eda

import numpy as np;
import pandas as pd;
import matplotlib.pyplot as plt;
import seaborn as sns;

df = pd.read_csv('D9-titanic_dataset.csv')
df.head()

df.columns

df.info()

df.info()

df.shape

df.describe()

df.isnull().sum()

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

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

df['Sex'] = df['Sex'].fillna(df['Sex'].mode()[0])

df['Embarked'] = df['Embarked'].fillna(df['Embarked'].mode()[0])

df['Fare'] = df['Fare'].fillna(df['Fare'].median())

df['Fare'] = df['Fare'].fillna(df['Fare'].median())

df.isnull().sum()

plt.boxplot(df['Age'])
plt.show()

plt.boxplot(df['Fare'])
plt.show()


#handling outlier in fare
q1 = df['Fare'].quantile(0.25)
q3 = df['Fare'].quantile(0.75)
iqr = q3 - q1
lower = q1 - 1.5 * iqr
upper = q3 + 1.5 * iqr
df['Fare'] = np.clip(df['Fare'],lower,upper)



#remove unwanted columns
df.drop('PassengerId',axis = 1, inplace = True)
df.drop('Name',axis = 1, inplace = True)
df.drop('Ticket',axis = 1, inplace = True)


df.columns

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

df.dtypes


df.tail()

df.drop(1308,inplace = True)


matrix = df.corr()
matrix


sns.heatmap(matrix,annot = True)
plt.show()


df['column_name'].replace(calue_to_replace,  np.nan, inplace= 
True)