Created
April 28, 2021 22:49
-
-
Save brunomsantiago/77bd56fbba4e962752f9a0862f622a28 to your computer and use it in GitHub Desktop.
String search on pandas dataframe
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import pandas as pd | |
from random import choice, randint | |
names = ['David', 'James', 'John', 'Michael', 'Richard', 'Robert', 'William'] | |
surnames = ['Davis', 'Jones', 'Lee', 'Miller', 'Moore', 'Smith', 'Taylor'] | |
colors = ['Black', 'Blue', 'Green', 'Purple', 'Red', 'White', 'Yellow'] | |
pets = ['', 'Dog', 'Cat', 'Bird', 'Fish', 'Bunny', 'Hamster', 'Guinea Pig'] | |
def random_person(): | |
person = {} | |
person['First Name'] = choice(names) | |
person['Last Name'] = choice(surnames) | |
person['Year of Birth'] = randint(1970, 2000) | |
person['Favorite Color'] = choice(colors) | |
person['Pet'] = choice(pets) | |
return person | |
def row_to_string(row): | |
return (' '.join(row.values.astype(str))).lower() | |
def search_df(df, query): | |
queries = query.lower().split(' ') | |
strings = df.apply(row_to_string, axis=1) | |
masks = [strings.str.contains(word) for word in queries] | |
final_mask = np.column_stack(masks).all(axis=1) | |
return df[final_mask] | |
data = [random_person() for _ in range(20)] | |
df = pd.DataFrame(data).sort_values(by='Year of Birth').reset_index(drop=True) | |
query = 'taylor 197' | |
df2 = search_df(df, query) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment