layout	default
title	Titanic

Titanic Overview

This project aims to predict the survival of passengers on the Titanic based on various features such as age, sex, class, and fare. The project uses machine learning algorithms to train models on the Titanic dataset and evaluate their performance.

Contents

• gender_submission.csv: A sample submission file in the correct format.
• README.md: This file, providing an overview of the project.
• test.csv: The test dataset used for making predictions.
• Titanic_cross_validation.ipynb: Jupyter notebook for cross-validation and model evaluation.
• Titanic_model.ipynb: Jupyter notebook for building and training the predictive model.
• train.csv: The training dataset used to build the model.

Models

The project uses several machine learning algorithms, including:

• Decision Tree Classifier
• Linear Support Vector Machine (SVM)
• Gradient Boosting Classifier
• K-Nearest Neighbors (KNN)
• Naive Bayes
• Logistic Regression

Performance Metrics

The project evaluates the performance of each model using accuracy, precision, recall, and F1-score.

Requirements

• Python 3.x
• Jupyter Notebook
• scikit-learn
• pandas
• numpy
• matplotlib
• seaborn

Implementation

EDA, Feature engineering and Model Building.

import numpy as np 
import pandas as pd 
import seaborn as sns 
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')

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

train['train_test'] = 1
test['train_test'] = 0
test['Survived'] = np.NaN
df = pd.concat([train,test])

Analysis

df.describe()

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare	train_test
count	1309.000000	891.000000	1309.000000	1046.000000	1309.000000	1309.000000	1308.000000	1309.000000
mean	655.000000	0.383838	2.294882	29.881138	0.498854	0.385027	33.295479	0.680672
std	378.020061	0.486592	0.837836	14.413493	1.041658	0.865560	51.758668	0.466394
min	1.000000	0.000000	1.000000	0.170000	0.000000	0.000000	0.000000	0.000000
25%	328.000000	0.000000	2.000000	21.000000	0.000000	0.000000	7.895800	0.000000
50%	655.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200	1.000000
75%	982.000000	1.000000	3.000000	39.000000	1.000000	0.000000	31.275000	1.000000
max	1309.000000	1.000000	3.000000	80.000000	8.000000	9.000000	512.329200	1.000000

df.dtypes

PassengerId      int64
Survived       float64
Pclass           int64
Name            object
Sex             object
Age            float64
SibSp            int64
Parch            int64
Ticket          object
Fare           float64
Cabin           object
Embarked        object
train_test       int64
dtype: object

numeric = train.select_dtypes(exclude='object')
numeric.columns

Index(['PassengerId', 'Survived', 'Pclass', 'Age', 'SibSp', 'Parch', 'Fare',
       'train_test'],
      dtype='object')

#correlation with prediction/target var

correlation = abs(numeric.corr()*100)
correlation[['Survived']].sort_values(['Survived'], ascending=False)

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived
Survived	100.000000
Pclass	33.848104
Fare	25.730652
Parch	8.162941
Age	7.722109
SibSp	3.532250
PassengerId	0.500666
train_test	NaN

plt.figure(figsize=(8,6))
sns.heatmap(correlation, mask=correlation<10, cmap='Blues', vmin=10, linewidths=.5, linecolor='k')

<AxesSubplot:>

fig = plt.figure(figsize=(18,16))

for index, col in enumerate(numeric.columns):
     plt.subplot(4,2,index+1)
     sns.distplot(numeric.loc[:,col].dropna(), kde=False)
     
fig.tight_layout(pad=1.0)

# Outliers 

fig =  plt.figure(figsize=(14,20))
for index , col in enumerate(numeric.columns):
    plt.subplot(4,4, index+1)
    sns.boxplot(y=col, data=numeric.dropna())
fig.tight_layout(pad=1.0)

cat = train.select_dtypes(include=['object']).copy()
cat['Pclass'] = train['Pclass']
cat = cat.drop(['Ticket', 'Cabin', 'Name'], axis=1) #droped knowing it has a lot of possible values
cat.columns

Index(['Sex', 'Embarked', 'Pclass'], dtype='object')

fig = plt.figure(figsize=(10,20))
for index in range(len(cat.columns)):
    plt.subplot(4,2,index+1)
    sns.countplot(x=cat.iloc[:,index],data=cat.dropna())
    plt.xticks(rotation=90)
fig.tight_layout(pad=1.0)

Transformation

df.isnull().sum().nlargest(40)  

Cabin          1014
Survived        418
Age             263
Embarked          2
Fare              1
PassengerId       0
Pclass            0
Name              0
Sex               0
SibSp             0
Parch             0
Ticket            0
train_test        0
dtype: int64

df = df.drop(['Cabin'],axis=1)

#Filling missing Age values based on the median of the name tiltle (Mss. Mr. Mrs. etc)

import re
df['name_titles'] = df['Name'].apply(lambda x: re.findall(',\s(\w*).',x)[0])
df['Age'] = df.groupby('name_titles')['Age'].transform(lambda x: x.fillna(x.median()))

df['Embarked'] = df['Embarked'].fillna('S')
df['Embarked'].unique()

array(['S', 'C', 'Q'], dtype=object)

df['Fare'] = df.groupby('Pclass')['Fare'].transform(lambda x: x.fillna(x.mean()))

df.isnull().sum().nlargest(40) 

Survived       418
PassengerId      0
Pclass           0
Name             0
Sex              0
Age              0
SibSp            0
Parch            0
Ticket           0
Fare             0
Embarked         0
train_test       0
name_titles      0
dtype: int64

df['fam'] = df['SibSp']+ df['Parch']

df = df.drop(['PassengerId', 'Name', 'Ticket', 'name_titles', 'Embarked', 'SibSp', 'Parch'], axis=1)
df

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Pclass	Sex	Age	Fare	train_test	fam
0	0.0	3	male	22.0	7.2500	1	1
1	1.0	1	female	38.0	71.2833	1	1
2	1.0	3	female	26.0	7.9250	1	0
3	1.0	1	female	35.0	53.1000	1	1
4	0.0	3	male	35.0	8.0500	1	0
...	...	...	...	...	...	...	...
413	NaN	3	male	29.0	8.0500	0	0
414	NaN	1	female	39.0	108.9000	0	0
415	NaN	3	male	38.5	7.2500	0	0
416	NaN	3	male	29.0	8.0500	0	0
417	NaN	3	male	4.0	22.3583	0	2

1309 rows × 7 columns

#converting Sex and Embarked into Binary 
df['Sex'] = np.where(df['Sex']== 'female', 1,0)
df = pd.get_dummies(df, columns=['Sex'])
df

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Pclass	Age	Fare	train_test	fam	Sex_0	Sex_1
0	0.0	3	22.0	7.2500	1	1	1	0
1	1.0	1	38.0	71.2833	1	1	0	1
2	1.0	3	26.0	7.9250	1	0	0	1
3	1.0	1	35.0	53.1000	1	1	0	1
4	0.0	3	35.0	8.0500	1	0	1	0
...	...	...	...	...	...	...	...	...
413	NaN	3	29.0	8.0500	0	0	1	0
414	NaN	1	39.0	108.9000	0	0	0	1
415	NaN	3	38.5	7.2500	0	0	1	0
416	NaN	3	29.0	8.0500	0	0	1	0
417	NaN	3	4.0	22.3583	0	2	1	0

1309 rows × 8 columns

dfbin = df.copy()
dfbin['Fare'] = pd.qcut(dfbin['Fare'], 5)
dfbin = pd.get_dummies(dfbin, columns=['Fare', 'Pclass', 'fam'])
dfbin

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Age	train_test	Sex_0	Sex_1	Fare_(-0.001, 7.854]	Fare_(7.854, 10.5]	Fare_(10.5, 21.558]	Fare_(21.558, 41.579]	Fare_(41.579, 512.329]	...	Pclass_3	fam_0	fam_1	fam_2	fam_3	fam_4	fam_5	fam_6	fam_7	fam_10
0	0.0	22.0	1	1	0	1	0	0	0	0	...	1	0	1	0	0	0	0	0	0	0
1	1.0	38.0	1	0	1	0	0	0	0	1	...	0	0	1	0	0	0	0	0	0	0
2	1.0	26.0	1	0	1	0	1	0	0	0	...	1	1	0	0	0	0	0	0	0	0
3	1.0	35.0	1	0	1	0	0	0	0	1	...	0	0	1	0	0	0	0	0	0	0
4	0.0	35.0	1	1	0	0	1	0	0	0	...	1	1	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
413	NaN	29.0	0	1	0	0	1	0	0	0	...	1	1	0	0	0	0	0	0	0	0
414	NaN	39.0	0	0	1	0	0	0	0	1	...	0	1	0	0	0	0	0	0	0	0
415	NaN	38.5	0	1	0	1	0	0	0	0	...	1	1	0	0	0	0	0	0	0	0
416	NaN	29.0	0	1	0	0	1	0	0	0	...	1	1	0	0	0	0	0	0	0	0
417	NaN	4.0	0	1	0	0	0	0	1	0	...	1	0	0	1	0	0	0	0	0	0

1309 rows × 22 columns

# Separating Train and Test 

train_df = df[df['train_test']==1]
test_df = df[df['train_test']==0]
train_df = train_df.drop('train_test', axis=1)
test_df = test_df.drop('train_test', axis=1)

train_dfbin = dfbin[dfbin['train_test']==1]
test_dfbin = dfbin[dfbin['train_test']==0]
train_dfbin = train_dfbin.drop('train_test', axis=1)
test_dfbin = test_dfbin.drop('train_test', axis=1)

Fitting the model

train_dfbin_y = train_dfbin.Survived
train_dfbin_X = train_dfbin.drop(['Survived'], axis=1)

train_df_y = train_df.Survived
train_df_X = train_df.drop(['Survived'], axis=1)

train_df_X

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Pclass	Age	Fare	fam	Sex_0	Sex_1
0	3	22.0	7.2500	1	1	0
1	1	38.0	71.2833	1	0	1
2	3	26.0	7.9250	0	0	1
3	1	35.0	53.1000	1	0	1
4	3	35.0	8.0500	0	1	0
...	...	...	...	...	...	...
886	2	27.0	13.0000	0	1	0
887	1	19.0	30.0000	0	0	1
888	3	22.0	23.4500	3	0	1
889	1	26.0	30.0000	0	1	0
890	3	32.0	7.7500	0	1	0

891 rows × 6 columns

from sklearn.ensemble import GradientBoostingClassifier
from sklearn import model_selection, metrics

model = GradientBoostingClassifier().fit(train_df_X, train_df_y)
accuracy =  round(model.score(train_df_X,train_df_y)*100,2)
cross_val = model_selection.cross_val_predict(GradientBoostingClassifier(n_estimators=150, learning_rate=0.1), train_df_X,train_df_y, cv=10, n_jobs=-1)
acc_cv = round(metrics.accuracy_score(train_df_y,cross_val)*100,2)
feature_ranks = pd.Series((model.feature_importances_)*100, index=train_df_X.columns).sort_values(ascending=False)

print('Acc ',accuracy )
print()
print('Cross val ', acc_cv)
print('Feature rank ')
print(feature_ranks)

Acc  89.67

Cross val  84.62
Feature rank 
Sex_1     24.076661
Sex_0     22.933807
Fare      17.025432
Pclass    14.650911
Age       12.053696
fam        9.259494
dtype: float64

Cross Validation (using different models)

import numpy as np 
import pandas as pd 
import seaborn as sns 
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
import math, time, random, datetime

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

train.isnull().sum()

PassengerId      0
Survived         0
Pclass           0
Name             0
Sex              0
Age            177
SibSp            0
Parch            0
Ticket           0
Fare             0
Cabin          687
Embarked         2
dtype: int64

df_bin =pd.DataFrame() #to store continuous variables in bins  ex(age bins: 0-10, 11-20, 21-31, etc..)
df_con = pd.DataFrame() # to store continuous variables 

train.dtypes

PassengerId      int64
Survived         int64
Pclass           int64
Name            object
Sex             object
Age            float64
SibSp            int64
Parch            int64
Ticket          object
Fare           float64
Cabin           object
Embarked        object
dtype: object

train.describe()

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

fig = plt.figure(figsize=(20,1))
sns.countplot(y='Survived', data=train)
print(train.Survived.value_counts())

0    549
1    342
Name: Survived, dtype: int64

df_bin['Survived']= train['Survived']
df_con['Survived']= train['Survived']

#Name ticket and Cabin have too many value types, hard to put in bins not so useful.
print(train.Name.value_counts().count())
print(train.Ticket.value_counts().count())
print(train.Cabin.value_counts().count())

891
681
147

sns.distplot(train.Pclass) # its Ordinal Data 

df_bin['Pclass']= train['Pclass']
df_con['Pclass']= train['Pclass']

plt.figure(figsize=(20,1))
sns.countplot(y='Sex', data=train)

<AxesSubplot:xlabel='count', ylabel='Sex'>

# Function to plot a count and a distribution(vs Survived) of each variable 

def plot_count_dist (data, bin_df, label_column, target_colum, figsize=(20,5), use_bin_fd=False):
    if use_bin_fd:
        fig= plt.figure(figsize=figsize)
        plt.subplot(1,2,1)
        sns.countplot(y=target_colum, data=bin_df)
        plt.subplot(1,2,2)
        sns.distplot(data.loc[data[label_column]==1][target_colum], kde_kws={'label':'Survived'})
        sns.distplot(data.loc[data[label_column]==0][target_colum], kde_kws={'label':'Did Not Survived'})
    else:
        fig= plt.figure(figsize=figsize)
        plt.subplot(1,2,1)
        sns.countplot(y=target_colum, data=data)
        plt.subplot(1,2,2)
        sns.distplot(data.loc[data[label_column]==1][target_colum], kde_kws={'label':'Survived'})
        sns.distplot(data.loc[data[label_column]==0][target_colum], kde_kws={'label':'Did Not Survived'})

# Adding Sex and changing to binary form using np.where
df_bin['Sex'] = train['Sex']
df_bin['Sex'] = np.where(df_bin['Sex']== 'female', 1,0)
df_con['Sex'] = train['Sex']

# Adding SibSp = num of Siblings/Spouse
df_bin['SibSp']= train['SibSp']
df_con['SibSp']= train['SibSp']

plot_count_dist(train, bin_df=df_bin, label_column='Survived', target_colum='SibSp', figsize=(20,10))

# Adding Parch = num of Parents/Children
df_bin['Parch']= train['Parch']
df_con['Parch']= train['Parch']
plot_count_dist(train, bin_df=df_bin, label_column='Survived', target_colum='Parch', figsize=(20,10))

# Ading Fare, first variable to be cut into bins 
df_con['Fare'] = train['Fare']
df_bin['Fare'] = pd.qcut(train['Fare'], 5)
plot_count_dist(train,df_bin,'Survived', 'Fare', use_bin_fd=True, figsize=(20,15))

# Embarqued
df_bin['Embarked'] = train['Embarked']
df_con['Embarked'] = train['Embarked']

df_bin = df_bin.dropna(subset=['Embarked'])
df_con = df_con.dropna(subset=['Embarked'])

import re
df_con['name_titles'] = train['Name'].apply(lambda x: re.findall(',\s(\w*).',x)[0])
df_con['Age'] = train['Age']
df_con['Age'] = df_con.groupby('name_titles')['Age'].transform(lambda x: x.fillna(x.median()))

Feature Encoding

df_bin.head(20)

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Pclass	Sex	SibSp	Parch	Fare	Embarked
0	0	3	0	1	0	(-0.001, 7.854]	S
1	1	1	1	1	0	(39.688, 512.329]	C
2	1	3	1	0	0	(7.854, 10.5]	S
3	1	1	1	1	0	(39.688, 512.329]	S
4	0	3	0	0	0	(7.854, 10.5]	S
5	0	3	0	0	0	(7.854, 10.5]	Q
6	0	1	0	0	0	(39.688, 512.329]	S
7	0	3	0	3	1	(10.5, 21.679]	S
8	1	3	1	0	2	(10.5, 21.679]	S
9	1	2	1	1	0	(21.679, 39.688]	C
10	1	3	1	1	1	(10.5, 21.679]	S
11	1	1	1	0	0	(21.679, 39.688]	S
12	0	3	0	0	0	(7.854, 10.5]	S
13	0	3	0	1	5	(21.679, 39.688]	S
14	0	3	1	0	0	(-0.001, 7.854]	S
15	1	2	1	0	0	(10.5, 21.679]	S
16	0	3	0	4	1	(21.679, 39.688]	Q
17	1	2	0	0	0	(10.5, 21.679]	S
18	0	3	1	1	0	(10.5, 21.679]	S
19	1	3	1	0	0	(-0.001, 7.854]	C

from sklearn.preprocessing import OneHotEncoder, LabelEncoder, label_binarize

#df_bin.drop('Survived', axis=1, inplace=True)
df_bin_enc = pd.get_dummies(df_bin, columns=['Pclass', 'Sex', 'SibSp', 'Parch', 'Fare', 'Embarked'])
df_bin_enc

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Pclass_1	Pclass_2	Pclass_3	Sex_0	Sex_1	SibSp_0	SibSp_1	SibSp_2	SibSp_3	...	Parch_5	Parch_6	Fare_(-0.001, 7.854]	Fare_(7.854, 10.5]	Fare_(10.5, 21.679]	Fare_(21.679, 39.688]	Fare_(39.688, 512.329]	Embarked_C	Embarked_Q	Embarked_S
0	0	0	0	1	1	0	0	1	0	0	...	0	0	1	0	0	0	0	0	0	1
1	1	1	0	0	0	1	0	1	0	0	...	0	0	0	0	0	0	1	1	0	0
2	1	0	0	1	0	1	1	0	0	0	...	0	0	0	1	0	0	0	0	0	1
3	1	1	0	0	0	1	0	1	0	0	...	0	0	0	0	0	0	1	0	0	1
4	0	0	0	1	1	0	1	0	0	0	...	0	0	0	1	0	0	0	0	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
886	0	0	1	0	1	0	1	0	0	0	...	0	0	0	0	1	0	0	0	0	1
887	1	1	0	0	0	1	1	0	0	0	...	0	0	0	0	0	1	0	0	0	1
888	0	0	0	1	0	1	0	1	0	0	...	0	0	0	0	0	1	0	0	0	1
889	1	1	0	0	1	0	1	0	0	0	...	0	0	0	0	0	1	0	1	0	0
890	0	0	0	1	1	0	1	0	0	0	...	0	0	1	0	0	0	0	0	1	0

889 rows × 28 columns

df_con_enc = pd.get_dummies(df_con, columns=['Sex', 'Embarked'])
df_con_enc

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Survived	Pclass	SibSp	Parch	Fare	name_titles	Age	Sex_female	Sex_male	Embarked_C	Embarked_Q	Embarked_S
0	0	3	1	0	7.2500	Mr	22.0	0	1	0	0	1
1	1	1	1	0	71.2833	Mrs	38.0	1	0	1	0	0
2	1	3	0	0	7.9250	Miss	26.0	1	0	0	0	1
3	1	1	1	0	53.1000	Mrs	35.0	1	0	0	0	1
4	0	3	0	0	8.0500	Mr	35.0	0	1	0	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...
886	0	2	0	0	13.0000	Rev	27.0	0	1	0	0	1
887	1	1	0	0	30.0000	Miss	19.0	1	0	0	0	1
888	0	3	1	2	23.4500	Miss	21.0	1	0	0	0	1
889	1	1	0	0	30.0000	Mr	26.0	0	1	1	0	0
890	0	3	0	0	7.7500	Mr	32.0	0	1	0	1	0

889 rows × 12 columns

Building Models 🙆🏽‍♂️

X_train_bin = df_bin_enc.drop('Survived', axis=1)
y_train_bin = df_bin_enc.Survived
X_train_con = df_con_enc.drop(['Survived','name_titles'], axis=1)
y_train_con = df_con_enc.Survived

from sklearn import model_selection, metrics
from sklearn.svm import LinearSVC
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LinearRegression, LogisticRegression, SGDClassifier
from sklearn.tree import DecisionTreeClassifier

# Function to run different algorithm with cross val 

def fit_algo(algo, X_train, y_train, cv): #cv Cross validate, number of times try 10 
    model = algo.fit(X_train, y_train)
    accuracy =  round(model.score(X_train,y_train)*100,2)
    cross_val = model_selection.cross_val_predict(algo, X_train,y_train, cv=cv, n_jobs=-1)
    acc_cv = round(metrics.accuracy_score(y_train,cross_val)*100,2)
    #feature_ranks = pd.Series((model.feature_importances_)*100, index=X_train.columns).sort_values(ascending=False)
    return accuracy, acc_cv, #feature_ranks

TOP Performing Algorithms

acc_grad_boost, cross_grad_boost, featureranks = fit_algo(GradientBoostingClassifier(n_estimators=300, learning_rate=0.1), X_train_con, y_train_con,10)

print('General Acc is ' , acc_grad_boost)
print()
print('With cross val is ',cross_grad_boost)
print()
print(featureranks)

General Acc is  94.94

With cross val is  84.03

Sex_female    22.476185
Fare          21.774555
Sex_male      17.517075
Age           16.592819
Pclass        12.358341
SibSp          5.821414
Embarked_S     1.495644
Parch          1.172607
Embarked_Q     0.420607
Embarked_C     0.370754
dtype: float64

acc_dTree, cross_dTree = fit_algo( DecisionTreeClassifier(),  X_train_con, y_train_con, 10)

print('General Acc is ' , acc_dTree)
print()
print('With cross val is ',cross_dTree)

General Acc is  97.86

With cross val is  76.15

Worst Performing Algorithms

accuracy_LSVC, Cross_LSVC =fit_algo(LinearSVC(), X_train_bin, y_train_bin, 10)

print('General Acc is ' , accuracy_LSVC)
print()
print('With cross val is ',Cross_LSVC)

General Acc is  80.2

With cross val is  78.85

acc_log, cross_log = fit_algo( LogisticRegression(),  X_train_bin, y_train_bin, 10)

print('General Acc is ' , acc_log)
print()
print('With cross val is ',cross_log)

General Acc is  79.64

With cross val is  78.85

acc_KN, cross_KN = fit_algo(KNeighborsClassifier(),  X_train_bin, y_train_bin, 10)

print('General Acc is ' , acc_KN)
print()
print('With cross val is ',cross_KN)

General Acc is  82.45

With cross val is  78.29

acc_gaus, cross_gaus = fit_algo(GaussianNB(),  X_train_con, y_train_con, 10)

print('General Acc is ' , acc_gaus)
print()
print('With cross val is ',cross_gaus)

General Acc is  79.08

With cross val is  78.52

acc_sgdc, cross_sgdc = fit_algo(SGDClassifier(),  X_train_bin, y_train_bin, 10)

print('General Acc is ' , acc_sgdc)
print()
print('With cross val is ',cross_sgdc)

General Acc is  80.2

With cross val is  77.28

from sklearn.svm import SVC, NuSVC

acc_grad_boost, cross_grad_boost = fit_algo(NuSVC(), X_train_bin, y_train_bin,10)

print('General Acc is ' , acc_grad_boost)
print()
print('With cross val is ',cross_grad_boost)

General Acc is  81.55

With cross val is  80.88