주어진 df_people :
Name
0 Tom
1 Jerry
및 df_colors (헤더 행 없음) :
0 Red
1 Green
2 Blue
어떤이의 데이터 취할 수있는 최적의 방법으로 간주됩니다 df_colors를 하고 추가 df_people 하도록 df_people이 결합 될 때 같을 것이다 :
Name Color_0 Color_1 Color_2
0 Tom Red Green Blue
1 Jerry Red Green Blue
아래는 지금까지 내가 가지고있는 것인데, 작동하지만 더 나은 또는 더 간결한 방법이 있는지 궁금합니다.
# Store data for new columns in a dictionary
new_columns = {}
for index_people, row_people in df_people.iterrows():
for index_colors, row_colors in df_colors.iterrows():
key = 'Color_' + str(index_colors)
if (key in new_columns):
new_columns[key].append(row_colors[0])
else:
new_columns[key] = [row_colors[0]]
# Add dictionary data as new columns
for key, value in new_columns.items():
df_people[key] = value
최신 정보
답변 해주셔서 감사합니다. 실제 데이터 프레임은 GB 크기이므로 속도가 중요했기 때문에 가장 빠른 방법을 사용했습니다. 다음은 테스트 케이스에 대한 코드입니다.
# Import required modules
import pandas as pd
import timeit
# Original
def method_1():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
# Store data for new columns in a dictionary
new_columns = {}
for index_people, row_people in df_people.iterrows():
for index_colors, row_colors in df_colors.iterrows():
key = 'Color_' + str(index_colors)
if (key in new_columns):
new_columns[key].append(row_colors[0])
else:
new_columns[key] = [row_colors[0]]
# Add dictionary data as new columns
for key, value in new_columns.items():
df_people[key] = value
# YOBEN_S - https://stackoverflow.com/a/60805881/452587
def method_2():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
_s = pd.concat([df_colors]*len(df_people), axis=1)
_s.columns = df_people.index
df_people = df_people.join(_s.T.add_prefix('Color_'))
# Dani Mesejo - https://stackoverflow.com/a/60805898/452587
def method_3():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
# Create mock key
_m1 = df_people.assign(key=1)
# Set new column names, transpose, and create mock key
_m2 = df_colors.set_index('Color_' + df_colors.index.astype(str)).T.assign(key=1)
df_people = _m1.merge(_m2, on='key').drop('key', axis=1)
# Erfan - https://stackoverflow.com/a/60806018/452587
def method_4():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
df_colors = df_colors.T.reindex(df_people.index).ffill().add_prefix('Color_')
df_people = df_people.join(df_colors)
print('Method 1:', timeit.timeit(method_1, number=10000))
print('Method 2:', timeit.timeit(method_2, number=10000))
print('Method 3:', timeit.timeit(method_3, number=10000))
print('Method 4:', timeit.timeit(method_4, number=10000))
산출:
Method 1: 36.029883089
Method 2: 27.042384837999997
Method 3: 68.22421793800001
Method 4: 32.94155895
시나리오를 단순화하려는 노력으로 안타깝게도 지나치게 단순화했습니다. 지금 질문을 다시 말하기에는 너무 늦었으므로 나중에 관련 질문을 게시 할 것입니다. 실제 시나리오에서뿐만 아니라 수학, 그래서 대신에 단순히 추가 열을 포함 df_colors
에 df_people
나는 또한 추가 된 각 셀에 대해 해당 행의 열에 대한 몇 가지 계산을 수행해야합니다.
업데이트 2
샘플 데이터 프레임을 더 크게 만들고 (jezrael에게 감사드립니다) 두 가지 새로운 방법을 추가했습니다.
# Import required modules
import numpy as np
import pandas as pd
import timeit
# Original
def method_1():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
# Store data for new columns in a dictionary
new_columns = {}
for index_people, row_people in df_people.iterrows():
for index_colors, row_colors in df_colors.iterrows():
key = 'Color_' + str(index_colors)
if (key in new_columns):
new_columns[key].append(row_colors[0])
else:
new_columns[key] = [row_colors[0]]
# Add dictionary data as new columns
for key, value in new_columns.items():
df_people[key] = value
# YOBEN_S - https://stackoverflow.com/a/60805881/452587
def method_2():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
_s = pd.concat([df_colors]*len(df_people), axis=1)
_s.columns = df_people.index
df_people = df_people.join(_s.T.add_prefix('Color_'))
# sammywemmy - https://stackoverflow.com/a/60805964/452587
def method_3():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
# Create a new column in df_people with aggregate of df_colors;
df_people['Colors'] = df_colors[0].str.cat(sep=',')
# Concatenate df_people['Name'] and df_people['Colors'];
# split column, expand into a dataframe, and add prefix
df_people = pd.concat([df_people.Name, df_people.Colors.str.split(',', expand=True).add_prefix('Color_')], axis=1)
# Dani Mesejo - https://stackoverflow.com/a/60805898/452587
def method_4():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
# Create mock key
_m1 = df_people.assign(key=1)
# Set new column names, transpose, and create mock key
_m2 = df_colors.set_index('Color_' + df_colors.index.astype(str)).T.assign(key=1)
df_people = _m1.merge(_m2, on='key').drop('key', axis=1)
# Erfan - https://stackoverflow.com/a/60806018/452587
def method_5():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
df_colors = df_colors.T.reindex(df_people.index).ffill().add_prefix('Color_')
df_people = df_people.join(df_colors)
# jezrael - https://stackoverflow.com/a/60826723/452587
def method_6():
df_people = pd.DataFrame(['Tom', 'Jerry', 'Bob', 'John', 'Bill', 'Tim', 'Harry', 'Rick'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red', 'Green', 'Blue'] * 10, columns=None)
_a = np.broadcast_to(df_colors[0], (len(df_people), len(df_colors)))
df_people = df_people.join(pd.DataFrame(_a, index=df_people.index).add_prefix('Color_'))
print('Method 1:', timeit.timeit(method_1, number=3))
print('Method 2:', timeit.timeit(method_2, number=3))
print('Method 3:', timeit.timeit(method_3, number=3))
print('Method 4:', timeit.timeit(method_4, number=3))
print('Method 5:', timeit.timeit(method_5, number=3))
print('Method 6:', timeit.timeit(method_6, number=3))
산출:
Method 1: 74.512771493
Method 2: 1.0007798979999905
Method 3: 0.40823360299999933
Method 4: 0.08115736700000298
Method 5: 0.11704620100000795
Method 6: 0.04700596800000767
업데이트 3
실제 데이터 세트를 더 정확하게 반영하는 전치 및 계산 관련 질문을 게시했습니다 .
numpy.broadcast_to
방법 별로 성능을 향상시킬 수 있습니다 .
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
a = np.broadcast_to(df_colors[0], (len(df_people), len(df_colors)))
df = df_people.join(pd.DataFrame(a, index=df_people.index).add_prefix('Color_'))
print (df)
Name Color_0 Color_1 Color_2
0 Tom Red Green Blue
1 Jerry Red Green Blue
import timeit
def method_2():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
_s = pd.concat([df_colors]*len(df_people), axis=1)
_s.columns = df_people.index
df_people = df_people.join(_s.T.add_prefix('Color_'))
def method_5():
df_people = pd.DataFrame([['Tom'], ['Jerry']], columns=['Name'])
df_colors = pd.DataFrame([['Red'], ['Green'], ['Blue']], columns=None)
a = np.broadcast_to(df_colors[0], (len(df_people), len(df_colors)))
df_people = df_people.join(pd.DataFrame(a, index=df_people.index).add_prefix('Color_'))
print('Method 2:', timeit.timeit(method_2, number=10000))
Method 2: 27.919169027998578
print('Method 5:', timeit.timeit(method_5, number=10000))
Method 5: 21.452649746001043
그러나 나는 DataFrame
3k 행과 30 열에 대해 큰 테스트가 더 낫다고 생각합니다 . 그러면 타이밍이 다릅니다.
# Import required modules
import pandas as pd
import timeit
# Original
def method_1():
df_people = pd.DataFrame(['Tom','Jerry','Bob'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red','Green', 'Blue'] * 10, columns=None)
# Store data for new columns in a dictionary
new_columns = {}
for index_people, row_people in df_people.iterrows():
for index_colors, row_colors in df_colors.iterrows():
key = 'Color_' + str(index_colors)
if (key in new_columns):
new_columns[key].append(row_colors[0])
else:
new_columns[key] = [row_colors[0]]
# Add dictionary data as new columns
for key, value in new_columns.items():
df_people[key] = value
# YOBEN_S - https://stackoverflow.com/a/60805881/452587
def method_2():
df_people = pd.DataFrame(['Tom','Jerry','Bob'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red','Green', 'Blue'] * 10, columns=None)
_s = pd.concat([df_colors]*len(df_people), axis=1)
_s.columns = df_people.index
df_people = df_people.join(_s.T.add_prefix('Color_'))
# Dani Mesejo - https://stackoverflow.com/a/60805898/452587
def method_3():
df_people = pd.DataFrame(['Tom','Jerry','Bob'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red','Green', 'Blue'] * 10, columns=None)
# Create mock key
_m1 = df_people.assign(key=1)
# Set new column names, transpose, and create mock key
_m2 = df_colors.set_index('Color_' + df_colors.index.astype(str)).T.assign(key=1)
df_people = _m1.merge(_m2, on='key').drop('key', axis=1)
# Erfan - https://stackoverflow.com/a/60806018/452587
def method_4():
df_people = pd.DataFrame(['Tom','Jerry','Bob'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red','Green', 'Blue'] * 10, columns=None)
df_colors = df_colors.T.reindex(df_people.index).ffill().add_prefix('Color_')
df_people = df_people.join(df_colors)
def method_5():
df_people = pd.DataFrame(['Tom','Jerry','Bob'] * 1000, columns=['Name'])
df_colors = pd.DataFrame(['Red','Green', 'Blue'] * 10, columns=None)
a = np.broadcast_to(df_colors[0], (len(df_people), len(df_colors)))
df_people = df_people.join(pd.DataFrame(a, index=df_people.index).add_prefix('Color_'))
print('Method 1:', timeit.timeit(method_1, number=3))
print('Method 2:', timeit.timeit(method_2, number=3))
print('Method 3:', timeit.timeit(method_3, number=3))
print('Method 4:', timeit.timeit(method_4, number=3))
print('Method 5:', timeit.timeit(method_5, number=3))
Method 1: 34.91457201199955
Method 2: 0.7901797180002177
Method 3: 0.05690281799979857
Method 4: 0.05774562500118918
Method 5: 0.026483284000278218
이 기사는 인터넷에서 수집됩니다. 재 인쇄 할 때 출처를 알려주십시오.
침해가 발생한 경우 연락 주시기 바랍니다[email protected] 삭제
몇 마디 만하겠습니다