=7000)
5.1.2 HTML Code

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>House Price Prediction</title>
<style>
body {
font-family: 'Arial', sans-serif;
margin: 0;
padding: 0;
background-image: url('https://img.freepik.com/free-photo/luxurious-villa-with-modern-
architectural-design_23-
2151694144.jpg?t=st=1727449469~exp=1727453069~hmac=460ec079448d829f563a4f1699122
d845e0bd982ebe58f532365c18c479c22b7&w=1480'); /* Replace with your image URL */
background-size: cover; /* Cover the entire viewport */
background-position: center; /* Center the image */
background-repeat: no-repeat; /* Prevent the image from repeating */
line-height: 1.6; /* Improved line spacing */
color: #333; /* Default text color */
}

header {
background-color: rgba(165, 214, 167, 0.8); /* Light green with transparency */
color: #fff;
padding: 20px;
text-align: center;
border-bottom: 3px solid #388e3c; /* Darker green border */
}
h1 {
font-size: 2.5em; /* Larger font size */
margin: 0;
}

main {
max-width: 800px;
margin: 30px auto;
padding: 20px;
background-color: rgba(255, 255, 255, 0.9); /* White background with transparency */
box-shadow: 0 0 15px rgba(0, 0, 0, 0.2);
border-radius: 8px;
}

footer {
text-align: center;
padding: 10px;
background-color: rgba(165, 214, 167, 0.8); /* Light green with transparency */
color: #fff;
position: relative;
bottom: 0;
width: 100%;
border-top: 3px solid #388e3c; /* Darker green border */
}

form {
margin-top: 20px;
}

label {
 display: block;
margin-bottom: 8px;
color: #424242; /* Dark gray for labels */
font-weight: bold; /* Bold labels */
}

select {
width: 100%;
padding: 10px;
margin-bottom: 15px;
border: 2px solid #a5d6a7; /* Light green border */
border-radius: 5px; /* Rounded corners for select */
background-color: #e8f5e9; /* Light green background for select */
font-size: 1em; /* Slightly larger font for dropdowns */
}

button {
background-color: #81c784; /* Green button */
color: #fff;
padding: 12px;
border: none;
border-radius: 5px; /* Rounded corners for button */
cursor: pointer;
transition: background-color 0.3s;
width: 100%;
font-size: 1.1em; /* Slightly larger button text */
font-weight: bold; /* Bold button text */
}

button:hover {
 background-color: #388e3c; /* Darker green on hover */
}

#predictedPrice {
margin-top: 20px;
font-weight: bold;
color: #e53935; /* Red color for predicted price */
text-align: center;
font-size: 1.5em; /* Larger font size for price */
}

/* Additional styling for better visual appeal */

p{
font-size: 1.2em; /* Larger paragraph text */
color: #555; /* Darker text for paragraph */
text-align: center;
margin-bottom: 20px;
}
</style>
</head>
<body>
<header>
<h1>House Price Prediction</h1>
</header>
<main>
<p>Use the form below to predict the price of your house!</p>

<form id="predictionForm">
<label for="beds">Bedrooms:</label>
<select id="beds" name="beds">
 <option value="" disabled selected>Select number of bedrooms</option>
{% for bedroom in bedrooms %}
<option value="{{ bedroom }}">{{ bedroom }}</option>
{% endfor %}
</select>

<label for="baths">Bathrooms:</label>
<select id="baths" name="baths">
<option value="" disabled selected>Select number of bathrooms</option>
{% for bathroom in bathrooms %}
<option value="{{ bathroom }}">{{ bathroom }}</option>
{% endfor %}
</select>

<label for="size">Size:</label>
<select id="size" name="size">
<option value="" disabled selected>Select size of the house</option>
{% for house_size in sizes %}
<option value="{{ house_size }}">{{ house_size }} sqft</option>
{% endfor %}
</select>

<label for="zip_code">Zip Code:</label>

<select id="zip_code" name="zip_code">
<option value="" disabled selected>Select zip code</option>
{% for zip_code in zip_codes %}
<option value="{{ zip_code }}">{{ zip_code }}</option>
{% endfor %}
</select>
 <button type="button" onclick="sendData()">Predict Price</button>
<div id="predictedPrice"></div>
</form>
</main>
<footer>
<p>&copy; 2024 House Price Prediction. All rights reserved.</p>
</footer>
<script>
function sendData() {
const form = document.getElementById('predictionForm');
const formData = new FormData(form);

fetch('/predict', {
method: 'POST',
body: formData
})
.then(response => response.text())
.then(price => {
document.getElementById("predictedPrice").innerHTML = "Price: $ " + price;
});
}
</script>
</body>
</html>
Table 1: Dataset Used.
5.2 Web Interface

Image 5.1: Link for Web.

Image 5.2: Web Interface.

5.3 Outcomes
5.3.1 Example 1

Image 5.3: First Input.

Image 5.4: First Output.

5.3.1 Example 2

Image 5.5: Second Input.

Image 5.6: Second Output.

 CHAPTER 6
CONCLUSION
The development of a house price prediction model represents a significant advancement in
leveraging data analytics and machine learning within the real estate sector. By systematically
gathering and analyzing relevant data, we have created a model that provides valuable insights into
the factors influencing property values.

The model not only aids in predicting house prices with commendable accuracy but also enhances
understanding of the housing market dynamics. Its ability to identify key features—such as
location, size, and amenities—demonstrates the practical application of statistical techniques and
machine learning.

Moreover, this project has established a solid framework for ongoing model improvement and
adaptability to changing market conditions. By incorporating new data and exploring advanced
modeling techniques, we can continually refine predictions to better serve stakeholders, including
buyers, sellers, and real estate professionals.

Overall, the house price prediction model serves as a powerful tool for informed decision-making,
empowering users with data-driven insights that can lead to smarter investments and greater
market understanding. As technology and methodologies evolve, the potential for enhanced
predictive capabilities will only increase, further benefiting the real estate industry.
References

[1] Cady, Field. Data Science for Business: What You Need to Know About Data Mining and Data-Analytic Thinking.
O'Reilly Media, 2015.

[2] Provost, Foster, and Tom Fawcett. Data Science for Business: What You Need to Know About Data Mining and
Data-Analytic Thinking. O'Reilly Media, 2013.

[3] Hand, David J., et al. Data Mining: Concepts and Techniques. Morgan Kaufmann, 2001.

[4] Bishop, Christopher M. Pattern Recognition and Machine Learning. Springer, 2006.

[5] Mayer-Schönberger, Viktor, and Kenneth Cukier. Big Data: A Revolution That Will Transform How We Live,
Work, and Think. Eamon Dolan Books, 2013.

[6] Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016.

[7] Kroll, Joshua A. et al. "Accountable Algorithms." University of California, Berkeley, School of Law, 2017.

[8] Alpaydin, Ethem. Introduction to Machine Learning. MIT Press, 2014.

[9] Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning: Data Mining,
Inference, and Prediction. Springer, 2009.

[10] Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 2018.

[11] Bishop, Christopher M. Pattern Recognition and Machine Learning. Springer, 2006.

[12] Alpaydin, Ethem. Introduction to Machine Learning. MIT Press, 2014.

[13] Lutz, Mark. Learning Python. O'Reilly Media, 2013.

[14] Grinberg, Miguel. Flask Web Development: Developing Web Applications with Python. O'Reilly Media, 2018.

[15] Python Software Foundation. "pickle — Python object serialization." Python Documentation.

[16] McKinney, Wes. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython. O'Reilly Media,
2017.

[17] Oliphant, Travis E. A Guide to NumPy. Trelgol Publishing, 2006.

[18] Pedregosa, Fabian, et al. "Scikit-learn: Machine Learning in Python." Journal of Machine Learning Research 12
(2011): 2825-2830.

[19] Kluyver, Thomas, et al. "Jupyter Notebooks – A Publishing Format for Reproducible Research." In Proceedings
of the 20th International Conference on Electronic Publishing (2016).

[20] Anaconda, Inc. "Anaconda Documentation." Anaconda Docs.

[21] W3C. "HTML Specification." W3C HTML.

[22] W3C. "Cascading Style Sheets (CSS) Specifications." W3C CSS.

[23] Flanagan, David. JavaScript: The Definitive Guide. O'Reilly Media, 2020.