text 数据集 - mainupulacao de arquivo

Posted 2021-04-29

#cria um dataset 

dataset = {'Actor': [],
           'Total Gross': [],
           'Number of Movies': [],
           'Average per Movie': [],
           '#1 Movie': [],
           'Gross': []}"
           

#manipulacao com dataset  - CSV
with open('actors.csv', 'r') as f:
    arquivo_csv = csv.reader(f, delimiter=',', quotechar='"')
    for i, row in enumerate(arquivo_csv):
        # pulando o header
        if i == 0:
            continue
        # parsing
        dataset['Actor'].append(row[0])
        dataset['Total Gross'].append(float(row[1]))
        dataset['Number of Movies'].append(int(row[2]))
        dataset['Average per Movie'].append(float(row[3]))
        dataset['#1 Movie'].append(row[4])
        dataset['Gross'].append(float(row[5]))
   
  #manipulacao com arquivo texto
  #linha a linha
  f = open("demofile.txt", "r")
  for x in f:
    print(x)

#arquivo inteiro
f = open("demofile.txt", "r")
print(f.read())

#ver DictReader

dataset = {}
with open('googleplaystore.csv', 'r') as f:
    arquivo_csv = csv.reader(f, delimiter=',', quotechar='"')
    for i, row in enumerate(arquivo_csv):
        if i ==0:
            header = row
            print(header)
            for col_name in header:
                dataset[col_name] = []
            continue
        if len(row) != len(header):
            print('Skipping row with missing values...')            
            continue
        for j, item in enumerate(row):            
            col_name = header[j]
            if col_name == 'Installs':
                item = float(item.replace('+', '').replace(',', ''))
            if col_name == 'Price':
                item = float(item.replace('$', ''))
            dataset[col_name].append(item)