데이터 과학을위한 파이썬 (무료 7 일 미니 코스)

filename = "responses.txt"
survey_name = "Q3 Customer Feedback"
max_entries = 100

with open("responses.txt", "r") as file:
    lines = file.readlines()

for i, line in enumerate(lines):
    cleaned = line.strip()  # removes \n and spaces
    print(f"{i + 1}: {cleaned}")

1: Yes
2: No
3: Yes
4: Maybe
5: No

with open("responses.txt", "r") as infile:
    lines = infile.readlines()

yes_responses = []

for line in lines:
    if line.strip().lower() == "yes":
        yes_responses.append(line.strip())

with open("yes_only.txt", "w") as outfile:
    for item in yes_responses:
        outfile.write(item + "\n")

with open("scores.txt", "r") as file:
    scores = [float(line.strip()) for line in file]

print(scores)

average = sum(scores) / len(scores)
print(f"Average score: {average:.2f}")

Alice, 34
Bob, 29
Eve, 41

with open("people.txt", "r") as file:
    records = []
    for line in file:
        name, age = line.strip().split(",")
        records.append((name.strip(), int(age.strip())))

for person in records:
    name, age = person
    if age > 30:
        print(f"{name} is over 30.")

people = []

with open("people.txt", "r") as file:
    for line in file:
        name, age = line.strip().split(",")
        person = {
            "name": name.strip(),
            "age": int(age.strip())
        }
        people.append(person)

for person in people:
    if person["age"] 

domains = set()

with open("emails.txt", "r") as file:
    for line in file:
        email = line.strip().lower()
        if "@" in email:
            domain = email.split("@")[1]
            domains.add(domain)

print(domains) 

{'gmail.com', 'yahoo.com', 'example.org'}

titles = [
    "  Data Scientist\n",
    "data scientist",
    "Senior Data Scientist ",
    "DATA scientist",
    "Data engineer",
    "Data Scientist"
]

cleaned = [title.strip().lower() for title in titles]

['data scientist', 'data scientist', 'senior data scientist', 'data scientist', 'data engineer', 'data scientist']

standardized = []

for title in cleaned:
    if "data scientist" in title:
        standardized.append("data scientist")
    else:
        standardized.append(title)

text = " The price is $5,000!  "

# Clean up
clean = text.strip().lower().replace("$", "").replace(",", "").replace("!", "")
print(clean)  

# Word count
word_count = len(clean.split())

# Contains digit
has_number = any(char.isdigit() for char in clean)

print(word_count)
print(has_number)

"the price is 5000"
4
True

email = "  [email protected]  "
email = email.strip().lower()

username, domain = email.split("@")

print(f"User: {username}, Domain: {domain}")

User: alice.johnson, Domain: example.com

comment = "I'm learning Python and SQL for data jobs."

if "python" in comment.lower():
    print("Mentioned Python")

Great course! Loved the pacing.
Not enough Python examples.
Too basic for experienced users.
python is exactly what I needed!
Would like more SQL content.
Excellent – very beginner-friendly.

data = [
    {"name": "Alice", "city": "London"},
    {"name": "Bob", "city": "Paris"},
    {"name": "Eve", "city": "London"},
    {"name": "John", "city": "New York"},
    {"name": "Dana", "city": "Paris"},
]

city_counts = {}

for person in data:
    city = person["city"]
    if city not in city_counts:
        city_counts[city] = 1
    else:
        city_counts[city] += 1

print(city_counts)

{'London': 2, 'Paris': 2, 'New York': 1}

salaries = [
    {"role": "Engineer", "salary": 75000},
    {"role": "Analyst", "salary": 62000},
    {"role": "Engineer", "salary": 80000},
    {"role": "Manager", "salary": 95000},
    {"role": "Analyst", "salary": 64000},
]

totals = {}
counts = {}

for person in salaries:
    role = person["role"]
    salary = person["salary"]
    
    totals[role] = totals.get(role, 0) + salary
    counts[role] = counts.get(role, 0) + 1

averages = {role: totals[role] / counts[role] for role in totals}

print(averages)

{'Engineer': 77500.0, 'Analyst': 63000.0, 'Manager': 95000.0}

ages = [29, 34, 29, 41, 34, 29]

freq = {}

for age in ages:
    freq[age] = freq.get(age, 0) + 1

most_common = max(freq.items(), key=lambda x: x[1])

print(f"Most common age: {most_common[0]} (appears {most_common[1]} times)")

Most common age: 29 (appears 3 times)

Alice,London,Engineer,75000
Bob,Paris,Analyst,62000
Eve,London,Engineer,80000
John,New York,Manager,95000
Dana,Paris,Analyst,64000

def clean_text(text):
    return text.strip().lower().replace(",", "").replace("$", "")

def parse_row(line):
    parts = line.strip().split(",")
    return {
        "name": parts[0],
        "city": parts[1],
        "role": parts[2],
        "salary": int(parts[3])
    }

with open("employees.txt") as file:
    rows = [parse_row(line) for line in file]

def average(values):
    return sum(values) / len(values) if values else 0

def count_by_key(data, key):
    counts = {}
    for item in data:
        k = item[key]
        counts[k] = counts.get(k, 0) + 1
    return counts

try:
    with open("employees.txt") as file:
        lines = file.readlines()
except FileNotFoundError:
    print("Error: File not found.")
    lines = []

records = []

for line in lines:
    try:
        parts = line.strip().split(",")
        if len(parts) != 4:
            raise ValueError("Incorrect number of fields")
        record = {
            "name": parts[0],
            "city": parts[1],
            "role": parts[2],
            "salary": int(parts[3])
        }
        records.append(record)
    except Exception as e:
        print(f"Skipping bad line: {line.strip()} ({e})")

with open("cleaned_employees.txt", "w") as out:
    for r in records:
        out.write(f"{r['name']},{r['city']},{r['role']},{r['salary']}\n")

Alice,London,Engineer,75000
Bob,Paris,Analyst
Eve,London,Engineer,eighty thousand
John,New York,Manager,95000

def load_csv(filename):
    with open(filename) as f:
        lines = [line.strip() for line in f if line.strip()]
    header = lines[0].split(",")
    rows = [line.split(",") for line in lines[1:]]
    return header, rows

def detect_type(value):
    try:
        float(value)
        return "numeric"
    except:
        return "text"

def profile_columns(header, rows):
    summary = {}
    for i, col in enumerate(header):
        values = [row[i].strip() for row in rows if len(row) == len(header)]
        col_type = detect_type(values[0])
        unique = set(values)
        summary[col] = {
            "type": col_type,
            "unique_count": len(unique),
            "most_common": max(set(values), key=values.count)
 }
 if col_type == "numeric":
 nums = [float(v) for v in values if v.replace('.', '', 1).isdigit()]
 summary[col]["average"] = sum(nums) / len(nums) if nums else 0
 return summary

def write_summary(summary, out_file):
    with open(out_file, "w") as f:
        for col, stats in summary.items():
            f.write(f"Column: {col}\n")
            for k, v in stats.items():
                f.write(f"  {k}: {v}\n")
            f.write("\n")

header, rows = load_csv("employees.csv")
summary = profile_columns(header, rows)
write_summary(summary, "profile_report.txt")