파이썬 기초와 데이터 처리 라이브러리

# 변수에 값 저장하기
name = "풍생고"
age = 17
height = 172.5
is_student = True

# 변수 출력하기
print(name)      # 풍생고
print(age)       # 17
print(height)    # 172.5

# 자료형 확인하기
print(type(name))  # <class 'str'>

score = 85
if score >= 90:
    print("A학점입니다!")
elif score >= 80:
    print("B학점입니다!")
elif score >= 70:
    print("C학점입니다!")
else:
    print("재시험 대상입니다.")
# 출력: B학점입니다!

# for 반복문 예시
fruits = ["사과", "바나나", "딸기"]
for fruit in fruits:
    print(fruit)

# range() 사용
for i in range(1, 6):
    print(i)   # 1, 2, 3, 4, 5

# while 반복문 예시
count = 1
while count <= 3:
    print(count)
    count += 1

# 함수 정의하기
def greet(name):
    message = "안녕, " + name + "!"
    return message

result = greet("김민준")
print(result)  # 안녕, 김민준!

# 두 수를 더하는 함수
def add(a, b):
    return a + b

print(add(10, 20))  # 30

import numpy as np

arr = np.array([1, 2, 3, 4, 5])
print(arr)    # [1 2 3 4 5]

np.zeros(5)      # [0. 0. 0. 0. 0.]
np.ones(5)       # [1. 1. 1. 1. 1.]
np.arange(1, 6)  # [1 2 3 4 5]

# 2차원 배열 (행렬)
mat = np.array([[1,2],[3,4]])
print(mat.shape)  # (2, 2)

import numpy as np
arr = np.array([10, 20, 30, 40])

print(arr * 2)   # [20 40 60 80]
print(arr + 5)   # [15 25 35 45]
print(arr ** 2)  # [100 400 900 1600]

print(arr[0])         # 10
print(arr[-1])        # 40 (마지막)
print(arr[1:3])       # [20 30]
print(arr[arr > 15])  # [20 30 40]

import numpy as np
scores = np.array([72, 85, 90, 60, 78])

print(np.sum(scores))   # 385
print(np.mean(scores))  # 77.0
print(np.max(scores))   # 90
print(np.min(scores))   # 60

reshaped = scores.reshape(5, 1)
print(np.sort(scores))  # [60 72 78 85 90]

import pandas as pd

data = {
    "이름": ["김민준", "이서연", "박지호"],
    "국어": [85, 92, 78],
    "수학": [78, 88, 95]
}
df = pd.DataFrame(data)
print(df)

import pandas as pd

df = pd.read_csv("students.csv")
print(df.head(3))
print(df.shape)    # (100, 4)
print(df.columns)
print(df.describe())

import pandas as pd
import numpy as np

data = {
    "이름": ["가", "나", "다"],
    "점수": [85, np.nan, 92]
}
df = pd.DataFrame(data)

print(df.isnull().sum())  # 점수: 1
df["점수"] = df["점수"].fillna(df["점수"].mean())

import pandas as pd

data = {
    "반": ["A","A","B","B","B"],
    "이름": ["김","이","박","최","정"],
    "점수": [85, 92, 78, 95, 88]
}
df = pd.DataFrame(data)

result = df.groupby("반")["점수"].mean()
print(result)
# A    88.5
# B    87.0

import matplotlib.pyplot as plt

months = ["3월","4월","5월","6월"]
scores = [72, 78, 85, 90]

plt.figure(figsize=(8, 4))
plt.plot(months, scores, marker="o")
plt.title("월별 성적 변화")
plt.xlabel("월")
plt.ylabel("점수")
plt.grid(True)
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

df = sns.load_dataset("tips")

sns.barplot(x="day", y="total_bill", data=df)
plt.title("요일별 평균 계산서")
plt.show()