def remove_duplicate_words(s):
from pandas import Series as sr
array=s.split(' ')
s=sr(array).drop_duplicates(keep='first')
print(' '.join(s))
from pandas import Series as sr
week1 = sr([290000, 310000], index=['토', '일'])
print(week1)
print('-' * 40)
week2 = sr([120000, 220000], index=['일', '토'])
print(week1)
print('-' * 40)
# 시리즈 객체의 사칙연산
# -> index가 동일한 항목끼리 연산이 수행된다.
result = week1 + week2
print(result)
print(type(result))
print('-' * 40)
from pandas import Series as sr items = 10, 30, 50, 70, 90 column = sr(items) print(column) print(type(column))
import pandas as pd
import numpy as np
from pandas import Series as sr
from pandas import DataFrame as frm
dict1 = {
'name': ['taukir', 'khan', 'mango', 'rahul'],
'country': ['India', 'canada', 'U.S', 'Europ'],
'salary': [251000, 256000, 14055, 18900]
}
df = frm(dict1)
df['dep'] = ['Developer', 'engineer', 'Designer', 'BDm']
#print df
#>>>>>>>>>>>>>>>>>>>Qa 2 >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
s1 = sr('aa bb cc dd ee'.split())
df2 = frm(s1)
#print df2
#>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
s2 = sr('aa bb cc dd ee'.split())
s2.name = 'Series'
df3 = frm(s2)
#print df3
#>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
nparr = np.zeros((5, 5))
#print nparr
print "==============================="
npDataFrame = frm(nparr)
#print npDataFrame
npDataFrame.columns = ["First", "Second", "Third", "Fourth", "Fifth"]
#print "==============================="
import pandas as pd
from pandas import Series as sr
print pd.__version__
l1 = [10, 203, 55, 30, 60]
s1 = sr(l1)
print s1
#===First two element
print s1[0]
print s1[1]
s1.index = list('abcde')
print s1
dict1 = dict(apple=100, mango=200, orange=500, grapes=600)
sr1 = sr(dict1)
print sr1
import numpy as np
import pandas as pd
from pandas import Series as sr, DataFrame as df
import matplotlib.pyplot as plt
#matplotlib的一个高级接口
import seaborn as sns
datas = pd.read_excel('data/data.xls')
# print(data.head())
sr1 = sr(datas.view_price)
sr2 = sr(datas.sales)
index = np.arange(sr1.size)
sr3 = sr(sr1 * sr2)
data = df(data=list(zip(sr1, sr2, sr3)),
index=index,
columns=["price", "sales", "GMV"])
datan = df(data=list(zip(sr1, sr3)), index=index, columns=["price", "GMV"])
# print(datan)
data = data.groupby("price").sum()
data.reset_index()
#绘图
# plt.figure(figsize=(6,12))
plt.bar(data.index, np.log(data["sales"]), color='pink')
plt.show()
'''
mean, cov = [4, 6], [(1.5, .7), (.7, 1)]
x, y = np.random.multivariate_normal(mean, cov, 80).T
sns.regplot(x=x, y=y, color="g", marker="+")
'''
from pandas import Series as sr from pandas import date_range as dr items = 10, 20, 30, 40, 50 s1 = dr(start='2020/1/1', periods=5) column = sr(items, s1) print(column)
