Dataset : Titanic with SVM / Research

titanic.py

#Author : Remon Hasan , University of Asia Pacific
# Machine Learning algorithm practice for research
#implemantation for google colab
#import library
import numpy as np 
import pandas as pd 

#read file 
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
train.head()

#print data
train.shape
test.shape

#missing train data
train.isnull().sum()

#missing test data
test.isnull().sum()

#Graphical libaray for visualization
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
sns.set()

#barchart function
def bar_chart(feature):
    survived = train[train['Survived']==1][feature].value_counts()
    dead = train[train['Survived']==0][feature].value_counts()
    df = pd.DataFrame([survived,dead])
    df.index = ['Survived','Dead']
    df.plot(kind='bar',stacked=True, figsize=(10,5))
#show gender
bar_chart('Sex')

#summing train and test dataset
train_test_data = [train,test]

for dataset in train_test_data:
    dataset['Title'] = dataset['Name'].str.extract('([A-Za-z]+)\.',expand=False)
    
#find number of train and test dataset title
train['Title'].value_counts()

#others titles are defined by 3
title_mapping = {"Mr": 0, "Miss": 1, "Mrs": 2, "Master": 3, "Dr": 3, "Rev": 3, "Col": 3, "Major": 3, "Mlle": 3, 
                 "Countess": 3, "Ms": 3, "Lady": 3, "Jonkheer": 3, "Don": 3, "Mme": 3, "Capt": 3, "Sir": 3, }
for dataset in train_test_data:
    dataset['Title'] = dataset['Title'].map(title_mapping)
#print train and test data
train.head()
test.head()

# delete unnecessary feature from dataset
train.drop('Name', axis=1, inplace=True)
test.drop('Name', axis=1, inplace=True)
# now print
train.head()
test.head()

#maping sex
sex_mapping = {"male": 0, "female": 1}
for dataset in train_test_data:
    dataset['Sex'] = dataset['Sex'].map(sex_mapping)
#print barchart
bar_chart('Sex')

# fill missing age with median age for each title (Mr, Mrs, Miss, Others)
train["Age"].fillna(train.groupby("Title")["Age"].transform("median"), inplace=True)
test["Age"].fillna(test.groupby("Title")["Age"].transform("median"), inplace=True)
train.groupby("Title")["Age"].transform("median")
# now print
train.head()

# showing in graph
facet = sns.FacetGrid(train, hue="Survived",aspect=4)
facet.map(sns.kdeplot,'Age',shade= True)
facet.set(xlim=(0, train['Age'].max()))
facet.add_legend()
# show 
plt.show()

#differentionate age

for dataset in train_test_data:
    dataset.loc[ dataset['Age'] <= 16, 'Age'] = 0,
    dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 26), 'Age'] = 1,
    dataset.loc[(dataset['Age'] > 26) & (dataset['Age'] <= 36), 'Age'] = 2,
    dataset.loc[(dataset['Age'] > 36) & (dataset['Age'] <= 62), 'Age'] = 3,
    dataset.loc[ dataset['Age'] > 62, 'Age'] = 4
# now print
train.head()

#filling missing values
Pclass1 = train[train['Pclass']==1]['Embarked'].value_counts()
Pclass2 = train[train['Pclass']==2]['Embarked'].value_counts()
Pclass3 = train[train['Pclass']==3]['Embarked'].value_counts()
df = pd.DataFrame([Pclass1, Pclass2, Pclass3])
df.index = ['1st class','2nd class', '3rd class']
df.plot(kind='bar',stacked=True, figsize=(10,5))

for dataset in train_test_data:
    dataset['Embarked'] = dataset['Embarked'].fillna('S')
train.head()

#each city defined by each number
embarked_mapping = {"S": 0, "C": 1, "Q": 2}
for dataset in train_test_data:
    dataset['Embarked'] = dataset['Embarked'].map(embarked_mapping)

# fill missing Fare with median fare for each Pclass
train["Fare"].fillna(train.groupby("Pclass")["Fare"].transform("median"), inplace=True)
test["Fare"].fillna(test.groupby("Pclass")["Fare"].transform("median"), inplace=True)
train.head(5)

#dividing tickets price into different begs
for dataset in train_test_data:
    dataset.loc[ dataset['Fare'] <= 17, 'Fare'] = 0,
    dataset.loc[(dataset['Fare'] > 17) & (dataset['Fare'] <= 30), 'Fare'] = 1,
    dataset.loc[(dataset['Fare'] > 30) & (dataset['Fare'] <= 100), 'Fare'] = 2,
    dataset.loc[ dataset['Fare'] > 100, 'Fare'] = 3
train.head()
train.Cabin.value_counts()

#define which cabin is it ?
for dataset in train_test_data:
    dataset['Cabin'] = dataset['Cabin'].str[:1]
    
Pclass1 = train[train['Pclass']==1]['Cabin'].value_counts()
Pclass2 = train[train['Pclass']==2]['Cabin'].value_counts()
Pclass3 = train[train['Pclass']==3]['Cabin'].value_counts()
df = pd.DataFrame([Pclass1, Pclass2, Pclass3])
df.index = ['1st class','2nd class', '3rd class']
df.plot(kind='bar',stacked=True, figsize=(10,5))

# cabin mapping
cabin_mapping = {"A": 0, "B": 0.4, "C": 0.8, "D": 1.2, "E": 1.6, "F": 2, "G": 2.4, "T": 2.8}
for dataset in train_test_data:
    dataset['Cabin'] = dataset['Cabin'].map(cabin_mapping)

# fill missing Fare with median fare for each Pclass
train["Cabin"].fillna(train.groupby("Pclass")["Cabin"].transform("median"), inplace=True)
test["Cabin"].fillna(test.groupby("Pclass")["Cabin"].transform("median"), inplace=True)
train["FamilySize"] = train["SibSp"] + train["Parch"] + 1
test["FamilySize"] = test["SibSp"] + test["Parch"] + 1
facet = sns.FacetGrid(train, hue="Survived",aspect=4)
facet.map(sns.kdeplot,'FamilySize',shade= True)
facet.set(xlim=(0, train['FamilySize'].max()))
facet.add_legend()
plt.xlim(0)

#family mapping
family_mapping = {1: 0, 2: 0.4, 3: 0.8, 4: 1.2, 5: 1.6, 6: 2, 7: 2.4, 8: 2.8, 9: 3.2, 10: 3.6, 11: 4}
for dataset in train_test_data:
    dataset['FamilySize'] = dataset['FamilySize'].map(family_mapping)
train.head()

#droping features
features_drop = ['Ticket', 'SibSp', 'Parch']
train = train.drop(features_drop, axis=1)
test = test.drop(features_drop, axis=1)
train = train.drop(['PassengerId'], axis=1)
train_data = train.drop('Survived', axis=1)
target = train['Survived']
#now print
train_data.shape, target.shape

#import libraries
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.svm import SVC
k_fold = KFold(n_splits=10, shuffle=True, random_state=0)
train_data.head(50)
test.head()

#using Decision Tree
clf = DecisionTreeClassifier()
scoring = 'accuracy'
score = cross_val_score(clf, train_data, target, cv=k_fold, n_jobs=1, scoring=scoring)
print(score)

# decision tree Score
round(np.mean(score)*100, 2)

#Testing by SVM
clf = SVC(gamma="auto")
clf.fit(train_data, target)
test_data = test.drop("PassengerId", axis=1).copy()
prediction = clf.predict(test_data)

submission = pd.DataFrame({
        "PassengerId": test["PassengerId"],
        "Survived": prediction
    })
# servived result will be saved as submission.csv
submission.to_csv('submission.csv', index=False)
submission = pd.read_csv('submission.csv')
submission.head()