Jupyter Notebook Guide: The Data Scientist's Favorite Tool

pip install jupyterlab
jupyter lab

pip install notebook
jupyter notebook

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from pathlib import Path

# Display settings
pd.set_option("display.max_columns", 50)
pd.set_option("display.float_format", "{:.2f}".format)
plt.style.use("seaborn-v0_8-whitegrid")
sns.set_palette("husl")

print("Libraries loaded")

# Load Titanic dataset (classic for learning)
df = pd.read_csv("titanic.csv")
print(f"Shape: {df.shape}")
df.head()

print("=== DATASET INFO ===")
df.info()

print("\n=== MISSING VALUES ===")
missing = df.isnull().sum()
print(missing[missing > 0])

print("\n=== SURVIVAL RATE ===")
print(f"{df['Survived'].mean():.1%} survived")

fig, axes = plt.subplots(1, 3, figsize=(15, 5))

# Survival by class
df.groupby("Pclass")["Survived"].mean().plot(kind="bar", ax=axes[0], color="steelblue")
axes[0].set_title("Survival Rate by Class")
axes[0].set_ylabel("Survival Rate")

# Age distribution by survival
df[df["Survived"] == 1]["Age"].hist(ax=axes[1], alpha=0.7, label="Survived", bins=20)
df[df["Survived"] == 0]["Age"].hist(ax=axes[1], alpha=0.7, label="Died", bins=20)
axes[1].set_title("Age Distribution")
axes[1].legend()

# Fare distribution
df["Fare"].hist(ax=axes[2], bins=30)
axes[2].set_title("Fare Distribution")

plt.tight_layout()
plt.show()

# Time a single line
%timeit sum(range(1000))

# Time an entire cell
%%timeit
total = 0
for i in range(1000):
    total += i

# Run a shell command
!pip install pandas

# Display all variables
%whos

# Load external script
%run my_script.py

# Show matplotlib plots inline
%matplotlib inline

# Show interactive plots
%matplotlib widget

# Display DataFrames as styled HTML
df.head().style.highlight_max(axis=0)

# Display images
from IPython.display import Image, display
display(Image("chart.png"))

# Display HTML
from IPython.display import HTML
HTML("<h2 style='color:blue'>HTML in a notebook</h2>")

# Display LaTeX equations
from IPython.display import Latex
Latex(r"$$\frac{d}{dx} e^x = e^x$$")

## Exploratory Analysis

Before building any models, let's understand the data.

### Key findings so far:
- **38% survival rate** overall
- First class passengers survived at **63%**, third class at only **24%**
- Women survived at **74%**, men at **19%**

These patterns suggest class and gender are strong predictors.

# DataFrames display as formatted tables
df.head(10)

# Conditional styling
df.style.background_gradient(subset=["Fare"], cmap="RdYlGn")

# Describe with colored output
df.describe().style.highlight_max()

# Interactive sorting and filtering
df.sort_values("Fare", ascending=False).head(10)

# Bad: monolithic cell
df = pd.read_csv("data.csv")
df.dropna(inplace=True)
df["new_col"] = df["col1"] * df["col2"]
result = df.groupby("category")["new_col"].sum()
result.plot()

# Good: one concern per cell
# Cell 1: Load
df = pd.read_csv("data.csv")
print(f"Loaded {len(df)} rows")

# Cell 2: Clean
df.dropna(inplace=True)
print(f"After cleaning: {len(df)} rows")

# Cell 3: Transform
df["revenue"] = df["price"] * df["quantity"]

# Cell 4: Analyze and visualize
by_category = df.groupby("category")["revenue"].sum()
by_category.plot(kind="bar", title="Revenue by Category")

# Export to HTML (shareable report)
jupyter nbconvert --to html analysis.ipynb

# Export to PDF
jupyter nbconvert --to pdf analysis.ipynb

# Export to Python script
jupyter nbconvert --to script analysis.ipynb

# Mount Google Drive
from google.colab import drive
drive.mount('/content/drive')

# Access file
df = pd.read_csv('/content/drive/MyDrive/data/my_file.csv')

# Install packages
!pip install yfinance

# Use free GPU
# Runtime → Change runtime type → GPU
import torch
print(torch.cuda.is_available())  # True if GPU allocated