Data Analysis On Titanic Dataset

In this project, I explored the classic Titanic dataset to understand passenger survival patterns using data visualization and built a machine learning model to predict survival chances. This project demonstrates key data analysis skills, including data cleaning, visualization, feature engineering, and predictive modeling.

Dataset & Tools

• Dataset: Titanic Dataset (Kaggle)

• Tools: Python, Pandas, Matplotlib, Seaborn, Scikit-learn

• Skills Demonstrated:

  • Data Cleaning & Exploration, Visualization & Insight Discovery, 

                    Predictive Modeling (Logistic Regression)

A Small Example for Graphs and Importing Pandas

import pandas as pd

# Time Series ;  Time Stamped data;

# ex. weather data (temp), stock prices; gold price,    -> line plot

We start by importing and cleaning the dataset: 

titanic_df.head()

A Simple plot to look at the data of people who died and survived the crash 

# Seabon.countplot  -- for categorical data

# Plot the Number of passengers Survived and didn't ...

sns.countplot(x='Survived',data=titanic_df)

plt.title('Passenger Information')

plt.xlabel('0=Died 1=Survived')

plt.ylabel('Total number of Passengers')

plt.show() 

A plot to show the passenger survived on gender wise

# Plot the Number of passengers Survived and didn't ...

sns.countplot(x='Survived',hue='Pclass',data=titanic_df)

plt.title('Passenger Information Genderwise Survival')

plt.xlabel('0=Died 1=Survived')

plt.ylabel('Total number of Passengers')

plt.show()

A plot to show each side by side for better understanding on passenger survived by class and gender

# Display two plots on the same figure (canvas)

#  Figure --> Axes (akseez) --> Axis (akis; x,y)

fig = plt.figure(figsize=(10,6))

# define two axes

ax1 = fig.add_subplot(121)

ax2 = fig.add_subplot(122)

   

sns.countplot(x='Survived',hue='Pclass',data=titanic_df,ax=ax1)

sns.countplot(x='Survived',hue='Sex',data=titanic_df,ax=ax2)

# titlle

#plt.title('Passengers info')

ax1.set_title('Passengers Information ClassWise')

ax2.set_title('Passengers Information GenderWise')

ax1.set_xlabel('Classes')

ax2.set_xlabel('Genders')

ax1.set_ylabel('Number of passengers')

plt.show()