Google Colab + Kaggle (Titanic) の実装に関するメモ

Reference

Titanic: Machine Learning from Disaster

【Kaggle初心者入門編】タイタニック号で生き残るのは誰？

File Upload 1

from google.colab import drive

drive.mount('/content/gdrive')

print (os.listdir('/content/gdrive/My Drive/...'))

File Upload 2

from google.colab import files
import os

files.upload()

print (os.getcwd())
print (os.listdir('/content'))

Sample Code

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf

#matplotlib inline

train = pd.read_csv('/content/train.csv')
test = pd.read_csv('/content/test.csv')

print ('Train: ')
print (train.describe())
print ()
print ('Test: ')
print (test.describe())

def missing_table(df):
  null_val = df.isnull().sum()
  percent = 100 * df.isnull().sum()/len(df)
  missing_table = pd.concat([null_val, percent], axis=1)
  return  missing_table.rename(columns = {0 : '# of missing', 1 : '%'})

print ('Train')
print (missing_table(train))
print ()
print ('Test')
print (missing_table(test))

train['Age'] = train['Age'].fillna(train['Age'].median())
train['Embarked'] = train['Embarked'].fillna('S')

train['Sex'][train['Sex'] == 'male'] = 0
train['Sex'][train['Sex'] == 'female'] = 1
train['Embarked'][train['Embarked'] == 'S' ] = 0
train['Embarked'][train['Embarked'] == 'C' ] = 1
train['Embarked'][train['Embarked'] == 'Q'] = 2

test['Age'] = test['Age'].fillna(test['Age'].median())
test['Sex'][test['Sex'] == 'male'] = 0
test['Sex'][test['Sex'] == 'female'] = 1
test['Embarked'][test['Embarked'] == 'S'] = 0
test['Embarked'][test['Embarked'] == 'C'] = 1
test['Embarked'][test['Embarked'] == 'Q'] = 2
test.Fare[152] = test.Fare.median()

from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import LeaveOneOut
from sklearn.metrics import accuracy_score

target = train['Survived'].values
features_train = train[['Pclass', 'Sex', 'Age', 'Fare']].values

# Decision Tree
clf = DecisionTreeClassifier()
clf.fit(features_train, target)

prediction_train = clf.predict(features_train)

score = accuracy_score(target, prediction_train)
print (score)

features_test = test[['Pclass', 'Sex', 'Age', 'Fare']].values

prediction_test = clf.predict(features_test)
print (prediction_test.shape)
print (prediction_test)

PassengerId = np.array(test['PassengerId']).astype(int)
solution = pd.DataFrame(prediction_test, PassengerId, columns = ['Survived'])

solution.to_csv('/content/solution.csv', index_label = ['PassengerId'])

files.download('/content/solution.csv')