Installing Python, NumPy, and Pandas

# Option A: pip (clean installation)
python --version             # Verify Python 3.8+
python -m venv ds_env        # Create virtual environment
ds_env\Scripts\activate      # Windows activation
pip install numpy pandas matplotlib seaborn jupyter openpyxl

# Launch Jupyter Notebook
jupyter notebook             # Opens browser at localhost:8888

# Option B: Anaconda (recommended for beginners)
# Download from: https://www.anaconda.com/download
conda create -n datascience python=3.11
conda activate datascience
conda install numpy pandas matplotlib seaborn scikit-learn jupyter
jupyter notebook

# Option C: Google Colab (no installation!)
# Open: https://colab.research.google.com
# NumPy + Pandas already installed, free GPU available

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

print(f"NumPy:  {np.__version__}")    # 1.26.0
print(f"Pandas: {pd.__version__}")    # 2.1.0

# Quick test
arr = np.array([1, 2, 3])
df = pd.DataFrame({'A': [10, 20], 'B': [30, 40]})
print("NumPy:", arr)         # [1 2 3]
print("Pandas:\n", df)
print("✅ Ready for data science!")

# Key shortcuts:
# Shift+Enter  → Run cell and move to next
# B            → Insert cell below
# DD           → Delete cell
# M            → Markdown mode

# Magic commands:
%timeit np.sum(np.arange(1_000_000))   # Benchmark
%matplotlib inline                      # Show plots in notebook

# Pandas display settings
pd.set_option('display.max_columns', None)
pd.set_option('display.float_format', '{:.2f}'.format)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')

print("Data science environment ready!")