인덱싱, 필터링 및 불리언 마스크

loc와 iloc

import pandas as pd

df = pd.DataFrame({"a":[1,2,3],"b":[4,5,6]}, index=["x","y","z"])
print(df.loc["y"])       # row with label y
print(df.iloc[1])        # row at position 1 (same row)
print(df.loc["x":"y"])   # rows x to y inclusive

불리언 마스크 필터링

import pandas as pd

df = pd.DataFrame({"name":["Alice","Bob","Carol"],"age":[30,17,25]})
adults = df[df["age"] >= 18]
print(adults)
# Alice 30
# Carol 25

여러 조건

import pandas as pd

df = pd.DataFrame({"city":["NY","LA","NY","LA"],"score":[80,90,70,85]})
result = df[(df["city"]=="NY") & (df["score"]>75)]
print(result)

query() 메서드

import pandas as pd

df = pd.DataFrame({"age":[30,17,25],"score":[90,80,70]})
result = df.query("age >= 18 and score > 75")
print(result)

isin() 필터링

import pandas as pd

df = pd.DataFrame({"city":["NY","LA","Chicago","NY"],"val":[1,2,3,4]})
print(df[df["city"].isin(["NY","LA"])])
# rows with NY or LA

범위 필터링에 between() 사용

import pandas as pd

df = pd.DataFrame({"score":[55,70,85,95,40]})
print(df[df["score"].between(60, 90)])
# 70 and 85

할당에 loc 사용

import pandas as pd

df = pd.DataFrame({"val":[1,2,3,4]})
df.loc[df["val"] > 2, "val"] = 99
print(df)
# 0:1  1:2  2:99  3:99

단일 값에 at 및 iat 사용

import pandas as pd

df = pd.DataFrame({"a":[10,20],"b":[30,40]})
print(df.at[0,"a"])    # 10  (by label)
print(df.iat[1,1])     # 40  (by position)

Dtype으로 선택하기

import pandas as pd

df = pd.DataFrame({"x":[1,2],"name":["a","b"],"score":[1.5,2.5]})
nums = df.select_dtypes(include=["number"])
print(nums.columns.tolist())   # ['x', 'score']

중복 제거

import pandas as pd

df = pd.DataFrame({"name":["Alice","Bob","Alice"],"age":[30,25,30]})
print(df.drop_duplicates())
# keeps first Alice, removes second

nlargest 및 nsmallest

import pandas as pd

df = pd.DataFrame({"product":["A","B","C","D"],"sales":[500,300,800,200]})
print(df.nlargest(2,"sales"))
# C 800
# A 500

빠른 확인

복습