titanic.py

# -*- coding: utf-8 -*-
"""titanic.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1aQVuC2_03D598qcnhCgEaPUTu_WeZN2-
"""

import pandas as pd

import zipfile
import os



unzipp = '/content/titanic.zip'

extract_dir = '/content/titanic'

os.makedirs(extract_dir, exist_ok=True)

with zipfile.ZipFile(unzipp, 'r') as zip_ref:
    zip_ref.extractall(extract_dir)

os.listdir(extract_dir)

import pandas as pd

train = pd.read_csv('/content/titanic/train.csv')
test = pd.read_csv('/content/titanic/test.csv')
test_ids = test["PassengerId"]

train.head(5)

def clean(train):
  train = train.drop(["Ticket","Cabin", "Name", "PassengerId"], axis=1)
  cols = ["SibSp","Age", "Fare","Parch"]

  for col in cols:
    train[col].fillna(train[col].median(), inplace=True)

  # Fixed typo here: "Embarked" instead of "Embared"
  train.Embarked.fillna("U", inplace=True)
  return train

train = clean(train)
test = clean(test)

train.head(3)

from sklearn import preprocessing
le = preprocessing.LabelEncoder()
columns = ["Sex", "Embarked"]

for col in columns:
    train[col] = le.fit_transform(train[col])
    test[col] = le.transform(test[col])
    print(le.classes_)

train.head(5)

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

y = train["Survived"]
X = train.drop("Survived", axis=1)

X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.datasets import load_iris

clf = LogisticRegression(random_state=0, max_iter=1000).fit(X_train, y_train)

predictions = clf.predict(X_val)
from sklearn.metrics import accuracy_score
accuracy_score(y_val, predictions)

submission_preds = clf.predict(test)

df = pd.DataFrame({"PassengerId": test_ids.values,
                   "Survived": submission_preds,
                  })

df.to_csv("submission.csv", index=False)