csv_analysis.py

import pandas as pd
import matplotlib.pyplot as plt

# Load the CSV file
data = pd.read_csv("titanic.csv")

# Display first 5 rows
print("First 5 Rows:")
print(data.head())

# Display column names
print("\nColumns:")
print(data.columns)

# Display dataset information
print("\nDataset Information:")
print(data.info())

# Display statistical summary
print("\nStatistical Summary:")
print(data.describe())

# Calculate average age
print("\nAverage Age:")
print(data["age"].mean())
# Bar Chart
data["class"].value_counts().plot(kind="bar")
plt.title("Passengers by Class")
plt.xlabel("Class")
plt.ylabel("Number of Passengers")
plt.show()

# Scatter Plot
plt.scatter(data["age"], data["fare"])
plt.title("Age vs Fare")
plt.xlabel("Age")
plt.ylabel("Fare")
plt.show()

# Heatmap
plt.imshow(data.corr(numeric_only=True), cmap="coolwarm")
plt.colorbar()
plt.xticks(range(len(data.corr(numeric_only=True).columns)),
           data.corr(numeric_only=True).columns, rotation=45)
plt.yticks(range(len(data.corr(numeric_only=True).columns)),
           data.corr(numeric_only=True).columns)
plt.title("Correlation Heatmap")
plt.show()