Memilih Kolom Berdasarkan Pola

Mengapa Memilih Kolom Berdasarkan Pola?

import pandas as pd

df = pd.DataFrame({
    'sales_jan': [100, 200],
    'sales_feb': [150, 250],
    'cost_jan': [50, 80],
    'cost_feb': [60, 90],
    'profit': [140, 280]
})

print(df.columns.tolist())
# ['sales_jan', 'sales_feb', 'cost_jan', 'cost_feb', 'profit']

filter(like=) untuk Mencocokkan Substring

import pandas as pd

df = pd.DataFrame({
    'sales_jan': [100, 200],
    'sales_feb': [150, 250],
    'cost_jan': [50, 80],
    'revenue_q1': [110, 210]
})

# Select columns whose name contains 'sales'
sales_cols = df.filter(like='sales')
print(sales_cols)
#    sales_jan  sales_feb
# 0        100        150
# 1        200        250

filter(regex=) untuk Mencocokkan Pola

import pandas as pd

df = pd.DataFrame({
    'q1_revenue': [100],
    'q2_revenue': [200],
    'q1_cost': [40],
    'q2_cost': [60],
    'annual_total': [360]
})

# Select columns ending with '_revenue'
revenue_cols = df.filter(regex='_revenue$')
print(revenue_cols)
#    q1_revenue  q2_revenue
# 0         100         200

# Select columns starting with 'q' (quarter columns)
quarter_cols = df.filter(regex='^q')
print(quarter_cols.columns.tolist())
# ['q1_revenue', 'q2_revenue', 'q1_cost', 'q2_cost']

Pemahaman Daftar pada df.columns

import pandas as pd

df = pd.DataFrame({
    'age': [25, 30],
    'age_group': ['young', 'mid'],
    'income': [50000, 70000],
    'income_tax': [8000, 12000],
    'name': ['Alice', 'Bob']
})

# Select columns that start with 'income'
income_cols = [c for c in df.columns if c.startswith('income')]
print(df[income_cols])
#    income  income_tax
# 0   50000        8000
# 1   70000       12000

Memilih Berdasarkan Akhiran Nama Kolom

import pandas as pd

df = pd.DataFrame({
    'revenue_2022': [100],
    'cost_2022': [40],
    'revenue_2023': [150],
    'cost_2023': [55],
    'notes': ['ok']
})

# Use Index.str.endswith for suffix selection
cols_2023 = df.columns[df.columns.str.endswith('_2023')]
print(df[cols_2023])
#    revenue_2023  cost_2023
# 0           150         55

Menghapus Kolom Berdasarkan Pola

import pandas as pd

df = pd.DataFrame({
    'id': [1, 2],
    'name': ['A', 'B'],
    'temp_col1': [0, 0],
    'temp_col2': [0, 0],
    'score': [90, 80]
})

# Drop columns whose name starts with 'temp_'
temp_cols = [c for c in df.columns if c.startswith('temp_')]
cleaned = df.drop(columns=temp_cols)
print(cleaned)
#    id name  score
# 0   1    A     90
# 1   2    B     80

Memilih Kolom Numerik dengan select_dtypes

import pandas as pd

df = pd.DataFrame({
    'name': ['Alice', 'Bob'],
    'age': [25, 30],
    'salary': [50000.0, 70000.0],
    'dept': ['Eng', 'HR']
})

# Select only numeric columns
numeric_df = df.select_dtypes(include='number')
print(numeric_df)
#    age   salary
# 0   25  50000.0
# 1   30  70000.0

# Exclude numeric columns
text_df = df.select_dtypes(exclude='number')
print(text_df)
#     name dept
# 0  Alice  Eng
# 1    Bob   HR

filter() pada Indeks Baris dengan axis=0

import pandas as pd

df = pd.DataFrame({
    'value': [10, 20, 30, 40]
}, index=['alpha_a', 'beta_b', 'alpha_c', 'gamma_d'])

# Filter rows by index label pattern
alpha_rows = df.filter(like='alpha', axis=0)
print(alpha_rows)
#          value
# alpha_a     10
# alpha_c     30

Menggabungkan Pola Pemilihan Kolom

import pandas as pd

df = pd.DataFrame(columns=[
    'user_id', 'user_name', 'user_email',
    'product_id', 'product_name', 'product_price',
    'order_total', 'order_date'
])

# Step 1: columns that start with 'user_' or 'order_'
step1 = [c for c in df.columns if c.startswith('user_') or c.startswith('order_')]

# Step 2: exclude email (PII)
final_cols = [c for c in step1 if 'email' not in c]
print(final_cols)
# ['user_id', 'user_name', 'order_total', 'order_date']

Mengurutkan Ulang Kolom Berdasarkan Pola

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'metric_b': [1], 'metric_a': [2],
    'id': [10], 'label': ['x'],
    'metric_c': [3]
})

# Put id and label first, then sort metric columns alphabetically
id_cols = ['id', 'label']
metric_cols = sorted([c for c in df.columns if c.startswith('metric')])
ordered = df[id_cols + metric_cols]
print(ordered.columns.tolist())
# ['id', 'label', 'metric_a', 'metric_b', 'metric_c']

Contoh Praktis: Data Survei Lebar

import pandas as pd

survey = pd.DataFrame({
    'respondent_id': [1, 2, 3],
    'q1_score': [4, 3, 5],
    'q2_score': [3, 4, 4],
    'q3_score': [5, 5, 3],
    'q1_comment': ['good', 'ok', 'great'],
    'q2_comment': ['fine', 'nice', 'meh']
})

# All score columns
score_cols = survey.filter(regex='_score$').columns
survey['avg_score'] = survey[score_cols].mean(axis=1)
print(survey[['respondent_id', 'avg_score']])
#    respondent_id  avg_score
# 0              1   4.000000
# 1              2   4.000000
# 2              3   4.000000

Pemeriksaan Cepat

Ringkasan Pelajaran