数据不一致

解决一些数据不一致问题
例如：“usa” 和 "USA"是一个东西，让它们在数据中变成一样。

# modules we'll use
import pandas as pd
import numpy as np

# helpful modules
import fuzzywuzzy
from fuzzywuzzy import process
import charset_normalizer

# read in all our data
professors = pd.read_csv("../input/pakistan-intellectual-capital/pakistan_intellectual_capital.csv")

# set seed for reproducibility
np.random.seed(0)

# get all the unique values in the 'Country' column
countries = professors['Country'].unique()

# sort them alphabetically and then take a closer look
countries.sort()
countries

array([' Germany', ' New Zealand', ' Sweden', ' USA', 'Australia',
       'Austria', 'Canada', 'China', 'Finland', 'France', 'Greece',
       'HongKong', 'Ireland', 'Italy', 'Japan', 'Macau', 'Malaysia',
       'Mauritius', 'Netherland', 'New Zealand', 'Norway', 'Pakistan',
       'Portugal', 'Russian Federation', 'Saudi Arabia', 'Scotland',
       'Singapore', 'South Korea', 'SouthKorea', 'Spain', 'Sweden',
       'Thailand', 'Turkey', 'UK', 'USA', 'USofA', 'Urbana', 'germany'],
      dtype=object)

# convert to lower case
# 全部转变为小写
professors['Country'] = professors['Country'].str.lower()

# remove trailing white spaces
# 去掉尾部的空格
professors['Country'] = professors['Country'].str.strip()

使用 fuzzy 库

Fuzzy matching ——模糊匹配

# get the top 10 closest matches to "south korea"
matches = fuzzywuzzy.process.extract("south korea", countries, limit=10, scorer=fuzzywuzzy.fuzz.token_sort_ratio)

# take a look at them
matches

[('south korea', 100),
 ('southkorea', 48),
 ('saudi arabia', 43),
 ('norway', 35),
 ('austria', 33),
 ('ireland', 33),
 ('pakistan', 32),
 ('portugal', 32),
 ('scotland', 32),
 ('australia', 30)]

# function to replace rows in the provided column of the provided dataframe
# that match the provided string above the provided ratio with the provided string
def replace_matches_in_column(df, column, string_to_match, min_ratio = 47):
    # get a list of unique strings
    strings = df[column].unique()
    
    # get the top 10 closest matches to our input string
    matches = fuzzywuzzy.process.extract(string_to_match, strings, 
                                         limit=10, scorer=fuzzywuzzy.fuzz.token_sort_ratio)

    # only get matches with a ratio > 90
    close_matches = [matches[0] for matches in matches if matches[1] >= min_ratio]

    # get the rows of all the close matches in our dataframe
    rows_with_matches = df[column].isin(close_matches)

    # replace all rows with close matches with the input matches 
    df.loc[rows_with_matches, column] = string_to_match
    
    # let us know the function's done
    print("All done!")


# use the function we just wrote to replace close matches to "south korea" with "south korea"
replace_matches_in_column(df=professors, column='Country', string_to_match="south korea")