Snippets Collections
# remove punc, segment and stopword
def punc_jieba(text, sep = ' '):
#     stopword = stopwords(["zh"])
    text_punc = re.sub("[\s+\>\<\:\?\.\!\/_,$%^*(+\"\']+|[+——!,。?、~@#¥%……&*()!,❤。~《》:()【】「」?”“;:、【】╮╯▽╰╭★→「」]+".encode().decode("utf8"),
                        "",text)
    text_cut = sep.join(jieba.cut(text_punc, cut_all=False)).lower()
#     tokens = word_tokenize(text_cut)
#     clean_text = [word for word in tokens if not word in stopword]
    
    return text_cut
# mothod1
def stop_word(text):
    stopword = stopwords(['zh'])
    remove_stw = [word for word in text if not word in stopword]
    return remove_stw
df['text'] = df['text'].apply(stop_word)
# mothod2
stopword = stopwords(['zh'])
df['text'] = df['text'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stopword)]))
sudo pip install opencc
# if nt work, should clone project first

import pandas as pd
import numpy as np
# -*- coding: utf-8 -*-
import opencc
from opencc import OpenCC

df = pd.read_csv('training.csv').astype(str)

def tra_sim(text):
    cc = OpenCC('tw2s')
    sim = cc.convert(text)
    return sim
df['sim_label'] = df['label'].apply(tra_sim)
df['sim_detail_label'] = df['detail_label'].apply(tra_sim)
df['sim_text'] = df['text'].apply(tra_sim)
# best way
data['resume'] = data[['Resume_title', 'City', 'State', 'Description', 'work_experiences', 'Educations', 'Skills', 'Certificates', 'Additional Information']].agg(' '.join, axis=1)


# other way
df["period"] = df["Year"] + df["quarter"]
df['Period'] = df['Year'] + ' ' + df['Quarter']
df["period"] = df["Year"].astype(str) + df["quarter"] #If one (or both) of the columns are not string typed
#Beware of NaNs when doing this!
df['period'] = df[['Year', 'quarter', ...]].agg('-'.join, axis=1) #for multiple string columns
df['period'] = df[['Year', 'quarter']].apply(lambda x: ''.join(x), axis=1)
#method cat() of the .str accessor 
df['Period'] = df.Year.str.cat(df.Quarter)
df['Period'] = df.Year.astype(str).str.cat(df.Quarter.astype(str), sep='q')
df['AllTogether'] = df['Country'].str.cat(df[['State', 'City']], sep=' - ') #add parameter na_rep to replace the NaN values with a string if have nan
columns = ['whatever', 'columns', 'you', 'choose']
df['period'] = df[columns].astype(str).sum(axis=1)

#a function
def str_join(df, sep, *cols):
   ...:     from functools import reduce
   ...:     return reduce(lambda x, y: x.astype(str).str.cat(y.astype(str), sep=sep), 
   ...:                   [df[col] for col in cols])
   ...: 

In [4]: df['cat'] = str_join(df, '-', 'c0', 'c1', 'c2', 'c3')
trx_1.select(f.countDistinct("stg_nexus_member_cd")).show()
# applying filter function 
df.filter(["Name", "College", "Salary"]) 

star

Sat Oct 31 2020 00:40:59 GMT+0000 (UTC) https://www.geeksforgeeks.org/python-pandas-dataframe-filter/

#pandas #filter #column

Save snippets that work with our extensions

Available in the Chrome Web Store Get Firefox Add-on Get VS Code extension