In [1]:
import os
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
source_path = 'D:\Python_my\Python_Netology_homework\data_names'
source_dir_path = os.path.normpath(os.path.abspath(source_path))
def download_year_data(year):
y = year
source_file = os.path.normpath(os.path.join(source_dir_path, 'yob{}.txt'.format(year)))
year_data = pd.read_csv(source_file, names=['Name', 'Gender', 'Count'])
# year_data['Year'] = year_data.apply(lambda x: int(year), axis=1)
year_data = year_data.drop(['Gender'], axis=1)
# print(year_data.query('Name == "Ruth" | Name == "Robert"').groupby('Name').sum())
return year_data.query('Name == ["Ruth", "Robert"]').groupby('Name').sum()
names = []
names_dict = {}
ruth_n_robert_all_time = {}
for i in range(1900, 2001):
names_dict[i] = download_year_data(i)
ruth_n_robert_all_time = pd.concat(names_dict, names=['Year'])
# print(ruth_n_robert_all_time)
print()
# print(ruth_n_robert_all_time.unstack('Name'))
In [2]:
ruth_n_robert_dynamics = ruth_n_robert_all_time.unstack('Name')
ruth_n_robert_dynamics
Out[2]:
In [5]:
ruth_n_robert_dynamics.plot(title='Ruth vs Robert', grid=True)
Out[5]:
In [6]:
ruth_n_robert_dynamics.plot.bar()
Out[6]:
In [5]:
import matplotlib.pyplot as plt
In [6]:
ruth_n_robert_dynamics.plot(title='Ruth vs Robert', grid=True)
Out[6]:
In [4]:
%matplotlib inline
In [8]:
ruth_n_robert_dynamics.plot(title='Ruth vs Robert', grid=True)
Out[8]:
In [9]:
ruth_n_robert_dynamics.plot.bar()
Out[9]:
In [ ]: