In [ ]:
# data analysis and wrangling
import pandas as pd
import numpy as np
import random as rnd
# visualization
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
In [ ]:
train_df = pd.read_csv('./train.csv')
test_df = pd.read_csv('./test.csv')
combine = [train_df, test_df]
In [ ]:
train_df
In [ ]:
print(train_df.__class__)
print("### shape")
print(train_df.shape)
print("### columns")
print(train_df.columns)
In [ ]:
train_df.describe()
In [ ]:
train_df.describe(include=['O'])
In [ ]:
train_df[['Pclass', 'Survived']].groupby(['Pclass'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
train_df[["Sex", "Survived"]].groupby(['Sex'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
train_df[["SibSp", "Survived"]].groupby(['SibSp'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
train_df[["Parch", "Survived"]].groupby(['Parch'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)
In [ ]:
# grid = sns.FacetGrid(train_df, col='Pclass', hue='Survived')
grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)
grid.add_legend();
In [ ]:
grid = sns.FacetGrid(train_df, row='Embarked', size=2.2, aspect=1.6)
grid.map(sns.pointplot, 'Pclass', 'Survived', 'Sex', palette='deep')
grid.add_legend()
In [ ]:
grid = sns.FacetGrid(train_df, row='Embarked', col='Survived', size=2.2, aspect=1.6)
grid.map(sns.barplot, 'Sex', 'Fare', alpha=.5, ci=None)
grid.add_legend()
In [ ]:
print("Before", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)
train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)
combine = [train_df, test_df]
"After", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape
In [ ]:
for dataset in combine:
dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)
pd.crosstab(train_df['Title'], train_df['Survived'])
In [ ]:
for dataset in combine:
dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col', 'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')
dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
train_df[['Title', 'Survived']].groupby(['Title'], as_index=False).mean()
In [ ]:
title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
for dataset in combine:
dataset['Title'] = dataset['Title'].map(title_mapping)
dataset['Title'] = dataset['Title'].fillna(0)
train_df['Title']
In [ ]:
train_df = train_df.drop(['Name', 'PassengerId'], axis=1)
test_df = test_df.drop(['Name'], axis=1)
combine = [train_df, test_df]
train_df.shape, test_df.shape
In [ ]:
for dataset in combine:
dataset['Sex'] = dataset['Sex'].map( {'female': 1, 'male': 0} ).astype(int)
train_df.head()
In [ ]:
grid = sns.FacetGrid(train_df, row='Pclass', col='Sex', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)
grid.add_legend()
In [ ]:
guess_ages = np.zeros((2,3))
guess_ages
for dataset in combine:
for i in range(0, 2): # Sex
for j in range(0, 3): # Pclass
guess_df = dataset[(dataset['Sex'] == i) & (dataset['Pclass'] == j+1)]['Age'].dropna()
age_guess = guess_df.median()
# Convert random age float to nearest .5 age
guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5
for i in range(0, 2):
for j in range(0, 3):
dataset.loc[ dataset.Age.isnull() & (dataset.Sex == i) & (dataset.Pclass == j + 1), 'Age'] = guess_ages[i,j]
dataset['Age'] = dataset['Age'].astype(int)
train_df.head()
In [ ]:
train_df['AgeBand'] = pd.cut(train_df['Age'], 5)
train_df[['AgeBand', 'Survived']].groupby(['AgeBand'], as_index=False).mean().sort_values(by='AgeBand', ascending=True)
In [ ]:
for dataset in combine:
dataset.loc[ dataset['Age'] <= 16, 'Age'] = 0
dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
dataset.loc[ dataset['Age'] > 64, 'Age']
train_df.head()
In [ ]:
train_df = train_df.drop(['AgeBand'], axis=1)
combine = [train_df, test_df]
train_df.head()
In [ ]:
for dataset in combine:
dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1
train_df[['FamilySize', 'Survived']].groupby(['FamilySize'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
for dataset in combine:
dataset['IsAlone'] = 0
dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
train_df[['IsAlone', 'Survived']].groupby(['IsAlone'], as_index=False).mean()
In [ ]:
train_df = train_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
test_df = test_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
combine = [train_df, test_df]
train_df.head()
In [ ]:
for dataset in combine:
dataset['Age*Class'] = dataset.Age * dataset.Pclass
train_df.loc[:, ['Age*Class', 'Age', 'Pclass']].head(10)
In [ ]:
freq_port = train_df.Embarked.dropna().mode()[0]
freq_port
In [ ]:
for dataset in combine:
dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)
train_df[['Embarked', 'Survived']].groupby(['Embarked'], as_index=False).mean().sort_values(by='Survived', ascending=False)
In [ ]:
for dataset in combine:
dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)
train_df.head()
In [ ]:
test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)
test_df.head()
In [ ]:
train_df['FareBand'] = pd.qcut(train_df['Fare'], 4)
train_df[['FareBand', 'Survived']].groupby(['FareBand'], as_index=False).mean().sort_values(by='FareBand', ascending=True)
In [ ]:
for dataset in combine:
dataset.loc[ dataset['Fare'] <= 7.91, 'Fare'] = 0
dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare'] = 2
dataset.loc[ dataset['Fare'] > 31, 'Fare'] = 3
dataset['Fare'] = dataset['Fare'].astype(int)
train_df = train_df.drop(['FareBand'], axis=1)
combine = [train_df, test_df]
train_df.head(10)
In [ ]:
test_df.head(10)
In [ ]:
X_train = train_df.drop("Survived", axis=1)
Y_train = train_df["Survived"]
X_test = test_df.drop("PassengerId", axis=1).copy()
X_train.shape, Y_train.shape, X_test.shape
X_train
In [ ]:
# Logistic Regression
logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train, Y_train) * 100, 2)
acc_log
In [ ]:
coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = ['Feature']
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])
coeff_df.sort_values(by='Correlation', ascending=False)
In [ ]:
# Random Forest
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train, Y_train)
Y_pred = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)
acc_random_forest
In [ ]:
submission = pd.DataFrame({
"PassengerId": test_df["PassengerId"],
"Survived": Y_pred
})
print(submission)
submission.to_csv('./submission.csv', index=False)