INDEX
1. Introduction
2. Features of the Project
3. Code(Syntax)
4. Output
5. Bibliography
6. Conclusion
CERTIFICATE
This is to certify that the Project entitled,
PROJECT ON DATA ANALYSIS OF THE LUNG
CANCER is a bonded work done by EKANSH
GIRDHAR of class XII-A AND ANUJ SALIL of class
XII-B, session 2024-25, and has been carried out
under my supervision and guidance.
……………………………..
……………………………
(Signature of Teacher) (Signature of
External Examiner)
…………………………….
(Signature of Principal)
ACKNOWLEDGEMENTS
I would like to express my sincere gratitude
towards my project guide and Informatics
Practices teacher, Ms. Pooja Thakur for
guiding me throughout the making of this
project. Her valuable advice helped me
immensely in the successful completion of
this project. I would also like to thank our
school principal, Ms. Meenu Kanwar, for her
coordination in extending every possible
support.
INTRODUCTION
Lung cancer is one of the most common and
serious types of cancer, causing a large number
of deaths worldwide. Understanding the disease,
its causes, and how it progresses is essential for
improving diagnosis, treatment, and survival
rates. However, the complexity of lung cancer
makes it a challenge for doctors and researchers.
This project uses a detailed dataset of 23,658
lung cancer patients to study the disease. The
data includes basic information like age, gender,
and ethnicity, as well as lifestyle details such as
smoking history and the number of years a
person smoked. It also contains important
medical details like the size and location of the
tumor, the stage of cancer, and the type of
treatment received. Blood test results and other
health indicators, such as hemoglobin, glucose,
and creatinine levels, provide additional insights.
By analyzing this information, the project aims to
find patterns and connections that can help
doctors make better decisions about diagnosis
and treatment. These insights could lead to
better care for patients and contribute to the
ongoing fight against lung cancer.
The dataset used for this project is obtained from
[Link] and is given ahead
I have done the analysis using Python Pandas on
windows machine but the project can be run on
any machine supporting Python and Pandas.
Aside from pandas, matplotlib python module has
also been used for visualization of this dataset.
FEATURES OF THE PROJECT
The whole project is majorly divided into four
major parts of reading, analysis and visualization.
It includes:
[Link] the data of csv file
[Link] the Dataframe Statistics
[Link] Analysis (Detailed)
[Link] Analysis (Comprehensive)
[Link] graphs using the data from csv file
(data visualization)
CODE
import pandas as pd
import numpy as np
import [Link] as plt
df = pd.read_csv("C:\\Users\\anujs\\Downloads\\[Link]",nrows=250)
while(True):
print("Main Menu")
print("1. Fetch data")
print("2. Dataframe Statistics")
print("3. Detailed and comprehensive Data Analysis")
print("4. Data Visualization")
print("5. Exit")
ch=int(input("Enter your choice:"))
if ch==1:
print(df)
elif ch==2:
while (True):
print("Dataframe Statistics Menu")
print("1. Display the Transpose")
print("2. Display all column names")
print("3. Display the indexes")
print("4. Display the shape")
print("5. Display the dimension")
print("6. Display the data types of all columns")
print("7. Display the size")
print("8. Modify Dataset")
print("9. Exit")
ch2=int(input("Enter choice"))
if ch2==1:
print(df.T)
elif ch2==2:
print([Link])
elif ch2==3:
print([Link])
elif ch2==4:
print([Link])
elif ch2==5:
print([Link])
elif ch2==6:
print([Link])
elif ch2==7:
print([Link])
elif ch2==8:
while(True) :
print( "Modify the Dataset")
print( "1. Add a column")
print( "2. Add a row")
print( "3. Remove a Row")
print( "4. Remove a Column")
print( "5. Exit")
choice=int(input( "Enter your choice: "))
if choice==1:
i=input("Enter the column name")
b=input("Enter the values needed to be added")
df[i]=b
print(df[i])
elif choice==2:
i=input("Enter the row name")
b=input("Enter the values needed to be added")
[Link][i]=b
print([Link][i])
elif choice==3:
a=input("Enter the row needed to be deleted")
[Link](a,inplace=True)
print(a," row deleted")
elif choice==4:
a=input("Enter the column needed to be deleted")
[Link](a,axis=1,inplace=True)
print(a," column deleted")
elif choice==5:
break
elif ch2==9:
break
elif ch==3:
while(True):
print('Data Extraction and Analysis:')
print('1. Display all Records')
print('2. Extract patients data')
print('3. Data Analysis')
print('4. Exit')
ch3=int(input("Enter choice"))
if ch3==1:
print('Display Data:')
print(df)
elif ch3==2:
while(True):
print('Extract Data:')
print('1. Top 5 Records')
print('2. Bottom 5 Records')
print('3. Specific number of records from the top')
print('4. Specific number of records from the bottom')
print('5. Sort Based on Category')
print('6. Exit')
e=int(input("Enter choice"))
if e==1:
print([Link](5))
elif e==2:
print([Link](5))
elif e==3:
i_top=int(input("Enter no of records to be extracted from
the top"))
print([Link](i_top))
elif e==4:
i_bottom=int(input("Enter no of records to be extracted
from the bottom"))
print([Link](i_bottom))
elif e==5:
while (True):
print('Sort based on category:')
print('1. Gender')
print('2. Ethnicity')
print('3. Smoking History of patient')
print('4. Smoking History in family')
print('5. Tumour Location')
print('6. Treatment Used')
print('7. Exit')
oi=int(input("Enter choice"))
if oi==1:
gender=int(input('Gender: 1-Male | 2-Female' ))
if gender==1:
print(df[[Link]=="Male"])
elif gender==2:
print(df[[Link]=="Female"])
elif oi==2:
while(True):
print('Ethnicity:')
print('1-Hispanic')
print('2-Caucasian')
print('3-African American')
print('4-Asian')
print('5-Other')
print('6. Exit')
ethnicity=int(input("Enter choice"))
if ethnicity==1:
print(df[[Link]=="Hispanic"])
elif ethnicity==2:
print(df[[Link]=="Caucasian"])
elif ethnicity==3:
print(df[[Link]=="African American"])
elif ethnicity==4:
print(df[[Link]=="Asian"])
elif ethnicity==5:
print(df[[Link]=="Other"])
elif ethnicity==6:
break
elif oi==3:
while(True):
print('Smoking History of patient:')
print('1-Current Smoker')
print('2-Never Smoked')
print('3-Former Smoker')
print('4. Exit')
smoke=int(input("Enter choice"))
if smoke==1:
print(df[df.Smoking_History=="Current
Smoker"])
elif smoke==2:
print(df[df.Smoking_History=="Never Smoked"])
elif smoke==3:
print(df[df.Smoking_History=="Former
Smoker"])
elif smoke==4:
break
elif oi==4:
history=int(input('Smoking History: 1-Yes | 2-No'))
if history==1:
print(df[df.Family_History=="Yes"])
elif history==2:
print(df[df.Family_History=="No"])
elif oi==5:
while(True):
print('Tumour location:')
print('1-Upper Lobe')
print('2-Middle Lobe')
print('3-Lower Lobe')
print('4. Exit')
loc=int(input("Enter choice"))
if loc==1:
print(df[df.Tumor_Location=="Upper Lobe"])
elif loc==2:
print(df[df.Tumor_Location=="Middle Lobe"])
elif loc==3:
print(df[df.Tumor_Location=="Lower Lobe"])
elif loc==4:
break
elif oi==6:
while(True):
print('Treatment Used:')
print('1-Surgery')
print('2-Radiation Therapy')
print('3-Chemotherapy')
print('4-Targeted Therapy')
print('5. Exit')
method=int(input("Enter choice"))
if method==1:
print(df[[Link]=="Surgery"])
elif method==2:
print(df[[Link]=="Radiation Therapy"])
elif method==3:
print(df[[Link]=="Chemotherapy"])
elif method==4:
print(df[[Link]=="Targeted Therapy"])
elif method==5:
break
elif oi==7:
break
elif e==6:
break
if ch3==3:
while(True):
print('Data Analysis:')
print('1. Count of all ethnic groups')
print('2. Average age of patients')
print('3. Oldest patient')
print('4. Youngest patient')
print('5. Maximum no. of smoking packs consumed by a
patient yearly')
print('6. Minimum no. of smoking packs consumed by a
patient yearly')
print('7. No. of patients having a history of smoking in both
personal and family')
print('8. Exit')
data = int(input('Enter the Choice'))
if data==1:
m=[Link]("Ethnicity")
print([Link]())
elif data==2:
print([Link]())
elif data==3:
print([Link]())
elif data==4:
print([Link]())
elif data==5:
print(df.Smoking_Pack_Years.max())
elif data==6:
print(df.Smoking_Pack_Years.min())
elif data==7:
c=0
p=len([Link])
for x in range(p):
if ([Link][x,"Smoking_History"] in ("Current
Smoker","Former Smoker")) and [Link][x,"Family_History"]=="Yes":
c+=1
print(c)
elif data==8:
break
elif ch3==4:
break
elif ch==4:
while(True):
print("Line Plot Sub Menu")
print("1. graph between male or female paitents ")
print("2. pie chart different ethinicity")
print('3. graph b/w Smoking history')
print('4. family history')
print('5. histogram for age category')
print("6. Exit")
ch4=int(input("Enter choice"))
if ch4==1:
gender= df['Gender'].value_counts()
[Link](kind='bar')
[Link]('Gender Distribution')
[Link]('Gender')
[Link]('Number of Patients')
[Link]()
elif ch4==2:
m = [Link]("Ethnicity").size()
[Link]([Link],labels=[Link])
[Link]("Distribution by Ethnicity")
[Link]()
elif ch4==3:
smoking_history= df['Smoking_History'].value_counts()
smoking_history.plot(kind='bar')
[Link]('Distribution of Smoking History')
[Link]('Smoking History')
[Link]('Number of Patients')
[Link](rotation=45)
[Link]()
elif ch4==4:
family_history = df['Family_History'].value_counts()
family_history.plot(kind='bar', color='lightgreen',
edgecolor='black')
[Link]('Distribution of Family History')
[Link]('Family History')
[Link]('Number of Patients')
[Link](rotation=45)
[Link]()
elif ch4==5:
[Link](df['Age'].dropna(), rwidth=0.8)
[Link]('Distribution by Age')
[Link]('Age')
[Link]('Number of Patients')
[Link]()
elif ch==5:
break
OUTPUT
1. Fetch Data
2. Dataframe Statistics
a. Display the Transpose
b. Display all column names
c. Display the indexes
d. Display the shape
e. Display the dimension
f. Display the data types of all columns
g. Display the size
h. Modify Dataset
(i) Add a column
(ii) Add a row
(iii) Remove a row
(iv) Remove a column
3. Detailed and comprehensive Data Analysis
a. Display all records
b. Extract patient data
(i) Top 5 Records
(ii) Bottom 5 Records
(iii) Specific number of records from the top
(iv) Specific number of records from the bottom
(v) Sort Based on Category
a. Gender
b. Ethnicity
c. Smoking History of patient
d. Smoking History in family
e. Tumour Location
f. Treatment Used
4. Comprehensive Data Analysis
(i) Count of all ethnic groups
(ii) Average age of patients
(iii) Oldest patient
(iv) Youngest patient
(v) Maximum no. of smoking packs consumed by a patient yearly
(vi) Minimum no. of smoking packs consumed by a patient yearly
(vii) No. of patients having a history of smoking in both personal and
family
4. Data Visualization
a. Graph between Male or Female paitents
b. Pie chart Different Ethnicity
c. Graph b/w Smoking History
d. Family History
e. Histogram for Age Category
BIBLIOGRAPHY
The following books/websites helped me in
the completion of this project.
• Informatics Practices NCERT
• Informatics Practices by Preeti Arora
• [Link]
• [Link]
• [Link]
CONCLUSION
Through this project, I have garnered an
extensive knowledge of the Pandas, and
PyPlot modules and their workings. I have
also understood the importance of data
analysis through its practical application.