Data Analysis of a titanic dataset from Kaggle

Introduction

The Titanic dataset from Kaggle includes information on the passengers of the Titanic, aiming to predict survival based on various features. The dataset headers are as follows: PassengerId, Survived, Pclass, Name, Sex, Age, SibSp, Parch, Ticket, Fare, Cabin, and Embarked. The purpose of this analysis is to derive initial insights that can guide further data analysis and predictive modeling. https://hng.tech/internship and https://hng.tech/hire

Observations

Summary Statistics

• Total Passengers: 891
• Survival Rate:
• Survived: 38.4%
• Did not survive: 61.6%

Class Distribution:

• 1st Class: 24.2%
• 2nd Class: 20.7%
• 3rd Class: 55.1%

Gender Distribution:

• Male: 64.8%
• Female: 35.2%

Initial Insights

1. Survival by Gender:

• Males: 18.9% survived
• Females: 74.2% survived

Survival by Class:

• 1st Class: 62.9% survived
• 2nd Class: 47.3% survived
• 3rd Class: 24.2% survived

Age Distribution:

• Average Age: 29.7 years
• Age Range: 0.42 to 80 years

Fare Distribution:

• Average Fare: $32.20
• Fare Range: $0 to $512.33

Basic Visualization

• Survival by Gender:

Survival rate by Gender

• Survival by Class:

Survival By Class

Conclusion

The initial analysis indicates significant differences in survival rates based on gender and class. Females and first-class passengers had a much higher survival rate compared to males and third-class passengers. Further analysis should focus on:

• Correlation Analysis: Investigating relationships between survival and features like Age, Fare, SibSp, and Parch.
• Predictive Modeling: Using classification algorithms to predict survival outcomes.
• Handling Missing Data: Addressing missing values in Age, Cabin, and Embarked columns for more comprehensive analysis.