Hai Habr!
A yau za mu yi aiki kan ƙwarewar amfani da kayan aiki don haɗawa da hangen nesa bayanai a cikin Python. A cikin abin da aka bayar
Bisa ga al'ada, a farkon, bari mu ayyana manufofin:
- Ƙungiya bayanai ta jinsi da shekara da kuma hango yanayin gaba ɗaya na adadin haihuwar jinsin biyu;
- Nemo shahararrun sunaye na kowane lokaci;
- Raba duk tsawon lokacin a cikin bayanan zuwa sassa 10 kuma ga kowane, nemo mafi shaharar sunan kowane jinsi. Ga kowane suna da aka samo, duba yanayin yanayinsa a kowane lokaci;
- A kowace shekara, ƙididdige sunaye nawa ke rufe kashi 50% na mutane kuma ku gani (za mu ga ire-iren sunaye na kowace shekara);
- Zaɓi shekaru 4 daga duka tazara kuma nuni ga kowace shekara rarraba ta harafin farko a cikin suna da ta harafin ƙarshe a cikin sunan;
- Yi jerin shahararrun mutane da yawa (shugabannin ƙasa, mawaƙa, ƴan wasan kwaikwayo, jaruman fina-finai) da kuma kimanta tasirinsu akan tasirin sunaye. Gina gani.
Ƙananan kalmomi, ƙarin lamba!
Bari mu tara bayanan ta jinsi da shekara kuma mu hango yanayin gaba ɗaya na adadin haihuwar jinsin biyu:
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='Мужчины')
stolb2 = ax.bar(index + 0.4, births_women_list, 0.4, alpha=0.8, color='r', label='Женщины')
ax.set_title('Рождаемость по полу и годам')
ax.set_xlabel('Года')
ax.set_ylabel('Рождаемость')
ax.set_xticklabels(years)
ax.set_xticks(index + 0.4)
ax.legend(loc=9)
fig.tight_layout()
plt.show()
Mu nemo fitattun sunaye a tarihi:
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)
Bari mu raba duk tsawon lokaci a cikin bayanan zuwa sassa 10 kuma ga kowane za mu sami mafi shaharar sunan kowane jinsi. Ga kowane suna da aka samo, muna ganin yanayinsa a kowane lokaci:
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('Года')
ax.set_ylabel('Рождаемость')
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()
A kowace shekara, muna ƙididdige sunaye nawa ne ke rufe kashi 50% na mutane kuma mu hango wannan bayanan:
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('Года', fontsize = 12)
ax1.set_ylabel('Разнообразие имен', fontsize = 12)
ax1.plot(dataframe['year'], dataframe['count'], color='r', ls='-')
ax1.legend(loc=9, fontsize=12)
plt.show()
Bari mu zaɓi shekaru 4 daga duka tazara kuma mu nuna kowace shekara rarraba ta harafin farko a cikin suna da ta harafin ƙarshe a cikin sunan:
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('Буква алфавита')
ax_first.set_ylabel('Частота, %')
ax_first.set_title('Первая буква в имени')
ax_first.set_xticks(index)
ax_first.set_xticklabels(ascii_uppercase)
ax_first.legend()
ax_last.set_xlabel('Буква алфавита')
ax_last.set_ylabel('Частота, %')
ax_last.set_title('Последняя буква в имени')
ax_last.set_xticks(index)
ax_last.set_xticklabels(ascii_uppercase)
ax_last.legend()
fig_first.tight_layout()
fig_last.tight_layout()
plt.show()
Bari mu yi jerin shahararrun mutane da yawa (shugabannin kasa, mawaƙa, 'yan wasan kwaikwayo, jaruman fina-finai) da kuma kimanta tasirin su akan tasirin sunaye:
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('Года', fontsize = 10)
ax.set_ylabel('Рождаемость', fontsize = 10)
ax.plot(dataframe['year'], dataframe['count'], label=celebrity, color='r', ls='-')
ax.legend(loc=9, fontsize=12)
plt.show()
Don horarwa, zaku iya ƙara lokacin rayuwar mashahuran zuwa ga gani daga misali na ƙarshe don tantance tasirinsu a sarari akan tasirin sunaye.
Da wannan ne aka cim ma burinmu kuma aka cika su. Mun haɓaka ƙwarewar yin amfani da kayan aiki don haɗawa da hangen nesa bayanai a cikin Python, kuma za mu ci gaba da aiki tare da bayanai. Kowane mutum na iya yanke shawara bisa shirye-shiryen da aka yi, bayanan da aka gani da kansu.
Ilimi ga kowa da kowa!
source: www.habr.com