https://github.com/girish119628/data-tagging

Data Tagging, Analysis and Insights Generation using Python [NLP, Tokenization]
https://github.com/girish119628/data-tagging

nlp-keywords-extraction tagging tokenization

Last synced: 23 days ago
JSON representation

Data Tagging, Analysis and Insights Generation using Python [NLP, Tokenization]

• Host: GitHub
• URL: https://github.com/girish119628/data-tagging
• Owner: girish119628
• Created: 2024-12-11T11:41:58.000Z (25 days ago)
• Default Branch: main
• Last Pushed: 2024-12-11T11:46:22.000Z (25 days ago)
• Last Synced: 2024-12-11T12:33:06.647Z (25 days ago)
• Topics: nlp-keywords-extraction, tagging, tokenization
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Data-Tagging

Data Tagging, Analysis and Insights Generation using Python

The tagging of each given field (Root Cause, Symptom_Condition, Symptom_Component, Fix_Condition, and Fix_Component.)

# 1. Column-Wise Analysis:

○ Perform a column-wise analysis of the provided dataset.

○ Describe each column in terms of its data type, unique values, distribution, and

overall significance for stakeholders

# 2. Data Cleaning:

○ Handle missing or invalid values using appropriate methods (e.g., imputation,

deletion).

○ Address inconsistencies in categorical columns (e.g., typos, inconsistent

capitalization).

○ Ensure numerical columns are in the correct format and free from outliers, where

applicable.

# 3. Identifying Critical Columns:

○ Select the top 5 critical columns that might be most insightful for stakeholders

according to your data understanding.

○ Provide reasoning for your selection.

○ Generate visualizations (e.g., bar plots etc) using Python to represent these

insights effectively. (atleast 3)

# 4. Generating tags/features from free text available :

○ Generate meaningful tags from the free text fields to summarize information,

example - failure conditions and components etc etc..

# 5. Summary and Insights (Food for thought and has bonus marks)

○ Write a summary of the tags generated, including potential insights derived from

the dataset.

○ Provide actionable recommendations for stakeholders based on your analysis.

○ Highlight discrepancies in the dataset (e.g., null values, missing primary keys)

and how did you approach.