davisvictorns

premier_league_all.groupby(by=["season", "team"]).mean().unstack()

davisvictorns

#function to get points in percentage
def percentage(val):
    return (val / (38*3)) * 100

fig, ax = plt.subplots(nrows=1, ncols=4, figsize=(26, 5))

#array with needed columns
itens = ["position", "points", "goals_for", "goals_against"]

premier_league_all_grouped = premier_league_all.groupby(by=["season", "team"]).mean().unstack()

davisvictorns

!pip install emoji

davisvictorns

import re
import regex
import pandas as pd
import numpy as np
import emoji
import plotly.express as px
from collections import Counter
import matplotlib.pyplot as plt
from os import path
from PIL import Image

davisvictorns

! git clone https://github.com/amueller/word_cloud.git
% cd word_cloud
! pip install .

davisvictorns

def iniciaDataHora(s):
    padrao = '^(\d{2})(\/)(\d{2})(\/)(\d{4}) (\d{2}):(\d{2})[ ]? -' 
    resultado = re.match(padrao, s)
    if resultado:
        return True
    return False

davisvictorns

autores_anoni = []
def anonimizarAutor(autor):
    if autor is None:
        return None
    if autor in autores_anoni:
        return autores_anoni.index(autor) + 1
    else:
        autores_anoni.append(autor)
        return autores_anoni.index(autor) + 1

davisvictorns

def dadosSeparados(linha):
    #01/11/2020 15:25 - Exemplo: Oi, eu sou o Exemplo

    data_search = re.search("(\d{2})(\/)(\d{2})(\/)(\d{4})", linha)
    data = data_search.group()

    hora_search = re.search("(\d{2}):(\d{2})", linha)
    hora = hora_search.group()

    #para o autor estamos pegando a string que está entre "- " e ": "

davisvictorns

dadoAnalisado = []
conversationPath = '/content/dev_chat_analise.txt' 
with open(conversationPath, encoding="utf-8") as fp:
    fp.readline()
    mensagemBuffer = [] 
    data, hora, autor, mensagem = None, None, None, ""
    while True:
        linha = fp.readline() 
        if not linha: 
            break

davisvictorns

df = pd.DataFrame(dadoAnalisado, columns=['data', 'hora', 'autor', 'mensagem'])
df["data"] = pd.to_datetime(df["data"])
df = df.dropna()
df.head(5)