import pandas as pd

titanic_data = pd.read_csv("titanic.csv")

titanic_data.head()

titanic_data.columns

titanic_data.dtypes

titanic_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 14 columns):
pclass       1309 non-null int64
survived     1309 non-null int64
name         1309 non-null object
sex          1309 non-null object
age          1046 non-null float64
sibsp        1309 non-null int64
parch        1309 non-null int64
ticket       1309 non-null object
fare         1308 non-null float64
cabin        295 non-null object
embarked     1307 non-null object
boat         486 non-null object
body         121 non-null float64
home.dest    745 non-null object
dtypes: float64(3), int64(4), object(7)
memory usage: 143.2+ KB

titanic_data['survived'][0:5]

titanic_data.survived[0:5]

titanic_data[['survived','age']][0:5]

titanic_data['survived'].value_counts()

titanic_data['survived'].value_counts(normalize=True) * 100

pd.crosstab( titanic_data.sex, titanic_data.survived )

pd.crosstab( titanic_data.sex, titanic_data.survived, normalize = "index" )

pd.crosstab( titanic_data.sex, titanic_data.survived, normalize = "columns" )

pd.crosstab( titanic_data.sex, titanic_data.survived, normalize = "all" )

below_5_years[0:3]

len( below_5_years )

titanic_data[ titanic_data.age <= 5 ]["survived"].value_counts( )

titanic_data[ titanic_data.age <= 5 ]["survived"].value_counts( normalize = True )

titanic_data[titanic_data.name.str.contains( "Allen") ]

titanic_data.embarked.unique()

titanic_data.embarked.value_counts(dropna=False)

titanic_data.embarked.dropna().unique()

len( clean_titanic_data )

clean_titanic_data = titanic_data.dropna( how = "all" )
len( clean_titanic_data )

clean_titanic_data = titanic_data.dropna( subset = ['age','pclass'], how = 'any' )
len( clean_titanic_data )

titanic_data.head( 2)

titanic_data.head(2)

titanic_data[ ( titanic_data.survived == 1 ) &
           ( titanic_data.age <= 5 ) ][['age',
                                        'sex',
                                        'pclass']][0:5]

titanic_data[ titanic_data.age.isnull() ][['age',
                                         'survived',
                                         'sex',
                                         'pclass']][0:5]

titanic_data[ -titanic_data.age.isnull() ][['age',
                                          'survived',
                                          'sex',
                                          'pclass']][0:5]

titanic_data.groupby( 'pclass' )['age'].mean()

pclass_age_mean_df = titanic_data.groupby( 'pclass' )['age'].mean().reset_index()
pclass_age_mean_df

pclass_gender_age_mean_df = titanic_data.groupby( ['pclass', 'sex'] )['age'].mean().reset_index()
pclass_gender_age_mean_df

pclass_gender_survival_count_df = titanic_data.groupby( ['pclass', 'sex'] )['survived'].sum().reset_index()
pclass_gender_survival_count_df

pclass_age_gender_survival_df

pclass_age_gender_survival_df.sort_values( 'survived')

pclass_age_gender_survival_df.sort_values( 'survived', ascending = False)