熊猫串匹配优化

len(df3)

9599904

# Creating a column then filtering
start_time = time.time()
search = ['Emma','Ryan','Gerald','Billy','Helen']
df3['search'] = df3['First'].str.contains('|'.join(search))
new_df = df3[df3['search'] == True]
end_time = time.time()
print(f'Elapsed time was {(end_time - start_time)} seconds')

Elapsed time was 6.525546073913574 seconds

start_time = time.time()
search = ['Emma','Ryan','Gerald','Billy','Helen']
input_supplier = df3[df3['First'].str.contains('|'.join(search), flags=re.IGNORECASE)]
end_time = time.time()
print(f'Elapsed time was {(end_time - start_time)} seconds')

Elapsed time was 11.464462518692017 seconds

import numpy as np
import pandas as pd
import re

names = np.array(['Walter', 'Emma', 'Gus', 'Ryan', 'Skylar', 'Gerald',
                  'Saul', 'Billy', 'Jesse', 'Helen'] * 1000000)
input_supplier = pd.DataFrame(names, columns=['Category Level - 3'])

len(input_supplier)
10000000

category = ['Emma', 'Ryan', 'Gerald', 'Billy', 'Helen']

%%timeit
input_supplier['search'] = \
    input_supplier['Category Level - 3'].str.contains('|'.join(category))
df1 = input_supplier[input_supplier['search'] == True]

4.42 s ± 37.4 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
df2 = input_supplier[input_supplier['Category Level - 3'].str.contains(
    '|'.join(category), flags=re.IGNORECASE)]

5.45 s ± 25.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
lcase_vals = [x.lower() for x in input_supplier['Category Level - 3']]
category_lcase = [x.lower() for x in category]
df3 = input_supplier.iloc[np.where(np.isin(lcase_vals, category_lcase))[0]]

2.02 s ± 31.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
col_vals = input_supplier['Category Level - 3'].values
df4 = input_supplier.iloc[np.where(np.isin(col_vals, category))[0]]

623 ms ± 1.12 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)