ืืื ืืืืจ!
ืืืึทื ื ืืืจ ืืืขืื ืึทืจืืขืื ืืืืฃ ืื ืกืงืืื ืคืื ื ืืฆื ืืืฉืืจืื ืคึฟืึทืจ ืืจืืคึผืื ื ืืื ืืืืืฉืืืึทืืืืืื ื ืืึทืื ืืื ืคึผืืืืึธื. ืืื ืื ืฆืืืขืฉืืขืื ืืึธืืืจ ืึทื ืึทืืืื ืขืืืขืืข ืงืขืจืึทืงืืขืจืืกืืืงืก ืืื ืืืืขื ืึท ืกืืื ืคืื ืืืืืฉืืืึทืืึทืืืืฉืึทื ื.
ืืืื ืืจืึทืืืฆืืข, ืืื ืื ืึธื ืืืื, ืืึธืื ืืื ืื ืืขืคืื ืืจื ืื ืฆืืื:
- ืืจืืคืข ืืึทืื ืืืื ืืืฉืขื ืืขืจ ืืื ืืึธืจ ืืื ืืืืืฉืืืึทืืืื ืื ืงืืืืขืืืืง ืืื ืึทืืืง ืคืื ืื ืืขืืืจื ืงืืจืก ืคืื ืืืืืข ืกืขืงืกืึทื;
- ืืขืคึฟืื ืขื ืื ืืขืจืกื ืคืึธืืงืก ื ืขืืขื ืคืื ืึทืืข ืืึธื;
- ืืืืื ืื ืืื ืฆืข ืฆืืื ืืื ืื ืืึทืื ืืื 10 ืคึผืึทืจืฅ ืืื ืคึฟืึทืจ ืืขืืขืจ, ืืขืคึฟืื ืขื ืื ืืขืจืกื ืคืึธืืงืก ื ืึธืืขื ืคืื ืืขืืขืจ ืืืฉืขื ืืขืจ. ืคึฟืึทืจ ืืขืืขืจ ื ืึธืืขื ืืขืคืื ืขื, ืืืืืฉืืืึทืืืื ืืืึทื ืืื ืึทืืืง ืืืืขืจ ืึทืืข ืืึธื;
- ืคึฟืึทืจ ืืขืืขืจ ืืึธืจ, ืจืขืืขื ืขื ืืื ืคืืืข ื ืขืืขื ืืขืงื 50% ืคืื ืืขื ืืฉื ืืื ืืืืืฉืืืึทืืืื (ืืืจ ืืืขืื ืืขื ืื ืคืึทืจืฉืืืื ืงืืึทื ืคืื ื ืขืืขื ืคึฟืึทืจ ืืขืืขืจ ืืึธืจ);
- ืืืืกืงืืืึทืื 4 ืืึธืจ ืคืื ืื ืืื ืฆืข ืืขืืึทืืขื ืืื ืืืืึทืื ืคึฟืึทืจ ืืขืืขืจ ืืึธืจ ืื ืคืึทืจืฉืคึผืจืืืืื ื ืืืจื ืืขืจ ืขืจืฉืืขืจ ืืจืืื ืืื ืื ื ืึธืืขื ืืื ืืืจื ืื ืืขืฆืืข ืืจืืื ืืื ืื ื ืึธืืขื;
- ืืึทืื ืึท ืจืฉืืื ืคืื ืขืืืขืืข ืืึทืจืืื ืืขื ืืฉื (ืคึผืจืขืืืืึทื ืฅ, ืืื ืืขืจืก, ืึทืงืืขืจื, ืคึฟืืื ืืืชืืืช) ืืื ืึธืคึผืฉืึทืฆื ืืืืขืจ ืืฉืคึผืขื ืืืืฃ ืื ืืื ืึทืืืง ืคืื ื ืขืืขื. ืืืืขื ืึท ืืืืืฉืืืึทืืึทืืืืฉืึทื.
ืืืืื ืืงืขืจ ืืืขืจืืขืจ, ืืขืจ ืงืึธื!
ืืื, ืืึธืื ืก ืืืื.
ืืึธืืืจ ืืจืืคึผืข ืื ืืึทืื ืืืื ืืืฉืขื ืืขืจ ืืื ืืึธืจ ืืื ืืืืืฉืืืึทืืืื ืื ืงืืืืขืืืืง ืืื ืึทืืืง ืคืื ืื ืืขืืืจื ืงืืจืก ืคืื ืืืืืข ืกืขืงืกืึทื:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
years = np.arange(1880, 2011, 3)
datalist = 'https://raw.githubusercontent.com/wesm/pydata-book/2nd-edition/datasets/babynames/yob{year}.txt'
dataframes = []
for year in years:
dataset = datalist.format(year=year)
dataframe = pd.read_csv(dataset, names=['name', 'sex', 'count'])
dataframes.append(dataframe.assign(year=year))
result = pd.concat(dataframes)
sex = result.groupby('sex')
births_men = sex.get_group('M').groupby('year', as_index=False)
births_women = sex.get_group('F').groupby('year', as_index=False)
births_men_list = births_men.aggregate(np.sum)['count'].tolist()
births_women_list = births_women.aggregate(np.sum)['count'].tolist()
fig, ax = plt.subplots()
fig.set_size_inches(25,15)
index = np.arange(len(years))
stolb1 = ax.bar(index, births_men_list, 0.4, color='c', label='ะัะถัะธะฝั')
stolb2 = ax.bar(index + 0.4, births_women_list, 0.4, alpha=0.8, color='r', label='ะะตะฝัะธะฝั')
ax.set_title('ะ ะพะถะดะฐะตะผะพััั ะฟะพ ะฟะพะปั ะธ ะณะพะดะฐะผ')
ax.set_xlabel('ะะพะดะฐ')
ax.set_ylabel('ะ ะพะถะดะฐะตะผะพััั')
ax.set_xticklabels(years)
ax.set_xticks(index + 0.4)
ax.legend(loc=9)
fig.tight_layout()
plt.show()
ืืึธืืืจ ืืขืคึฟืื ืขื ืื ืืขืจืกื ืคืึธืืงืก ื ืขืืขื ืืื ืืขืฉืืืืข:
years = np.arange(1880, 2011)
dataframes = []
for year in years:
dataset = datalist.format(year=year)
dataframe = pd.read_csv(dataset, names=['name', 'sex', 'count'])
dataframes.append(dataframe)
result = pd.concat(dataframes)
names = result.groupby('name', as_index=False).sum().sort_values('count', ascending=False)
names.head(10)
ืืึธืืืจ ืฆืขืืืืื ืื ืืื ืฆืข ืฆืืื ืืื ืื ืืึทืื ืืื 10 ืคึผืึทืจืฅ ืืื ืคึฟืึทืจ ืืขืืขืจ ืืืจ ืืืขืื ืืขืคึฟืื ืขื ืื ืืขืจืกื ืคืึธืืงืก ื ืึธืืขื ืคืื ืืขืืขืจ ืืืฉืขื ืืขืจ. ืคึฟืึทืจ ืืขืืขืจ ื ืึธืืขื ืืขืคึฟืื ืขื, ืืืจ ืืืืืฉืืืึทืืืื ืืืื ืืื ืึทืืืง ืืืืขืจ ืึทืืข ืฆืืื:
years = np.arange(1880, 2011)
part_size = int((years[years.size - 1] - years[0]) / 10) + 1
parts = {}
def GetPart(year):
return int((year - years[0]) / part_size)
for year in years:
index = GetPart(year)
r = years[0] + part_size * index, min(years[years.size - 1], years[0] + part_size * (index + 1))
parts[index] = str(r[0]) + '-' + str(r[1])
dataframe_parts = []
dataframes = []
for year in years:
dataset = datalist.format(year=year)
dataframe = pd.read_csv(dataset, names=['name', 'sex', 'count'])
dataframe_parts.append(dataframe.assign(years=parts[GetPart(year)]))
dataframes.append(dataframe.assign(year=year))
result_parts = pd.concat(dataframe_parts)
result = pd.concat(dataframes)
result_parts_sums = result_parts.groupby(['years', 'sex', 'name'], as_index=False).sum()
result_parts_names = result_parts_sums.iloc[result_parts_sums.groupby(['years', 'sex'], as_index=False).apply(lambda x: x['count'].idxmax())]
result_sums = result.groupby(['year', 'sex', 'name'], as_index=False).sum()
for groupName, groupLabels in result_parts_names.groupby(['name', 'sex']).groups.items():
group = result_sums.groupby(['name', 'sex']).get_group(groupName)
fig, ax = plt.subplots(1, 1, figsize=(18,10))
ax.set_xlabel('ะะพะดะฐ')
ax.set_ylabel('ะ ะพะถะดะฐะตะผะพััั')
label = group['name']
ax.plot(group['year'], group['count'], label=label.aggregate(np.max), color='b', ls='-')
ax.legend(loc=9, fontsize=11)
plt.show()
ืคึฟืึทืจ ืืขืืขืจ ืืึธืจ, ืืืจ ืจืขืืขื ืขื ืืื ืคืืืข ื ืขืืขื ืืขืงื 50% ืคืื ืืขื ืืฉื ืืื ืืืืืฉืืืึทืืืื ืื ืืึทืื:
dataframe = pd.DataFrame({'year': [], 'count': []})
years = np.arange(1880, 2011)
for year in years:
dataset = datalist.format(year=year)
csv = pd.read_csv(dataset, names=['name', 'sex', 'count'])
names = csv.groupby('name', as_index=False).aggregate(np.sum)
names['sum'] = names.sum()['count']
names['percent'] = names['count'] / names['sum'] * 100
names = names.sort_values(['percent'], ascending=False)
names['cum_perc'] = names['percent'].cumsum()
names_filtered = names[names['cum_perc'] <= 50]
dataframe = dataframe.append(pd.DataFrame({'year': [year], 'count': [names_filtered.shape[0]]}))
fig, ax1 = plt.subplots(1, 1, figsize=(22,13))
ax1.set_xlabel('ะะพะดะฐ', fontsize = 12)
ax1.set_ylabel('ะ ะฐะทะฝะพะพะฑัะฐะทะธะต ะธะผะตะฝ', fontsize = 12)
ax1.plot(dataframe['year'], dataframe['count'], color='r', ls='-')
ax1.legend(loc=9, fontsize=12)
plt.show()
ืืึธืืืจ ืืืืกืงืืืึทืื 4 ืืึธืจ ืคืื ืื ืืื ืฆืข ืืขืืึทืืขื ืืื ืืืืึทืื ืคึฟืึทืจ ืืขืืขืจ ืืึธืจ ืื ืคืึทืจืฉืคึผืจืืืืื ื ืืืจื ืืขืจ ืขืจืฉืืขืจ ืืจืืื ืืื ืืขื ื ืึธืืขื ืืื ืืืจื ืื ืืขืฆืืข ืืจืืื ืืื ืืขื ื ืึธืืขื:
from string import ascii_lowercase, ascii_uppercase
fig_first, ax_first = plt.subplots(1, 1, figsize=(14,10))
fig_last, ax_last = plt.subplots(1, 1, figsize=(14,10))
index = np.arange(len(ascii_uppercase))
years = [1944, 1978, 1991, 2003]
colors = ['r', 'g', 'b', 'y']
n = 0
for year in years:
dataset = datalist.format(year=year)
csv = pd.read_csv(dataset, names=['name', 'sex', 'count'])
names = csv.groupby('name', as_index=False).aggregate(np.sum)
count = names.shape[0]
dataframe = pd.DataFrame({'letter': [], 'frequency_first': [], 'frequency_last': []})
for letter in ascii_uppercase:
countFirst = (names[names.name.str.startswith(letter)].count()['count'])
countLast = (names[names.name.str.endswith(letter.lower())].count()['count'])
dataframe = dataframe.append(pd.DataFrame({
'letter': [letter],
'frequency_first': [countFirst / count * 100],
'frequency_last': [countLast / count * 100]}))
ax_first.bar(index + 0.3 * n, dataframe['frequency_first'], 0.3, alpha=0.5, color=colors[n], label=year)
ax_last.bar(index + bar_width * n, dataframe['frequency_last'], 0.3, alpha=0.5, color=colors[n], label=year)
n += 1
ax_first.set_xlabel('ะัะบะฒะฐ ะฐะปัะฐะฒะธัะฐ')
ax_first.set_ylabel('ะงะฐััะพัะฐ, %')
ax_first.set_title('ะะตัะฒะฐั ะฑัะบะฒะฐ ะฒ ะธะผะตะฝะธ')
ax_first.set_xticks(index)
ax_first.set_xticklabels(ascii_uppercase)
ax_first.legend()
ax_last.set_xlabel('ะัะบะฒะฐ ะฐะปัะฐะฒะธัะฐ')
ax_last.set_ylabel('ะงะฐััะพัะฐ, %')
ax_last.set_title('ะะพัะปะตะดะฝัั ะฑัะบะฒะฐ ะฒ ะธะผะตะฝะธ')
ax_last.set_xticks(index)
ax_last.set_xticklabels(ascii_uppercase)
ax_last.legend()
fig_first.tight_layout()
fig_last.tight_layout()
plt.show()
ืืึธืืืจ ืืึทืื ืึท ืจืฉืืื ืคืื ืขืืืขืืข ืืึทืจืืื ืืขื ืืฉื (ืคึผืจืขืืืืึทื ืฅ, ืืื ืืขืจืก, ืึทืงืืขืจื, ืคึฟืืื ืืืชืืืช) ืืื ืึธืคึผืฉืึทืฆื ืืืืขืจ ืืฉืคึผืขื ืืืืฃ ืื ืืื ืึทืืืง ืคืื ื ืขืืขื:
celebrities = {'Frank': 'M', 'Britney': 'F', 'Madonna': 'F', 'Bob': 'M'}
dataframes = []
for year in years:
dataset = datalist.format(year=year)
dataframe = pd.read_csv(dataset, names=['name', 'sex', 'count'])
dataframes.append(dataframe.assign(year=year))
result = pd.concat(dataframes)
for celebrity, sex in celebrities.items():
names = result[result.name == celebrity]
dataframe = names[names.sex == sex]
fig, ax = plt.subplots(1, 1, figsize=(16,8))
ax.set_xlabel('ะะพะดะฐ', fontsize = 10)
ax.set_ylabel('ะ ะพะถะดะฐะตะผะพััั', fontsize = 10)
ax.plot(dataframe['year'], dataframe['count'], label=celebrity, color='r', ls='-')
ax.legend(loc=9, fontsize=12)
plt.show()
ืคึฟืึทืจ ืืจืืื ืื ื, ืืืจ ืงืขื ืขื ืืืืื ืื ืืขืื ืคืื ืื ืจืื ืฆื ืื ืืืืืฉืืืึทืืึทืืืืฉืึทื ืคืื ืื ืืขืฆืืข ืืืืฉืคึผืื ืฆื ืงืืืจ ืึทืกืกืขืกืก ืืืืขืจ ืืฉืคึผืขื ืืืืฃ ืื ืืื ืึทืืืง ืคืื ื ืขืืขื.
ืืื ืืขื ืืขื ืขื ืึทืืข ืืื ืืืขืจืข ืฆืืื ืืขืจืืจืืืื ืืื ืืงืืื ืืขืืืขื. ืืืจ ืืึธืื ืืขืืืขืืึธืคึผืขื ืื ืกืงืืื ืคืื ื ืืฆื ืืืฉืืจืื ืคึฟืึทืจ ืืจืืคึผืื ื ืืื ืืืืืฉืืืึทืืืืืื ื ืืึทืื ืืื ืคึผืืืืึธื, ืืื ืืืจ ืืืขืื ืคืึธืจืืขืฆื ืฆื ืึทืจืืขืื ืืื ืืึทืื. ืึทืืขืืขื ืงืขื ืขื ืฆืืขื ืงืึทื ืงืืืืฉืึทื ื ืืืืืจื ืืืืฃ ืคืึทืจืืืง, ืืืืืฉืืืึทืืืืื ืืึทืื ืืื.
ืืืืกื ืฆื ืึทืืขืืขื!
ืืงืืจ: www.habr.com