import pandas as pd df = pd.read_csv("names.txt") #df["separado"] = df["Nombres"].str.split() #df["nombre"] = df["separado"][0:] #df["apellido"] = df["separado"][1:] #df["nombre"]= df["Nombres"].str.split(" ", n = 1, expand = True) #df["nombre"] = df["Nombres"].str.split(" ", n = 1, expand = True) #df["nombre"]= df["Nombres"].str.split(" ", n = 1, expand = True) df[['nombre', 'apellido']] = df['Nombres'].str.split(' ', 1, expand=True) del df['Nombres'] df.to_csv("archivosalida.csv", sep=';', encoding='utf-8') with open("archivosalida2.csv","w") as fw: for i in df: fw.write(i[0]+";"+i[1]) df.head(5)

import pandas as pd words = [] with open('el_quijote.txt','r') as f: for line in f: for word in line.split(): words.append(word.lower()) column_values = ['palabra'] df = pd.DataFrame(data = words, columns = column_values ) #df.head(5) #print(words) #df.head(5) #parte1 print("\nfrecuencia por palabra") print(df["palabra"].value_counts()) valores = df["palabra"].value_counts() print("\ntop 10 frecuencia por palabra") print(valores[:10]) #print((df["palabra"].unique()).size ) #parte2 print("\ntop 10 cuales palabras") print(df["palabra"].value_counts()[:10].index.tolist()) #import padas as pd

archivo = r'el_quijote.txt' with open(archivo) as f: texto = f.readlines() completo = [] for l in texto: linea = l.split() for p in linea: completo.append(p.lower()) palabra = '' conteo_palabras = {} conteo = 0 keys = [] for p in completo: if p not in keys: keys.append(p) print(keys)

from nltk.corpus import stopwords from nltk.tokenize.toktok import ToktokTokenizer from nltk.tokenize import word_tokenize, regexp_tokenize

import nltk nltk.download('stopwords') nltk.download('punkt') nltk.download('perluniprops') nltk.download('nonbreaking_prefixes')

## defecto para ingles word_tokens = word_tokenize(content.lower()) len(word_tokens)

## no funciona bien con español, ya que no incluye acentos ni ñ word_tokens = regexp_tokenize(content.lower(), pattern='\w+') len(word_tokens)

## mejor para español pero contiene caracteres como punto, comas, etc.. toktok = ToktokTokenizer() word_tokens = toktok.tokenize(content.lower()) len(word_tokens)

stop_words = list(stopwords.words('spanish')) stop_words += [',', '.', ':', ';'] ## agregamos mas stopwords len(stop_words)

filtered_words =[w for w in word_tokens if not w in stop_words ] len(filtered_words)

from collections import Counter counter = Counter(filtered_words) counter.most_common(10)

import csv with open('data/data-text.csv', 'r') as f: reader = csv.reader(f) for row in reader: print(row[0], row[1]) break

import pandas as pd df = pd.read_csv('data/data-text.csv') df

df.to_csv('data/data-text-copy.csv')

import json with open('data/data-text.json') as f: content = f.read() data = json.loads(content) for item in data: print(item) break

with open('file.json', 'w') as f: json.dump(data, f)

df = pd.read_json('data/data-text.json') df

df.to_json('data/data-text-copy.json')

!pip install xlrd