import pandas as pd
df = pd.read_csv('result.csv')
df
result = df.groupby(['Year', 'Sex']).sum()
df2019 = pd.read_csv('yob2019.txt', names=['Name', 'Sex', 'Cnt'])
df2019.Cnt.sum()
1665373+1779948
result
result.index.get_level_values(0)
result.index.get_level_values(1)
result.loc[result.index.get_level_values(1) == 'M']
result.loc[ result.index.get_level_values(0).isin(range(1880, 1891)) ]
result.loc[
(result.index.get_level_values(0).isin(range(1880, 1891)))
&
(result.index.get_level_values(1) == 'M')
]
result2 = result.unstack('Sex')
result2
result2.loc[1880][1]
result2.loc[2019].Cnt.F
result2.Cnt
result2
result2.plot()
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 6))
plt.plot(result2.index, result2['Cnt'])
plt.gcf().axes[0].yaxis.get_major_formatter().set_scientific(False)
plt.xticks( range(1880, result2.index.max()+1, 5), rotation='vertical' )
# plt.yticks(range(0, int(round(result2['count'].max()))+5000, 1000))
plt.xlabel('Годы')
plt.ylabel('Кол-во имен')
# for index, value in enumerate(result2['count']):
# plt.text(
# index,
# value,
# value,
# rotation=90,
# size='10',
# color='#000',
# ha='center')
plt.grid()
plt.legend(['Cnt, F', 'Cnt, M'])
# plt.savefig('Count.png', dpi=100)
plt.show()
result2.index.max()