Navigating History and Data Science: The Titanic Kaggle Challenge

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

# Load the Titanic training dataset from a CSV file and display the first 5 rows.

train_data = pd.read_csv("/kaggle/input/titanic/train.csv")
train_data.head()

# Load the Titanic test dataset from a CSV file and display the first 5 rows.

test_data = pd.read_csv("/kaggle/input/titanic/test.csv")
test_data.head()

# Calculate and print the survival rate of women in the Titanic training dataset.

women = train_data.loc[train_data.Sex == 'female']["Survived"]
rate_women = sum(women)/len(women)

print("% of women who survived:", rate_women)

# Calculate and print the survival rate of men in the Titanic training dataset.

men = train_data.loc[train_data.Sex == 'male']["Survived"]
rate_men = sum(men)/len(men)

print("% of men who survived:", rate_men)

# Train a Random Forest classifier and make predictions on the Titanic test dataset.

# Import the Random Forest Classifier from scikit-learn.

from sklearn.ensemble import RandomForestClassifier

# Define the target variable (survival) and select features for the model.

y = train_data["Survived"]

features = ["Pclass", "Sex", "SibSp", "Parch"]
X = pd.get_dummies(train_data[features]) # Convert categorical data to numerical for training data
X_test = pd.get_dummies(test_data[features]) # Convert categorical data to numerical for test data

# Initialize and train the Random Forest model.

model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X, y) # Fit the model to the training data

# Make predictions using the test data.
    
predictions = model.predict(X_test)

# Create a DataFrame with the test data PassengerIds and the survival predictions, then save it to a CSV file.

output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})
output.to_csv('submission.csv', index=False) # Save the predictions to a submission file

# Print a success message.

print("Your submission was successfully saved!")