Titanic_Machine_Learning_from_Disaster/analysis.ipynb

Titanic_Machine_Learning_from_Disaster

Imports

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px

Data description

df_train = pd.read_csv('train.csv')

df_train.columns

Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

df_train.describe()

	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

Analysis before data cleaning

sns.catplot(x='Sex', y='Survived', data=df_train, kind='violin')

<seaborn.axisgrid.FacetGrid at 0x1f232d8f6d0>

# sns.pairplot(data=df_train, hue='Survived')

Data Cleaning

df_train = pd.get_dummies(data=df_train, columns=['Sex', 'Embarked'])

df_train.drop(['Sex_male', 'Name', 'Ticket', 'PassengerId'], axis=1, inplace=True)

df_train['Cabin'] = df_train['Cabin'].fillna('None')

df_train['Cabin'].unique()

array(['None', 'C85', 'C123', 'E46', 'G6', 'C103', 'D56', 'A6',
       'C23 C25 C27', 'B78', 'D33', 'B30', 'C52', 'B28', 'C83', 'F33',
       'F G73', 'E31', 'A5', 'D10 D12', 'D26', 'C110', 'B58 B60', 'E101',
       'F E69', 'D47', 'B86', 'F2', 'C2', 'E33', 'B19', 'A7', 'C49', 'F4',
       'A32', 'B4', 'B80', 'A31', 'D36', 'D15', 'C93', 'C78', 'D35',
       'C87', 'B77', 'E67', 'B94', 'C125', 'C99', 'C118', 'D7', 'A19',
       'B49', 'D', 'C22 C26', 'C106', 'C65', 'E36', 'C54',
       'B57 B59 B63 B66', 'C7', 'E34', 'C32', 'B18', 'C124', 'C91', 'E40',
       'T', 'C128', 'D37', 'B35', 'E50', 'C82', 'B96 B98', 'E10', 'E44',
       'A34', 'C104', 'C111', 'C92', 'E38', 'D21', 'E12', 'E63', 'A14',
       'B37', 'C30', 'D20', 'B79', 'E25', 'D46', 'B73', 'C95', 'B38',
       'B39', 'B22', 'C86', 'C70', 'A16', 'C101', 'C68', 'A10', 'E68',
       'B41', 'A20', 'D19', 'D50', 'D9', 'A23', 'B50', 'A26', 'D48',
       'E58', 'C126', 'B71', 'B51 B53 B55', 'D49', 'B5', 'B20', 'F G63',
       'C62 C64', 'E24', 'C90', 'C45', 'E8', 'B101', 'D45', 'C46', 'D30',
       'E121', 'D11', 'E77', 'F38', 'B3', 'D6', 'B82 B84', 'D17', 'A36',
       'B102', 'B69', 'E49', 'C47', 'D28', 'E17', 'A24', 'C50', 'B42',
       'C148'], dtype=object)

df_train['Cabin'].value_counts()

None           687
C23 C25 C27      4
G6               4
B96 B98          4
C22 C26          3
              ... 
E34              1
C7               1
C54              1
E36              1
C148             1
Name: Cabin, Length: 148, dtype: int64

df_train['Age'] = df_train['Age'].fillna(df_train['Age'].mean())

counts = df_train['Cabin'].value_counts().copy(deep=True)
df_train['Cabin'][df_train['Cabin'].isin(counts[counts==1].index)] = 'Alone'
df_train['Cabin'][df_train['Cabin'].isin(counts[counts==2].index)] = 'Double room'
df_train['Cabin'][df_train['Cabin'].isin(counts[counts==3].index)] = 'Three person room'
df_train['Cabin'][df_train['Cabin'].isin(counts[counts==4].index)] = 'Four person room'
df_train['Cabin'][df_train['Cabin'].isin(counts[counts>4].index)] = 'Other'

C:\Users\Maciej\AppData\Local\Temp/ipykernel_8664/4127688350.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_train['Cabin'][df_train['Cabin'].isin(counts[counts==1].index)] = 'Alone'
C:\Users\Maciej\AppData\Local\Temp/ipykernel_8664/4127688350.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_train['Cabin'][df_train['Cabin'].isin(counts[counts==2].index)] = 'Double room'
C:\Users\Maciej\AppData\Local\Temp/ipykernel_8664/4127688350.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_train['Cabin'][df_train['Cabin'].isin(counts[counts==3].index)] = 'Three person room'
C:\Users\Maciej\AppData\Local\Temp/ipykernel_8664/4127688350.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_train['Cabin'][df_train['Cabin'].isin(counts[counts==4].index)] = 'Four person room'
C:\Users\Maciej\AppData\Local\Temp/ipykernel_8664/4127688350.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_train['Cabin'][df_train['Cabin'].isin(counts[counts>4].index)] = 'Other'

df_train['Cabin'].value_counts()

Other                687
Alone                101
Double room           76
Three person room     15
Four person room      12
Name: Cabin, dtype: int64

df_train = pd.get_dummies(data=df_train, columns=['Cabin'])

Analysis

corrmat = df_train.corr() 
cols = corrmat.nlargest(15, 'Survived')['Survived'].index 
cm = np.corrcoef(df_train[cols].values.T) 
sns.set(font_scale=1.25) 
hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 8}, yticklabels=cols.values, xticklabels=cols.values)