titanic-naive-bayes-1
April 21, 2024
[ ]: import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
[ ]: df = pd.read_csv('/content/train.csv')
df
[ ]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
.. … … …
886 887 0 2
887 888 1 1
888 889 0 3
889 890 1 1
890 891 0 3
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th… female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
.. … … … …
886 Montvila, Rev. Juozas male 27.0 0
887 Graham, Miss. Margaret Edith female 19.0 0
888 Johnston, Miss. Catherine Helen "Carrie" female NaN 1
889 Behr, Mr. Karl Howell male 26.0 0
890 Dooley, Mr. Patrick male 32.0 0
Parch Ticket Fare Cabin Embarked
1
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 NaN S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 NaN S
.. … … … … …
886 0 211536 13.0000 NaN S
887 0 112053 30.0000 B42 S
888 2 W./C. 6607 23.4500 NaN S
889 0 111369 30.0000 C148 C
890 0 370376 7.7500 NaN Q
[891 rows x 12 columns]
[ ]: df.shape
[ ]: (891, 12)
[ ]: df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 891 non-null int64
1 Survived 891 non-null int64
2 Pclass 891 non-null int64
3 Name 891 non-null object
4 Sex 891 non-null object
5 Age 714 non-null float64
6 SibSp 891 non-null int64
7 Parch 891 non-null int64
8 Ticket 891 non-null object
9 Fare 891 non-null float64
10 Cabin 204 non-null object
11 Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB
[ ]: df.describe(include='all')
[ ]: PassengerId Survived Pclass Name Sex \
count 891.000000 891.000000 891.000000 891 891
unique NaN NaN NaN 891 2
top NaN NaN NaN Braund, Mr. Owen Harris male
freq NaN NaN NaN 1 577
2
mean 446.000000 0.383838 2.308642 NaN NaN
std 257.353842 0.486592 0.836071 NaN NaN
min 1.000000 0.000000 1.000000 NaN NaN
25% 223.500000 0.000000 2.000000 NaN NaN
50% 446.000000 0.000000 3.000000 NaN NaN
75% 668.500000 1.000000 3.000000 NaN NaN
max 891.000000 1.000000 3.000000 NaN NaN
Age SibSp Parch Ticket Fare Cabin \
count 714.000000 891.000000 891.000000 891 891.000000 204
unique NaN NaN NaN 681 NaN 147
top NaN NaN NaN 347082 NaN B96 B98
freq NaN NaN NaN 7 NaN 4
mean 29.699118 0.523008 0.381594 NaN 32.204208 NaN
std 14.526497 1.102743 0.806057 NaN 49.693429 NaN
min 0.420000 0.000000 0.000000 NaN 0.000000 NaN
25% 20.125000 0.000000 0.000000 NaN 7.910400 NaN
50% 28.000000 0.000000 0.000000 NaN 14.454200 NaN
75% 38.000000 1.000000 0.000000 NaN 31.000000 NaN
max 80.000000 8.000000 6.000000 NaN 512.329200 NaN
Embarked
count 889
unique 3
top S
freq 644
mean NaN
std NaN
min NaN
25% NaN
50% NaN
75% NaN
max NaN
[ ]: df.dtypes
[ ]: PassengerId int64
Survived int64
Pclass int64
Name object
Sex object
Age float64
SibSp int64
Parch int64
Ticket object
Fare float64
Cabin object
3
Embarked object
dtype: object
[ ]: df.duplicated().sum()
[ ]: 0
[ ]: df.drop(["Sex","Name","Ticket","Cabin"], axis=1, inplace=True)
df
[ ]: PassengerId Survived Pclass Age SibSp Parch Fare Embarked
0 1 0 3 22.0 1 0 7.2500 S
1 2 1 1 38.0 1 0 71.2833 C
2 3 1 3 26.0 0 0 7.9250 S
3 4 1 1 35.0 1 0 53.1000 S
4 5 0 3 35.0 0 0 8.0500 S
.. … … … … … … … …
886 887 0 2 27.0 0 0 13.0000 S
887 888 1 1 19.0 0 0 30.0000 S
888 889 0 3 NaN 1 2 23.4500 S
889 890 1 1 26.0 0 0 30.0000 C
890 891 0 3 32.0 0 0 7.7500 Q
[891 rows x 8 columns]
[ ]: df.isnull().sum()
[ ]: PassengerId 0
Survived 0
Pclass 0
Age 177
SibSp 0
Parch 0
Fare 0
Embarked 2
dtype: int64
[ ]: df['Age'].fillna(df['Age'].mean(), inplace=True)
[ ]: df.dropna(inplace=True)
[ ]: df.isnull().sum()
[ ]: PassengerId 0
Survived 0
Pclass 0
Age 0
4
SibSp 0
Parch 0
Fare 0
Embarked 0
dtype: int64
[ ]: Q1=np.percentile(df['Age'], 25)
Q2=np.percentile(df['Age'], 50)
Q3=np.percentile(df['Age'], 75)
[ ]: IQR=Q3-Q1
[ ]: min=Q1-1.5*IQR
max=Q3+1.5*IQR
[ ]: df['Age'] = df['Age'].clip(min,max)
sns.boxplot(x=df['Age'])
plt.show()
[ ]: df=pd.get_dummies(df,columns=['Embarked'],dtype=int)
5
[ ]: x=df.drop(columns=['Survived'])
x
[ ]: PassengerId Pclass Age SibSp Parch Fare Embarked_C \
0 1 3 22.000000 1 0 7.2500 0
1 2 1 38.000000 1 0 71.2833 1
2 3 3 26.000000 0 0 7.9250 0
3 4 1 35.000000 1 0 53.1000 0
4 5 3 35.000000 0 0 8.0500 0
.. … … … … … … …
886 887 2 27.000000 0 0 13.0000 0
887 888 1 19.000000 0 0 30.0000 0
888 889 3 29.699118 1 2 23.4500 0
889 890 1 26.000000 0 0 30.0000 1
890 891 3 32.000000 0 0 7.7500 0
Embarked_Q Embarked_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
[889 rows x 9 columns]
[ ]: y=df['Survived']
y
[ ]: 0 0
1 1
2 1
3 1
4 0
..
886 0
887 1
888 0
889 1
890 0
Name: Survived, Length: 889, dtype: int64
6
[ ]: x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.
↪2,random_state=42)
[ ]: print("Training set shape:", x_train.shape, y_train.shape)
Training set shape: (711, 9) (711,)
[ ]: print("Testing set shape:", x_test.shape, y_test.shape)
Testing set shape: (178, 9) (178,)
[ ]: model=GaussianNB()
[ ]: model.fit(x_train,y_train)
[ ]: GaussianNB()
[ ]: y_pred=model.predict(x_test)
y_pred
[ ]: array([0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1,
0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0,
0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0,
0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0,
0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0,
1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0,
0, 0])
[ ]: from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Accuracy: 0.6348314606741573
[ ]:
