ํค์ด ํ๋ธ๋ฅด!
์ค๋ ์ฐ๋ฆฌ๋ Python์์ ๋ฐ์ดํฐ ๊ทธ๋ฃนํ ๋ฐ ์๊ฐํ ๋๊ตฌ๋ฅผ ์ฌ์ฉํ๋ ๊ธฐ์ ์ ๋ํด ์์
ํ ๊ฒ์
๋๋ค. ์ ๊ณต๋
์ ํต์ ์ผ๋ก ์ฒ์์๋ ๋ชฉํ๋ฅผ ์ ์ํฉ๋๋ค.
- ์ฑ๋ณ ๋ฐ ์ฐ๋๋ณ๋ก ๋ฐ์ดํฐ๋ฅผ ๊ทธ๋ฃนํํ๊ณ ๋จ๋ ์ถ์๋ฅ ์ ์ ๋ฐ์ ์ธ ์ญํ์ ์๊ฐํํฉ๋๋ค.
- ์ญ์ฌ์ ๊ฐ์ฅ ์ธ๊ธฐ ์๋ ์ด๋ฆ์ ์ฐพ์ผ์ญ์์ค.
- ๋ฐ์ดํฐ์ ์ ์ฒด ๊ธฐ๊ฐ์ 10๊ฐ ๋ถ๋ถ์ผ๋ก ๋๋๊ณ ๊ฐ ๋ถ๋ถ์ ๋ํด ๊ฐ ์ฑ๋ณ์์ ๊ฐ์ฅ ์ธ๊ธฐ ์๋ ์ด๋ฆ์ ์ฐพ์ต๋๋ค. ๋ฐ๊ฒฌ๋ ๊ฐ ์ด๋ฆ์ ๋ํด ์๊ฐ ๊ฒฝ๊ณผ์ ๋ฐ๋ฅธ ์ญํ์ ์๊ฐํํฉ๋๋ค.
- ๋งค๋ ์ธ๊ตฌ์ 50%๊ฐ ์ปค๋ฒํ๋ ์ด๋ฆ์ด ๋ช ๊ฐ์ธ์ง ๊ณ์ฐํ๊ณ ์๊ฐํํฉ๋๋ค(๊ฐ ์ฐ๋์ ๋ค์ํ ์ด๋ฆ์ด ํ์๋จ).
- ์ด ๊ฐ๊ฒฉ์์ 4๋ ์ ์ ํํ๊ณ ๊ฐ ์ฐ๋์ ๋ํด ์ด๋ฆ์ ์ฒซ ๊ธ์์ ์ด๋ฆ์ ๋ง์ง๋ง ๊ธ์๋ก ๋ถํฌ๋ฅผ ํ์ํฉ๋๋ค.
- ๋ช๋ช ์ ๋ช ํ ์ฌ๋๋ค(๋ํต๋ น, ๊ฐ์, ๋ฐฐ์ฐ, ์ํ ์์ )์ ๋ชฉ๋ก์ ๋ง๋ค๊ณ ์ด๋ฆ์ ์ญํ์ ๋ฏธ์น๋ ์ํฅ์ ํ๊ฐํฉ๋๋ค. ์๊ฐํ ๊ตฌ์ถ.
๋ ์ ์ ๋จ์ด, ๋ ๋ง์ ์ฝ๋!
์ฑ๋ณ๊ณผ ์ฐ๋๋ณ๋ก ๋ฐ์ดํฐ๋ฅผ ๊ทธ๋ฃนํํ๊ณ ๋จ๋ ์ถ์๋ฅ ์ ์ ๋ฐ์ ์ธ ์ญํ์ ์๊ฐํํด ๋ณด๊ฒ ์ต๋๋ค.
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()
์ญ์ฌ์ ๊ฐ์ฅ ์ ๋ช ํ ์ด๋ฆ์ ์ฐพ์๋ด ์๋ค.
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)
๋ฐ์ดํฐ์ ์ ์ฒด ๊ธฐ๊ฐ์ 10๊ฐ ๋ถ๋ถ์ผ๋ก ๋๋๊ณ ๊ฐ ๋ถ๋ถ์ ๋ํด ๊ฐ ์ฑ๋ณ์์ ๊ฐ์ฅ ์ธ๊ธฐ ์๋ ์ด๋ฆ์ ์ฐพ์ต๋๋ค. ๋ฐ๊ฒฌ๋ ๊ฐ ์ด๋ฆ์ ๋ํด ์ ์ฒด ์๊ฐ ๋์์ ์ญํ์ ์๊ฐํํฉ๋๋ค.
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()
๋งค๋ ์ฐ๋ฆฌ๋ ์ฌ๋๋ค์ 50%๊ฐ ์ปค๋ฒํ๋ ์ด๋ฆ์ ์๋ฅผ ๊ณ์ฐํ๊ณ ์ด ๋ฐ์ดํฐ๋ฅผ ์๊ฐํํฉ๋๋ค.
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()
์ ์ฒด ๊ฐ๊ฒฉ์์ 4๋ ์ ์ ํํ๊ณ ๊ฐ ์ฐ๋์ ๋ํด ์ด๋ฆ์ ์ฒซ ๊ธ์์ ์ด๋ฆ์ ๋ง์ง๋ง ๊ธ์๋ก ๋ถํฌ๋ฅผ ํ์ํด ๋ณด๊ฒ ์ต๋๋ค.
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()
๋ช๋ช ์ ๋ช ํ ์ฌ๋๋ค(๋ํต๋ น, ๊ฐ์, ๋ฐฐ์ฐ, ์ํ ์์ )์ ๋ชฉ๋ก์ ๋ง๋ค๊ณ ์ด๋ฆ์ ์ญํ์ ๋ฏธ์น๋ ์ํฅ์ ํ๊ฐํด ๋ด ์๋ค.
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()
์ฐ์ต์ ์ํด ์ด๋ฆ์ ์ญํ์ ๋ฏธ์น๋ ์ํฅ์ ์๊ฐ์ ์ผ๋ก ํ๊ฐํ๊ธฐ ์ํด ๋ง์ง๋ง ์์ ์๊ฐํ์ ์ ๋ช
์ธ์ ์์ ๊ธฐ๊ฐ์ ์ถ๊ฐํ ์ ์์ต๋๋ค.
์ด์ ์ฐ๋ฆฌ์ ๋ชจ๋ ๋ชฉํ๊ฐ ๋ฌ์ฑ๋๊ณ ๋ฌ์ฑ๋์์ต๋๋ค. ์ฐ๋ฆฌ๋ Python์์ ๋ฐ์ดํฐ ๊ทธ๋ฃนํ ๋ฐ ์๊ฐํ ๋๊ตฌ ์ฌ์ฉ์ ๋ง์คํฐํ์ผ๋ฉฐ ๋ฐ์ดํฐ๋ก ๋ ๋ง์ ์์ ์ ํ ๊ฒ์ ๋๋ค. ๋๊ตฌ๋ ๋ฏธ๋ฆฌ ๋ง๋ค์ด์ง ์๊ฐํ๋ ๋ฐ์ดํฐ์์ ๊ฒฐ๋ก ์ ๋ด๋ฆด ์ ์์ต๋๋ค.
๋ชจ๋ ์ง์!
์ถ์ฒ : habr.com