Titan - Train dataset

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix, classification_report

df = pd.read_csv('/content/titanic_train.csv')

df.head(2)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C

Exploratory Analysis on basic import of dataset

df.isnull()

	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

891 rows × 12 columns

sns.heatmap(df.isnull(), yticklabels= False, cbar = False, cmap = "Blues")

<matplotlib.axes._subplots.AxesSubplot at 0x7f9335ad1c10>

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

<matplotlib.axes._subplots.AxesSubplot at 0x7f933c3f0750>

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

<matplotlib.axes._subplots.AxesSubplot at 0x7f933c2d55d0>

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

<matplotlib.axes._subplots.AxesSubplot at 0x7f933c032c90>

df.drop('PassengerId', inplace = True, axis = 1)

sns.pairplot(df)

<seaborn.axisgrid.PairGrid at 0x7f933998e890>

df.head(2)

	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C

sns.boxplot(x = 'Pclass', y = 'Age', data = df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f933620eb50>

def impute_age(cols):
    Age = cols[0]
    Pclass = cols[1]

    if pd.isnull(Age) == True:
        if Pclass == 1:
            return 37
        elif Pclass == 2:
            return 32
        else:
            return 24
    else:
        return Age

df['Age'] = df[['Age', 'Pclass']].apply(impute_age, axis = 1)

sns.heatmap(df.isnull(), cmap = 'Blues')

<matplotlib.axes._subplots.AxesSubplot at 0x7f9335d6c950>

df.head(2)

	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C

df.drop(['Name', 'Ticket'], inplace = True, axis = 1)

df.head(2)

	Survived	Pclass	Sex	Age	SibSp	Parch	Fare	Cabin	Embarked
0	0	3	male	22.0	1	0	7.2500	NaN	S
1	1	1	female	38.0	1	0	71.2833	C85	C

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

Embark_df = pd.get_dummies(df['Embarked'], drop_first = True)

sex_df

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

891 rows × 1 columns

Embark_df

	Q	S
0	0	1
1	0	0
2	0	1
3	0	1
4	0	1
...	...	...
886	0	1
887	0	1
888	0	1
889	0	0
890	1	0

891 rows × 2 columns

df = pd.concat([df, sex_df, Embark_df], axis = 1)

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

logreg = LogisticRegression()

df

	Survived	Pclass	Sex	Age	SibSp	Parch	Fare	Embarked	male	Q	S
0	0	3	male	22.0	1	0	7.2500	S	1	0	1
1	1	1	female	38.0	1	0	71.2833	C	0	0	0
2	1	3	female	26.0	0	0	7.9250	S	0	0	1
3	1	1	female	35.0	1	0	53.1000	S	0	0	1
4	0	3	male	35.0	0	0	8.0500	S	1	0	1
...	...	...	...	...	...	...	...	...	...	...	...
886	0	2	male	27.0	0	0	13.0000	S	1	0	1
887	1	1	female	19.0	0	0	30.0000	S	0	0	1
888	0	3	female	24.0	1	2	23.4500	S	0	0	1
889	1	1	male	26.0	0	0	30.0000	C	1	0	0
890	0	3	male	32.0	0	0	7.7500	Q	1	1	0

891 rows × 11 columns

df.drop('Sex', inplace = True, axis = 1)

df.drop('Embarked', inplace = True, axis = 1)

df

	Survived	Pclass	Age	SibSp	Parch	Fare	male	Q	S
0	0	3	22.0	1	0	7.2500	1	0	1
1	1	1	38.0	1	0	71.2833	0	0	0
2	1	3	26.0	0	0	7.9250	0	0	1
3	1	1	35.0	1	0	53.1000	0	0	1
4	0	3	35.0	0	0	8.0500	1	0	1
...	...	...	...	...	...	...	...	...	...
886	0	2	27.0	0	0	13.0000	1	0	1
887	1	1	19.0	0	0	30.0000	0	0	1
888	0	3	24.0	1	2	23.4500	0	0	1
889	1	1	26.0	0	0	30.0000	1	0	0
890	0	3	32.0	0	0	7.7500	1	1	0

891 rows × 9 columns

from sklearn.model_selection import train_test_split

X = df.drop('Survived', axis = 1)
y = df['Survived']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=101)

logreg.fit(X_train, y_train)

/usr/local/lib/python3.7/dist-packages/sklearn/linear_model/_logistic.py:818: 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
  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG,

LogisticRegression()

predictions = logreg.predict(X_test)

predictions

array([0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,
       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0,
       0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0,
       1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1,
       0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0,
       0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1,
       1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0,
       0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0,
       1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1,
       0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1,
       1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 1,
       0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0,
       1, 0, 0, 1])

df

	Survived	Pclass	Age	SibSp	Parch	Fare	male	Q	S
0	0	3	22.0	1	0	7.2500	1	0	1
1	1	1	38.0	1	0	71.2833	0	0	0
2	1	3	26.0	0	0	7.9250	0	0	1
3	1	1	35.0	1	0	53.1000	0	0	1
4	0	3	35.0	0	0	8.0500	1	0	1
...	...	...	...	...	...	...	...	...	...
886	0	2	27.0	0	0	13.0000	1	0	1
887	1	1	19.0	0	0	30.0000	0	0	1
888	0	3	24.0	1	2	23.4500	0	0	1
889	1	1	26.0	0	0	30.0000	1	0	0
890	0	3	32.0	0	0	7.7500	1	1	0

891 rows × 9 columns

print(classification_report(y_test, predictions))

              precision    recall  f1-score   support

           0       0.78      0.87      0.82       154
           1       0.79      0.67      0.72       114

    accuracy                           0.78       268
   macro avg       0.79      0.77      0.77       268
weighted avg       0.78      0.78      0.78       268

confusion_matrix(y_test, predictions)

array([[134,  20],
       [ 38,  76]])

sns.heatmap(df, cmap = 'Blues')

<matplotlib.axes._subplots.AxesSubplot at 0x7f9335e6c3d0>

df

	Survived	Pclass	Age	SibSp	Parch	Fare	male	Q	S
0	0	3	22.0	1	0	7.2500	1	0	1
1	1	1	38.0	1	0	71.2833	0	0	0
2	1	3	26.0	0	0	7.9250	0	0	1
3	1	1	35.0	1	0	53.1000	0	0	1
4	0	3	35.0	0	0	8.0500	1	0	1
...	...	...	...	...	...	...	...	...	...
886	0	2	27.0	0	0	13.0000	1	0	1
887	1	1	19.0	0	0	30.0000	0	0	1
888	0	3	24.0	1	2	23.4500	0	0	1
889	1	1	26.0	0	0	30.0000	1	0	0
890	0	3	32.0	0	0	7.7500	1	1	0

891 rows × 9 columns

df.head(2)

	Survived	Pclass	Age	SibSp	Parch	Fare	male	Q	S
0	0	3	22.0	1	0	7.2500	1	0	1
1	1	1	38.0	1	0	71.2833	0	0	0