Project Based Learning — NCERT Solutions

Project III: A survey of the effect of social networking sites on behaviour of teenagers

This project is about conducting a survey to study how social networking sites affect the behaviour of teenagers.

Background

With the internet revolution, teenagers spend a lot of time on social networking sites, and this can influence their behaviour. Excessive use of such sites may sometimes seriously affect mental health. A well-designed survey can help discover useful facts.

Specifications

1. Create a survey questionnaire using any freely available online tool such as Google Forms.
2. Store the responses in a CSV file.
3. Prepare data analysis questions that you want the survey to answer.
4. Import the CSV file into a Pandas DataFrame.
5. Perform statistical computations such as mean, median, etc. for the identified questions.
6. Visualise the findings using appropriate charts.

What the project involves

• Designing questions for teenagers
• Collecting responses digitally
• Storing response data in CSV format
• Analysing the survey mathematically using Pandas
• Presenting the results visually

So, the project is a survey-based data analysis activity in which student responses are collected, analysed statistically, and shown through graphs to understand the effect of social networking sites on teenage behaviour.

Project IV: Utilising an open data source to use a national, state or district level Dataset

This project uses the Open Government Data (OGD) Platform India: www.data.gov.in. The given example dataset is “Special Tabulation on Adolescent and youth population classified by various parameters for India, States and Union Territories, 2011”.

Dataset details

• Contributed by: Ministry of Home Affairs, Government of India
• Released under: NDSAP
• Published on the portal on: 07/09/2015

Statistics of the dataset

• Number of rows: 12168
• Number of columns: 123

Some columns mentioned in the chapter

• State
• Area Name
• Total/Rural/Urban
• Adolescent and youth
• Total Male
• Total Female
• SC-M / SC-F
• ST-M / ST-F
• Literates-M / Literates-F
• Illiterates-M / Illiterates-F
• MainWorker-M / MainWorker-F
• MarginalWorker-M / MarginalWorker-F
• and many more similar columns

Possible analysis questions

The chapter lists several questions that can be answered from this dataset, such as:

1. Total population, total male population, and total female population aged 10 to 24 in India
2. State or Union Territory with the maximum number of illiterates in youth ages
3. Percentage of people working as marginal workers
4. Top 5 states/UTs with maximum marginal workers
5. Compare sex ratio of urban and rural areas using a graph
6. State with highest and lowest percentage of literate Scheduled Tribes and Scheduled Castes
7. Compare female marginal workers and male marginal workers for each state
8. Percentage of Scheduled Tribes living in urban areas and pie chart of literate vs illiterate STs in urban areas
9. State-wise ratio of literates vs illiterates in all age groups
10. State with maximum and minimum number of ST in India
11. State-wise literate females and males and the ratio between them

Steps suggested in the chapter

A project work may be carried out by selecting any 4–5 such questions and solving them step-by-step with explanation and documentation.

For the first sample task, the chapter gives these steps:

• Read the CSV file into a DataFrame
• Check the shape
• View the columns
• Filter the required data
• Create a new DataFrame
• Rename columns for ease of use
• Group data as required
• Plot the data as a bar chart

Example task given in the chapter

The sample question is:
What is the total population, total male population and total female population aged 10 to 24 in India?

The chapter then demonstrates how to:

• read the CSV using Pandas
• filter rows where Area Name = INDIA
• keep the needed columns
• group by Category
• remove unwanted categories like All Ages, Adolescent (10-19), and Youth (15-24)
• plot the final data using a bar chart

So, this project is about using a large public dataset, selecting meaningful questions, analysing the data with Pandas, and presenting the results through graphs and charts.