
import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

%matplotlib inline

import seaborn as sns


titanic_data = pd.read_csv('titanic_train.csv')


sns.countplot(x='Survived', data=titanic_data)

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


sns.countplot(x='Survived', hue='Sex', data=titanic_data)

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


sns.countplot(x='Survived', hue='Pclass', data=titanic_data)

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


plt.hist(titanic_data['Age'].dropna())

(array([ 54.,  46., 177., 169., 118.,  70.,  45.,  24.,   9.,   2.]),
 array([ 0.42 ,  8.378, 16.336, 24.294, 32.252, 40.21 , 48.168, 56.126,
        64.084, 72.042, 80.   ]),
 <BarContainer object of 10 artists>)


plt.hist(titanic_data['Fare'])

(array([732., 106.,  31.,   2.,  11.,   6.,   0.,   0.,   0.,   3.]),
 array([  0.     ,  51.23292, 102.46584, 153.69876, 204.93168, 256.1646 ,
        307.39752, 358.63044, 409.86336, 461.09628, 512.3292 ]),
 <BarContainer object of 10 artists>)


titanic_data.isnull()


sns.heatmap(titanic_data.isnull(), cbar=False)

<AxesSubplot:>


sns.boxplot(titanic_data['Pclass'], titanic_data['Age'])

C:\Users\DELL\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='Pclass', ylabel='Age'>


#Pclass value 1

titanic_data[titanic_data['Pclass'] == 1]['Age'].mean()

#Pclass value 2

titanic_data[titanic_data['Pclass'] == 2]['Age'].mean()

#Pclass 3

titanic_data[titanic_data['Pclass'] == 2]['Age'].mean()

29.87763005780347


def impute_missing_age(columns):

    age = columns[0]

    passenger_class = columns[1]

    

    if pd.isnull(age):

        if(passenger_class == 1):

            return titanic_data[titanic_data['Pclass'] == 1]['Age'].mean()

        elif(passenger_class == 2):

            return titanic_data[titanic_data['Pclass'] == 2]['Age'].mean()

        elif(passenger_class == 3):

            return titanic_data[titanic_data['Pclass'] == 3]['Age'].mean()

        

    else:

        return age


titanic_data['Age'] = titanic_data[['Age', 'Pclass']].apply(impute_missing_age, axis = 1)


sns.heatmap(titanic_data.isnull(), cbar=False)

<AxesSubplot:>


titanic_data.drop('Cabin', axis=1, inplace = True)


titanic_data.dropna(inplace = True)


pd.get_dummies(titanic_data['Sex'])


pd.get_dummies(titanic_data['Sex'], drop_first = True)


sex_data = pd.get_dummies(titanic_data['Sex'], drop_first = True)

embarked_data = pd.get_dummies(titanic_data['Embarked'], drop_first = True)


titanic_data = pd.concat([titanic_data, sex_data, embarked_data], axis = 1)


titanic_data.drop(['Name', 'Ticket', 'Sex', 'Embarked'], axis = 1, inplace = True)


y_data = titanic_data['Survived']

x_data = titanic_data.drop('Survived', axis = 1)


from sklearn.model_selection import train_test_split


x_training_data, x_test_data, y_training_data, y_test_data = train_test_split(x_data, y_data, test_size = 0.3)


from sklearn.linear_model import LogisticRegression


model = LogisticRegression()


model.fit(x_training_data, y_training_data)

C:\Users\DELL\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

LogisticRegression()


predictions = model.predict(x_test_data)


from sklearn.metrics import classification_report


classification_report(y_test_data, predictions)

'              precision    recall  f1-score   support\n\n           0       0.79      0.86      0.82       159\n           1       0.76      0.66      0.71       108\n\n    accuracy                           0.78       267\n   macro avg       0.78      0.76      0.76       267\nweighted avg       0.78      0.78      0.78       267\n'


from sklearn.metrics import confusion_matrix

print(confusion_matrix(y_test_data, predictions))

[[137  22]
 [ 37  71]]

	female	male
0	0	1
1	1	0
2	1	0
3	1	0
4	0	1
...	...	...
886	0	1
887	1	0
888	1	0
889	0	1
890	0	1

	male
0	1
1	0
2	0
3	0
4	1
...	...
886	1
887	0
888	0
889	1
890	1

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	False	False	False	False	False	False	False	False	False	False	True	False
1	False	False	False	False	False	False	False	False	False	False	False	False
2	False	False	False	False	False	False	False	False	False	False	True	False
3	False	False	False	False	False	False	False	False	False	False	False	False
4	False	False	False	False	False	False	False	False	False	False	True	False
...	...	...	...	...	...	...	...	...	...	...	...	...
886	False	False	False	False	False	False	False	False	False	False	True	False
887	False	False	False	False	False	False	False	False	False	False	False	False
888	False	False	False	False	False	True	False	False	False	False	True	False
889	False	False	False	False	False	False	False	False	False	False	False	False
890	False	False	False	False	False	False	False	False	False	False	True	False

LOGISTIC REGRESSION¶