Exploratory Data Analysis (EDA) in Python

pip install pandas matplotlib seaborn missingno

import pandas as pd

df = pd.read_csv("https://raw.githubusercontent.com/mwaskom/seaborn-data/master/titanic.csv")
print(df.head())

print(df.shape)        # Rows, Columns
print(df.info())       # Data types & non-null count
print(df.describe())   # Statistical summary

print(df.isnull().sum())

import missingno as msno
msno.matrix(df)

print(df['sex'].value_counts())

import matplotlib.pyplot as plt
df['age'].hist(bins=20)
plt.title("Age Distribution")
plt.xlabel("Age")
plt.ylabel("Frequency")
plt.show()

import seaborn as sns
sns.countplot(x='class', data=df)
plt.title("Passenger Class Distribution")
plt.show()

correlation = df.corr()
sns.heatmap(correlation, annot=True, cmap='coolwarm')
plt.title("Correlation Matrix")
plt.show()

sns.boxplot(x='survived', y='age', data=df)
plt.title("Age Distribution by Survival")
plt.show()

sns.barplot(x='sex', y='survived', data=df)
plt.title("Survival Rate by Gender")
plt.show()

sns.boxplot(x=df['fare'])
plt.title("Outlier Detection in Fare")
plt.show()

sns.pairplot(df[['age', 'fare', 'pclass', 'survived']], hue='survived')
plt.show()