File I/O Basics

Starting with Text Files — The First Step in Data Persistence

---

Why Do We Need File Operations?

• Save data analysis results
• Read external data
• Generate reports
• Data backup

---

Basic File Operations

1. Writing to Files

# Write to text file
with open('output.txt', 'w', encoding='utf-8') as f:
    f.write("This is the first line\n")
    f.write("This is the second line\n")

# Append content
with open('output.txt', 'a', encoding='utf-8') as f:
    f.write("This is appended content\n")

Mode descriptions:

• 'r': Read-only (default)
• 'w': Write (overwrite)
• 'a': Append
• 'r+': Read and write

2. Reading Files

# Method 1: Read entire file at once
with open('output.txt', 'r', encoding='utf-8') as f:
    content = f.read()
    print(content)

# Method 2: Read line by line
with open('output.txt', 'r', encoding='utf-8') as f:
    for line in f:
        print(line.strip())  # strip() removes newline characters

# Method 3: Read all lines into a list
with open('output.txt', 'r', encoding='utf-8') as f:
    lines = f.readlines()
    print(lines)  # ['First line\n', 'Second line\n', ...]

3. Context Managers (with Statement)

# Not recommended (requires manual closing)
f = open('file.txt', 'r')
content = f.read()
f.close()

# Recommended (automatically closes)
with open('file.txt', 'r') as f:
    content = f.read()
# File is automatically closed when exiting the with block

---

Practical Cases

Case 1: Save Survey Results

respondents = [
    {'id': 1001, 'age': 25, 'income': 50000},
    {'id': 1002, 'age': 30, 'income': 75000},
    {'id': 1003, 'age': 35, 'income': 85000}
]

# Save to text file
with open('survey_results.txt', 'w', encoding='utf-8') as f:
    f.write("Survey Results\n")
    f.write("=" * 40 + "\n")
    for resp in respondents:
        line = f"ID:{resp['id']}, Age:{resp['age']}, Income:{resp['income']}\n"
        f.write(line)

print("Results saved to survey_results.txt")

Case 2: Read and Process Data

# Read data file
ages = []
with open('ages.txt', 'r') as f:
    for line in f:
        age = int(line.strip())
        ages.append(age)

# Statistics
print(f"Average age: {sum(ages) / len(ages):.1f}")
print(f"Maximum age: {max(ages)}")
print(f"Minimum age: {min(ages)}")

Case 3: Logging

from datetime import datetime

def log_analysis(message):
    """Record analysis log"""
    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    with open('analysis.log', 'a', encoding='utf-8') as f:
        f.write(f"[{timestamp}] {message}\n")

# Usage
log_analysis("Started data cleaning")
log_analysis("Removed 15 outliers")
log_analysis("Data cleaning completed")

---

Path Operations

Using pathlib (Recommended)

from pathlib import Path

# Create path objects
data_dir = Path('data')
raw_dir = data_dir / 'raw'        # Path concatenation
processed_dir = data_dir / 'processed'

# Create directories
raw_dir.mkdir(parents=True, exist_ok=True)

# Check if file exists
file_path = raw_dir / 'survey.txt'
if file_path.exists():
    print("File exists")

# List files in directory
for file in data_dir.glob('*.txt'):
    print(file.name)

Using os.path (Traditional Method)

import os

# Join paths
file_path = os.path.join('data', 'raw', 'survey.txt')

# Check existence
if os.path.exists(file_path):
    print("File exists")

# Create directory
os.makedirs('data/processed', exist_ok=True)

# List files
files = os.listdir('data')

---

Best Practices

1. Always Specify Encoding

# Explicitly specify UTF-8
with open('file.txt', 'r', encoding='utf-8') as f:
    content = f.read()

2. Use with Statement

# Automatically closes file
with open('file.txt', 'r') as f:
    content = f.read()

3. Handle File Not Found Cases

from pathlib import Path

file_path = Path('data.txt')
if file_path.exists():
    with open(file_path, 'r') as f:
        content = f.read()
else:
    print("File does not exist")

---

Practice Exercises

# Exercise 1: Create student grades file
# Write the following data to scores.txt
scores = [
    ('Alice', 85),
    ('Bob', 92),
    ('Carol', 78)
]
# Format: Alice: 85

# Exercise 2: Analyze text file
# Read file and count:
# - Total number of lines
# - Total number of characters
# - Number of lines containing a specific keyword

---

Next Steps

In the next section, we'll learn about CSV and Excel file processing.

Keep going!