Various-Resources-Titanic

Sun 29 June 2025

import pandas as pd
import numpy as np

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression, LinearRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.neural_network import MLPClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df = pd.read_csv(url)
df.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	373450	8.0500	NaN	S

data = df.copy()

# Drop columns that won't help in prediction
data.drop(['PassengerId', 'Name', 'Ticket', 'Cabin'], axis=1, inplace=True)
data.head()

	Survived	Pclass	Sex	Age	SibSp	Fare	Embarked
0	0	3	male	22.0	1	7.2500	S
1	1	1	female	38.0	1	71.2833	C
2	1	3	female	26.0	0	7.9250	S
3	1	1	female	35.0	1	53.1000	S
4	0	3	male	35.0	0	8.0500	S

# Check for missing values
data.isnull().sum()

Survived      0
Pclass        0
Sex           0
Age         177
SibSp         0
Parch         0
Fare          0
Embarked      2
dtype: int64

# Fill missing 'Age' with mean
data['Age'] = data['Age'].fillna(data['Age'].mean())

# Drop rows with missing 'Embarked'
data.dropna(subset=['Embarked'], inplace=True)

# Verify again
data.isnull().sum()

Survived    0
Pclass      0
Sex         0
Age         0
SibSp       0
Parch       0
Fare        0
Embarked    0
dtype: int64

# Convert 'Sex' and 'Embarked' using one-hot encoding
data = pd.get_dummies(data, columns=['Sex', 'Embarked'], drop_first=True)
data.head()

	Survived	Pclass	Age	SibSp	Fare	Sex_male	Embarked_Q	Embarked_S
0	0	3	22.0	1	7.2500	True	False	True
1	1	1	38.0	1	71.2833	False	False	False
2	1	3	26.0	0	7.9250	False	False	True
3	1	1	35.0	1	53.1000	False	False	True
4	0	3	35.0	0	8.0500	True	False	True

X = data.drop('Survived', axis=1)  # Features
y = data['Survived']              # Target

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42)

lr_model = LinearRegression().fit(X_train, y_train)
print("Linear Regression R² Score:", lr_model.score(X_test, y_test))

Linear Regression R² Score: 0.39185146303300156

# 1. KNN
knn = KNeighborsClassifier().fit(X_train, y_train)

# 2. Logistic Regression
log_reg = LogisticRegression(solver='liblinear').fit(X_train, y_train)

# 3. Support Vector Machine
svm = SVC(kernel='linear').fit(X_train, y_train)

# 4. Naive Bayes
nb = GaussianNB().fit(X_train, y_train)

# 5. Neural Network
mlp = MLPClassifier(max_iter=500).fit(X_train, y_train)

# 6. Decision Tree
tree = DecisionTreeClassifier().fit(X_train, y_train)

# 7. Random Forest
rf = RandomForestClassifier().fit(X_train, y_train)

models = [knn, log_reg, svm, nb, mlp, tree, rf]

for model in models:
    name = model.__class__.__name__
    y_pred = model.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print("-" * 28)
    print(f"{name}:")
    print("Accuracy: {:.2%}".format(acc))

----------------------------
KNeighborsClassifier:
Accuracy: 68.91%
----------------------------
LogisticRegression:
Accuracy: 79.03%
----------------------------
SVC:
Accuracy: 79.03%
----------------------------
GaussianNB:
Accuracy: 78.28%
----------------------------
MLPClassifier:
Accuracy: 77.15%
----------------------------
DecisionTreeClassifier:
Accuracy: 77.15%
----------------------------
RandomForestClassifier:
Accuracy: 77.53%

Score: 10

Category: basics