1┌─────────────────────────────────────────────────────────┐
2│                   Python Data Stack                      │
3├─────────────────────────────────────────────────────────┤
4│                                                          │
5│   ┌────────────┐  ┌────────────┐  ┌────────────┐       │
6│   │   NumPy    │  │   Pandas   │  │ Matplotlib │       │
7│   │ (Arrays)   │  │(DataFrames)│  │  (Charts)  │       │
8│   └────────────┘  └────────────┘  └────────────┘       │
9│         ▲               ▲               ▲               │
10│         │               │               │               │
11│   ┌─────┴───────────────┴───────────────┴─────┐        │
12│   │              Python 3.10+                  │        │
13│   └────────────────────────────────────────────┘        │
14│                                                          │
15│   Supporting: Seaborn, Plotly, Scipy, Statsmodels       │
16│                                                          │
17└─────────────────────────────────────────────────────────┘

1# Download Anaconda từ https://www.anaconda.com/download
2 
3# Sau khi cài, verify:
4conda --version
5# conda 23.x.x
6 
7# Create môi trường mới
8conda create -n data-analysis python=3.10
9 
10# Activate môi trường
11conda activate data-analysis
12 
13# Install packages
14conda install pandas numpy matplotlib seaborn jupyter

1# Download Python từ https://www.python.org/downloads/
2 
3# Verify installation
4python --version
5# Python 3.10.x
6 
7pip --version
8# pip 23.x.x
9 
10# Create virtual environment
11python -m venv data-analysis-env
12 
13# Activate (Windows)
14data-analysis-env\Scripts\activate
15 
16# Activate (macOS/Linux)
17source data-analysis-env/bin/activate
18 
19# Install packages
20pip install pandas numpy matplotlib seaborn jupyter notebook

1# Core packages
2pip install pandas numpy scipy
3 
4# Visualization
5pip install matplotlib seaborn plotly
6 
7# Jupyter
8pip install jupyter notebook jupyterlab
9 
10# Database connections
11pip install sqlalchemy psycopg2-binary pymysql
12 
13# Excel support
14pip install openpyxl xlrd
15 
16# Statistical analysis
17pip install statsmodels scikit-learn
18 
19# Date handling
20pip install python-dateutil pytz

1# Classic Notebook
2jupyter notebook
3 
4# JupyterLab (recommended)
5jupyter lab
6 
7# Mở URL: http://localhost:8888

1# Cell 1: Imports (always at top)
2import pandas as pd
3import numpy as np
4import matplotlib.pyplot as plt
5import seaborn as sns
6
7# Settings
8pd.set_option('display.max_columns', None)
9pd.set_option('display.max_rows', 100)
10plt.style.use('seaborn-v0_8-whitegrid')
11%matplotlib inline
12
13# Cell 2: Load data
14# Cell 3: Explore data
15# Cell 4+: Analysis
16# Last cell: Summary & conclusions

1# Install Python extension
2# Install Jupyter extension
3 
4# Benefits:
5# - Full IDE features (debugging, Git)
6# - Run notebooks in VS Code
7# - Better code completion
8# - Integrated terminal

1# PyCharm Professional has Jupyter support
2# Good for large projects
3# Excellent debugging
4 
5# Community edition: Free but no Jupyter
6# Professional: Paid with full features

1# Access: https://colab.research.google.com
2
3# Benefits:
4# - Free GPU/TPU access
5# - No setup required
6# - Share easily
7# - Pre-installed packages
8
9# Mount Google Drive
10from google.colab import drive
11drive.mount('/content/drive')

1# Numbers
2integer_val = 42
3float_val = 3.14
4complex_val = 1 + 2j
5
6# Strings
7name = "Data Analysis"
8multiline = """
9This is a
10multiline string
11"""
12
13# Boolean
14is_valid = True
15is_empty = False
16
17# None
18missing_value = None
19
20# Type checking
21print(type(42))         # <class 'int'>
22print(type(3.14))       # <class 'float'>
23print(type("hello"))    # <class 'str'>

1# List - ordered, mutable
2numbers = [1, 2, 3, 4, 5]
3numbers.append(6)
4numbers[0] = 10
5print(numbers[1:3])  # [2, 3]
6
7# Tuple - ordered, immutable
8coordinates = (10.5, 20.3)
9x, y = coordinates  # Unpacking
10
11# Dictionary - key-value pairs
12person = {
13    'name': 'Alice',
14    'age': 30,
15    'city': 'Hanoi'
16}
17print(person['name'])  # Alice
18person['email'] = 'alice@email.com'  # Add new key
19
20# Set - unique values
21unique_ids = {1, 2, 3, 2, 1}  # {1, 2, 3}

1# Conditionals
2score = 85
3if score >= 90:
4    grade = 'A'
5elif score >= 80:
6    grade = 'B'
7else:
8    grade = 'C'
9
10# Loops
11# For loop
12for i in range(5):
13    print(i)  # 0, 1, 2, 3, 4
14
15for name in ['Alice', 'Bob', 'Charlie']:
16    print(f"Hello, {name}")
17
18# While loop
19count = 0
20while count < 3:
21    print(count)
22    count += 1
23
24# List comprehension (Pythonic!)
25squares = [x**2 for x in range(10)]
26even_squares = [x**2 for x in range(10) if x % 2 == 0]

1# Basic function
2def greet(name):
3    return f"Hello, {name}!"
4
5# Default parameters
6def calculate_tax(amount, rate=0.1):
7    return amount * rate
8
9# Multiple returns
10def get_statistics(numbers):
11    return min(numbers), max(numbers), sum(numbers)/len(numbers)
12
13minimum, maximum, average = get_statistics([1, 2, 3, 4, 5])
14
15# Lambda functions
16square = lambda x: x ** 2
17add = lambda a, b: a + b
18
19# *args and **kwargs
20def flexible_func(*args, **kwargs):
21    print(f"Args: {args}")
22    print(f"Kwargs: {kwargs}")
23
24flexible_func(1, 2, 3, name='Alice', age=30)

1import numpy as np
2
3# Create arrays
4arr1 = np.array([1, 2, 3, 4, 5])
5arr2 = np.zeros(5)          # [0, 0, 0, 0, 0]
6arr3 = np.ones(5)           # [1, 1, 1, 1, 1]
7arr4 = np.arange(0, 10, 2)  # [0, 2, 4, 6, 8]
8arr5 = np.linspace(0, 1, 5) # [0, 0.25, 0.5, 0.75, 1]
9
10# 2D arrays
11matrix = np.array([
12    [1, 2, 3],
13    [4, 5, 6],
14    [7, 8, 9]
15])
16
17print(matrix.shape)  # (3, 3)
18print(matrix.dtype)  # int64

1a = np.array([1, 2, 3, 4])
2b = np.array([5, 6, 7, 8])
3
4# Element-wise operations
5print(a + b)      # [6, 8, 10, 12]
6print(a * b)      # [5, 12, 21, 32]
7print(a ** 2)     # [1, 4, 9, 16]
8
9# Statistics
10print(np.mean(a))   # 2.5
11print(np.std(a))    # 1.118
12print(np.median(a)) # 2.5
13print(np.sum(a))    # 10
14
15# Aggregations
16data = np.random.randn(100)
17print(f"Mean: {np.mean(data):.2f}")
18print(f"Std: {np.std(data):.2f}")
19print(f"Min: {np.min(data):.2f}")
20print(f"Max: {np.max(data):.2f}")

1arr = np.arange(10)  # [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
2
3# Basic indexing
4print(arr[0])     # 0
5print(arr[-1])    # 9
6print(arr[2:5])   # [2, 3, 4]
7print(arr[::2])   # [0, 2, 4, 6, 8]
8
9# Boolean indexing
10mask = arr > 5
11print(arr[mask])  # [6, 7, 8, 9]
12
13# 2D indexing
14matrix = np.arange(12).reshape(3, 4)
15# [[ 0,  1,  2,  3],
16#  [ 4,  5,  6,  7],
17#  [ 8,  9, 10, 11]]
18
19print(matrix[1, 2])     # 6
20print(matrix[0, :])     # [0, 1, 2, 3]
21print(matrix[:, 1])     # [1, 5, 9]
22print(matrix[0:2, 1:3]) # [[1, 2], [5, 6]]

1# test_setup.py
2print("Testing Python Data Analysis Setup...")
3print("=" * 50)
4
5# Test imports
6try:
7    import pandas as pd
8    print(f"✅ Pandas {pd.__version__}")
9except ImportError:
10    print("❌ Pandas not installed")
11
12try:
13    import numpy as np
14    print(f"✅ NumPy {np.__version__}")
15except ImportError:
16    print("❌ NumPy not installed")
17
18try:
19    import matplotlib
20    print(f"✅ Matplotlib {matplotlib.__version__}")
21except ImportError:
22    print("❌ Matplotlib not installed")
23
24try:
25    import seaborn as sns
26    print(f"✅ Seaborn {sns.__version__}")
27except ImportError:
28    print("❌ Seaborn not installed")
29
30try:
31    import scipy
32    print(f"✅ SciPy {scipy.__version__}")
33except ImportError:
34    print("❌ SciPy not installed")
35
36# Test basic operations
37print("\n" + "=" * 50)
38print("Testing operations...")
39
40df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
41print(f"✅ Created DataFrame:\n{df}")
42
43arr = np.random.randn(5)
44print(f"\n✅ NumPy random array: {arr}")
45
46print("\n" + "=" * 50)
47print("🎉 Setup complete! Ready for Data Analysis!")

1# 1. Tạo virtual environment mới
2# 2. Install tất cả packages cần thiết
3# 3. Chạy Jupyter Lab
4# 4. Tạo notebook đầu tiên với các imports
5# 5. Load sample data và hiển thị
6
7# YOUR CODE HERE