pandas Day 4
November 8, 2023
[ ]: import pandas as pd
import seaborn as sns
[ ]: df = sns.load_dataset('titanic')
df.head()
[ ]: survived pclass sex age sibsp parch fare embarked class \
0 0 3 male 22.0 1 0 7.2500 S Third
1 1 1 female 38.0 1 0 71.2833 C First
2 1 3 female 26.0 0 0 7.9250 S Third
3 1 1 female 35.0 1 0 53.1000 S First
4 0 3 male 35.0 0 0 8.0500 S Third
who adult_male deck embark_town alive alone
0 man True NaN Southampton no False
1 woman False C Cherbourg yes False
2 woman False NaN Southampton yes True
3 woman False C Southampton yes False
4 man True NaN Southampton no True
[ ]: df.shape
[ ]: (891, 15)
[ ]: df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 survived 891 non-null int64
1 pclass 891 non-null int64
2 sex 891 non-null object
3 age 714 non-null float64
4 sibsp 891 non-null int64
5 parch 891 non-null int64
6 fare 891 non-null float64
7 embarked 889 non-null object
1
8 class 891 non-null category
9 who 891 non-null object
10 adult_male 891 non-null bool
11 deck 203 non-null category
12 embark_town 889 non-null object
13 alive 891 non-null object
14 alone 891 non-null bool
dtypes: bool(2), category(2), float64(2), int64(4), object(5)
memory usage: 80.7+ KB
[ ]: df.isnull().sum()
[ ]: survived 0
pclass 0
sex 0
age 177
sibsp 0
parch 0
fare 0
embarked 2
class 0
who 0
adult_male 0
deck 688
embark_town 2
alive 0
alone 0
dtype: int64
[ ]: df.isnull().sum() / df.shape[0]
[ ]: survived 0.000000
pclass 0.000000
sex 0.000000
age 0.198653
sibsp 0.000000
parch 0.000000
fare 0.000000
embarked 0.002245
class 0.000000
who 0.000000
adult_male 0.000000
deck 0.772166
embark_town 0.002245
alive 0.000000
alone 0.000000
dtype: float64
2
[ ]: df.shape[0]
[ ]: 891
[ ]: df.shape[0]
df.shape[1]
[ ]: 15
[ ]: sns.heatmap(df.isnull(), cbar=False)
[ ]: <Axes: >
[ ]: sns.heatmap(df.isnull(), cbar=True)
[ ]: <Axes: >
3
[ ]: df[['sex', 'age', 'class']]
[ ]: sex age class
0 male 22.0 Third
1 female 38.0 First
2 female 26.0 Third
3 female 35.0 First
4 male 35.0 Third
.. … … …
886 male 27.0 Second
887 female 19.0 First
888 female NaN Third
889 male 26.0 First
890 male 32.0 Third
[891 rows x 3 columns]
4
[ ]: print(df['sex'].unique())
df.sex.nunique()
['male' 'female']
[ ]: 2
[ ]: df.nunique()
[ ]: survived 2
pclass 3
sex 2
age 88
sibsp 7
parch 7
fare 248
embarked 3
class 3
who 3
adult_male 2
deck 7
embark_town 3
alive 2
alone 2
dtype: int64
[ ]: df.columns
[ ]: Index(['survived', 'pclass', 'sex', 'age', 'sibsp', 'parch', 'fare',
'embarked', 'class', 'who', 'adult_male', 'deck', 'embark_town',
'alive', 'alone'],
dtype='object')
[ ]: df['embark_town'].unique()
[ ]: array(['Southampton', 'Cherbourg', 'Queenstown', nan], dtype=object)
[ ]: df['embark_town'].value_counts()
[ ]: embark_town
Southampton 644
Cherbourg 168
Queenstown 77
Name: count, dtype: int64
[ ]: df.groupby('sex')['fare'].mean()
5
[ ]: sex
female 44.479818
male 25.523893
Name: fare, dtype: float64
[ ]: df.groupby(['class', 'sex'])['fare'].mean()
C:\Users\Lala Abu\AppData\Local\Temp\ipykernel_9808\299023266.py:1:
FutureWarning: The default of observed=False is deprecated and will be changed
to True in a future version of pandas. Pass observed=False to retain current
behavior or observed=True to adopt the future default and silence this warning.
df.groupby(['class', 'sex'])['fare'].mean()
[ ]: class sex
First female 106.125798
male 67.226127
Second female 21.970121
male 19.741782
Third female 16.118810
male 12.661633
Name: fare, dtype: float64
[ ]: df.groupby(['survived', 'sex', 'who'])['fare'].mean()
[ ]: survived sex who
0 female child 32.076113
woman 20.967174
male child 33.073905
man 21.490736
1 female child 30.887800
woman 54.813801
male child 35.562700
man 42.076422
Name: fare, dtype: float64
[ ]: df.groupby(['survived', 'who']).size()
[ ]: survived who
0 child 34
man 449
woman 66
1 child 49
man 88
woman 205
dtype: int64
[ ]: df.drop('deck', axis=1, inplace=True)
6
[ ]: print (df.age.median())
print (df.age.mean())
28.0
29.69911764705882
[ ]: df['age'].fillna(df['age'].mean(), inplace=True)
[ ]: print (df.age.median())
print (df.age.mean())
29.69911764705882
29.69911764705882
[ ]:
