Домашняя работа по уроку 4.1

In [10]:

    

import pandas as pd
PATH = '/Users/martysyuk/Documents/Python 3 Coding/Repositorys/PY-3-Learning/homeworks/names/'
YEARS = ['1900', '1950', '2000']
MERGE_ON = ['Name', 'Gender']
COLUMNS = ['Name', 'Gender', 'Count']

data = open_csv_files_by_year(YEARS)


    

In [2]:

    

def open_csv_files_by_year(*args):
    _data = dict()
    for year in args[0]:
        try:
            _file_name = PATH + 'yob' + str(year) + '.txt'
            _data.update({year: pd.read_csv(_file_name, names=COLUMNS)})
        except FileNotFoundError:
            pass
    return _data


    

In [3]:

    

def count_top3(_data_):
    names = pd.concat(_data_)
    df = names.groupby(MERGE_ON, as_index=False).sum().sort_values(by='Count', ascending=False).head(3)
    
    return list(df.Name)


    

In [5]:

    

def count_dynamics(_data_):
    _dyn_data_ = dict()
    male_by_years = list()
    female_by_years = list()
    for year in _data_:
        male_by_years.append(year[year.Gender == 'M'].Count.sum())
        female_by_years.append(year[year.Gender == 'F'].Count.sum())
    _dyn_data_.update({'M': male_by_years, 'F': female_by_years})
    
    return _dyn_data_


    

In [8]:

    

count_top3(data)


    

    
Out[8]:





['James', 'John', 'Robert']

In [9]:

    

count_dynamics(data)


    

    
Out[9]:





{'F': [299822, 1713450, 1814738], 'M': [150490, 1791474, 1962556]}