Habari Habr!
Leo tutafanya kazi juu ya ustadi wa kutumia zana za vikundi vya data na taswira katika Python. Katika zinazotolewa
Kwa jadi, mwanzoni, tunafafanua malengo:
- Data ya kikundi kwa jinsia na mwaka na kuibua mienendo ya jumla ya kiwango cha kuzaliwa kwa jinsia zote mbili;
- Pata majina maarufu zaidi katika historia;
- Gawanya kipindi chote cha muda katika data katika sehemu 10 na kwa kila tafuta jina maarufu zaidi la kila jinsia. Kwa kila jina lililopatikana, taswira mienendo yake kwa wakati;
- Kwa kila mwaka, hesabu ni majina ngapi yanajumuishwa na 50% ya watu na taswira (tutaona aina mbalimbali za majina kwa kila mwaka);
- Chagua miaka 4 kutoka kwa muda wa jumla na uonyeshe kwa kila mwaka usambazaji kwa herufi ya kwanza kwa jina na kwa herufi ya mwisho kwa jina;
- Tengeneza orodha ya watu kadhaa maarufu (marais, waimbaji, waigizaji, mashujaa wa sinema) na tathmini ushawishi wao juu ya mienendo ya majina. Jenga taswira.
Maneno machache, kanuni zaidi!
Hebu tupange data kulingana na jinsia na mwaka na tuone taswira ya mienendo ya jumla ya kiwango cha kuzaliwa kwa jinsia zote mbili:
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='ΠΡΠΆΡΠΈΠ½Ρ')
stolb2 = ax.bar(index + 0.4, births_women_list, 0.4, alpha=0.8, color='r', label='ΠΠ΅Π½ΡΠΈΠ½Ρ')
ax.set_title('Π ΠΎΠΆΠ΄Π°Π΅ΠΌΠΎΡΡΡ ΠΏΠΎ ΠΏΠΎΠ»Ρ ΠΈ Π³ΠΎΠ΄Π°ΠΌ')
ax.set_xlabel('ΠΠΎΠ΄Π°')
ax.set_ylabel('Π ΠΎΠΆΠ΄Π°Π΅ΠΌΠΎΡΡΡ')
ax.set_xticklabels(years)
ax.set_xticks(index + 0.4)
ax.legend(loc=9)
fig.tight_layout()
plt.show()
Wacha tupate majina maarufu zaidi katika historia:
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)
Hebu tugawanye kipindi chote cha muda katika data katika sehemu 10 na kwa kila moja tunapata jina maarufu zaidi la kila jinsia. Kwa kila jina lililopatikana, tunaona mienendo yake kwa wakati wote:
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('ΠΠΎΠ΄Π°')
ax.set_ylabel('Π ΠΎΠΆΠ΄Π°Π΅ΠΌΠΎΡΡΡ')
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()
Kwa kila mwaka, tunakokotoa ni majina mangapi yanajumuishwa na 50% ya watu na kuibua data hii:
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('ΠΠΎΠ΄Π°', fontsize = 12)
ax1.set_ylabel('Π Π°Π·Π½ΠΎΠΎΠ±ΡΠ°Π·ΠΈΠ΅ ΠΈΠΌΠ΅Π½', fontsize = 12)
ax1.plot(dataframe['year'], dataframe['count'], color='r', ls='-')
ax1.legend(loc=9, fontsize=12)
plt.show()
Wacha tuchague miaka 4 kutoka kwa muda wote na kuonyesha kwa kila mwaka usambazaji kwa herufi ya kwanza kwa jina na herufi ya mwisho kwa jina:
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('ΠΡΠΊΠ²Π° Π°Π»ΡΠ°Π²ΠΈΡΠ°')
ax_first.set_ylabel('Π§Π°ΡΡΠΎΡΠ°, %')
ax_first.set_title('ΠΠ΅ΡΠ²Π°Ρ Π±ΡΠΊΠ²Π° Π² ΠΈΠΌΠ΅Π½ΠΈ')
ax_first.set_xticks(index)
ax_first.set_xticklabels(ascii_uppercase)
ax_first.legend()
ax_last.set_xlabel('ΠΡΠΊΠ²Π° Π°Π»ΡΠ°Π²ΠΈΡΠ°')
ax_last.set_ylabel('Π§Π°ΡΡΠΎΡΠ°, %')
ax_last.set_title('ΠΠΎΡΠ»Π΅Π΄Π½ΡΡ Π±ΡΠΊΠ²Π° Π² ΠΈΠΌΠ΅Π½ΠΈ')
ax_last.set_xticks(index)
ax_last.set_xticklabels(ascii_uppercase)
ax_last.legend()
fig_first.tight_layout()
fig_last.tight_layout()
plt.show()
Wacha tufanye orodha ya watu kadhaa maarufu (marais, waimbaji, waigizaji, mashujaa wa sinema) na tutathmini ushawishi wao juu ya mienendo ya majina:
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('ΠΠΎΠ΄Π°', fontsize = 10)
ax.set_ylabel('Π ΠΎΠΆΠ΄Π°Π΅ΠΌΠΎΡΡΡ', fontsize = 10)
ax.plot(dataframe['year'], dataframe['count'], label=celebrity, color='r', ls='-')
ax.legend(loc=9, fontsize=12)
plt.show()
Kwa mazoezi, unaweza kuongeza kipindi cha maisha ya mtu Mashuhuri kwa taswira kutoka kwa mfano wa mwisho ili kutathmini ushawishi wao kwenye mienendo ya majina.
Juu ya hili, malengo yetu yote yalifikiwa na kutimizwa. Tumefahamu matumizi ya zana za kupanga data na taswira katika Python, na tutafanya kazi na data zaidi. Kila mtu anaweza kufikia hitimisho juu ya data iliyopangwa tayari, iliyoonyeshwa.
Maarifa yote!
Chanzo: mapenzi.com