Created
September 26, 2022 06:35
-
-
Save NathanDai5287/d5f1865bbf3eaf5ee5cbe47b4df6a3a1 to your computer and use it in GitHub Desktop.
Titanic Survival Classification
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
from sklearn.preprocessing import LabelEncoder | |
from sklearn.model_selection import train_test_split | |
from sklearn.linear_model import LogisticRegression | |
# combine train and test data because usually the data will not be split | |
# df = pd.read_csv('data/train.csv').append(pd.read_csv('data/test.csv')).to_csv('data/titanic.csv', index=False) | |
# read data | |
df = pd.read_csv('data/titanic.csv') | |
# get summary of data | |
print(df.info()) | |
# show first 5 rows | |
print(df.head()) | |
le = LabelEncoder() # convert categorical string variables to integers | |
df['Sex'] = le.fit_transform(df['Sex']) # "female" and "male" | |
df['Ticket'] = le.fit_transform(df['Ticket']) # ticket type | |
df['Cabin'] = le.fit_transform(df['Cabin']) # cabin types | |
df['Embarked'] = le.fit_transform(df['Embarked']) # port of embarkation | |
# you can create new variables from existing ones | |
df['FamilySize'] = df['SibSp'] + df['Parch'] + 1 # number of family members | |
# fill missing values with median | |
df['Age'].fillna(df['Age'].median(), inplace=True) | |
df['Fare'].fillna(df['Fare'].median(), inplace=True) | |
# drop datapoint if "survived" is missing | |
df.dropna(subset=['Survived'], inplace=True) | |
# drop passenger name because it does not affect survival | |
df.drop('Name', axis=1, inplace=True) | |
# set independent and depend variables | |
independents = df[[variable for variable in df.columns if variable != 'Survived']] | |
dependent = df['Survived'].values | |
# split training and testing data with train_test_split (80% training, 20% testing) | |
x_train, x_test, y_train, y_test = train_test_split(independents, dependent, test_size=0.2, random_state=42) | |
# create logistic regression model | |
model = LogisticRegression() | |
# fit model and predict | |
model.fit(x_train, y_train) | |
y_pred = model.predict(x_test) | |
# get accuracy of model | |
print('Accuracy of logistic regression classifier on test set: {:.2f}'.format(model.score(x_test, y_test))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment