Python Setup & Environment

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

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

1# Core
2pip install pandas numpy scipy
3 
4# Visualization
5pip install matplotlib seaborn plotly
6 
7# Jupyter
8pip install jupyter notebook jupyterlab
9 
10# Database + Excel
11pip install sqlalchemy psycopg2-binary openpyxl xlrd
12 
13# Statistics
14pip install statsmodels scikit-learn

1# Classic Notebook
2jupyter notebook
3 
4# JupyterLab (recommended)
5jupyter lab
6# → 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

1integer_val = 42
2float_val = 3.14
3name = "Data Analysis"
4is_valid = True
5missing_value = None
6
7print(type(42))         # <class 'int'>
8print(type(3.14))       # <class 'float'>
9print(type("hello"))    # <class 'str'>

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

1# List comprehension (Pythonic!)
2squares = [x**2 for x in range(10)]
3even_squares = [x**2 for x in range(10) if x % 2 == 0]
4
5# Functions
6def calculate_tax(amount, rate=0.1):
7    return amount * rate
8
9# Lambda
10square = lambda x: x ** 2
11
12# Multiple returns
13def get_statistics(numbers):
14    return min(numbers), max(numbers), sum(numbers)/len(numbers)
15minimum, maximum, average = get_statistics([1, 2, 3, 4, 5])
16
17# *args and **kwargs
18def flexible_func(*args, **kwargs):
19    print(f"Args: {args}, Kwargs: {kwargs}")

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

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

1print("Testing Python Data Analysis Setup...")
2print("=" * 50)
3
4import pandas as pd
5print(f"✅ Pandas {pd.__version__}")
6
7import numpy as np
8print(f"✅ NumPy {np.__version__}")
9
10import matplotlib
11print(f"✅ Matplotlib {matplotlib.__version__}")
12
13import seaborn as sns
14print(f"✅ Seaborn {sns.__version__}")
15
16# Test operations
17df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
18print(f"✅ DataFrame created:\n{df}")
19
20print("\n🎉 Setup complete! Ready for Data Analysis!")