Scribd
Upload
3 views2 pages

DataScience Object Retrieval Notes

The document outlines the initial steps in the data science process, focusing on defining the object and retrieving data. It emphasizes the importance of clearly stating the problem to guide the project and provides key steps for defining the core question, type of analysis, and data sources. Additionally, it highlights the qualities of good data and the challenges faced during data retrieval.

Uploaded by

tanushree
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views2 pages

DataScience Object Retrieval Notes

The document outlines the initial steps in the data science process, focusing on defining the object and retrieving data. It emphasizes the importance of clearly stating the problem to guide the project and provides key steps for defining the core question, type of analysis, and data sources. Additionally, it highlights the qualities of good data and the challenges faced during data retrieval.

Uploaded by

tanushree
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Defining the Object & Retrieving Data in the Data

Science Process

Step 1: Defining the Object


Defining the object means clearly stating what problem you want to solve and what the outcome
should be before starting any data analysis. It acts as the guiding direction for the entire project.
Why It’s Important:
- Prevents wasting time on irrelevant data or analysis.
- Ensures everyone shares the same understanding.
- Helps in choosing correct data sources, tools, and models.
- Allows measurable tracking of success.
Key Steps:
1 Understand the context Meet stakeholders, ask 'What problem are we solving?'
2 Define the core question Convert vague problems into precise, answerable questions.
3 Decide the type of analysis Descriptive, Diagnostic, Predictive, or Prescriptive.
4 Identify the target variable Specific measure to predict or improve.
5 State the objective in measurable
Include
termsclear metrics and timelines.
6 Set boundaries and constraints Define limits like time, budget, available data.

Example: Problem: 'We want to help students perform better in math.'


Defined Object: 'Analyze attendance, homework, and test scores to identify key factors affecting
math performance, aiming for a 10% improvement next year.'
Step 2: Retrieving Data
Retrieving data is the process of collecting and accessing the raw information needed to answer
your defined question. It is often the most time-consuming step in data science.
Data Sources:
Internal Sources Company databases, CRM, transaction logs, sensor readings
External Sources Public datasets, APIs, purchased data, web scraping
Manual Collection Surveys, interviews, observations

Qualities of Good Data:


- Relevance: Data must relate directly to your objective.
- Accuracy: Correct and precise information.
- Completeness: Few or no missing values.
- Timeliness: Up-to-date.
- Ethical Compliance: Collected legally, respecting privacy.
Challenges:
- Missing or incomplete entries.
- Data stored in multiple formats or locations.
- Access restrictions or licensing issues.
- Noisy or unstructured data.
Example: Objective: 'Predict students at risk of failing math.'
Data Retrieval Plan: Use SQL to extract last 3 years' grades, attendance, and homework logs from
the school database, checking for missing IDs and standardizing formats.

You might also like