In [1]:
import pandas as pd
from IPython.display import display
In [2]:
States = ['NY', 'NY', 'NY', 'NY', 'FL', 'FL', 'GA', 'GA', 'FL', 'FL']
data = [1.0, 2, 3, 4, 5, 6, 7, 8, 9, 10]
idx = pd.date_range('1/1/2012', periods=10, freq='MS')
df1 = pd.DataFrame(data, index=idx, columns=['Revenue'])
df1['State'] = States
display(df1)
data2 = [10.0, 10.0, 9, 9, 8, 8, 7, 7, 6, 6]
idx2 = pd.date_range('1/1/2013', periods=10, freq='MS')
df2 = pd.DataFrame(data2, index=idx2, columns=['Revenue'])
df2['State'] = States
display(df2)
In [3]:
# Объединение датафреймов
df = pd.concat([df1,df2])
df
Out[3]:
In [4]:
# Вариант 1
newdf = df.copy()
newdf['x-Mean'] = abs(newdf['Revenue'] - newdf['Revenue'].mean())
newdf['1.96*std'] = 1.96*newdf['Revenue'].std()
newdf['Outlier'] = abs(newdf['Revenue'] - newdf['Revenue'].mean()) > 1.96*newdf['Revenue'].std()
newdf
Out[4]:
In [9]:
# Вариант 2
newdf = df.copy()
State = newdf.groupby('State')
def s(group):
group['x-Mean'] = abs(group['Revenue'] - group['Revenue'].mean())
group['1.96*std'] = 1.96*group['Revenue'].std()
group['Outlier'] = abs(group['Revenue'] - group['Revenue'].mean()) > 1.96*group['Revenue'].std()
return group
Newdf2 = State.apply(s)
Newdf2
Out[9]:
In [11]:
State.tail()
Out[11]:
In [13]:
# Сложные преобразования
newdf = df.copy()
State = newdf.groupby('State')
newdf['Lower'] = State['Revenue'].transform( lambda x:
x.quantile(q=.25) - (1.5*(x.quantile(q=.75)-x.quantile(q=.25))) )
newdf['Upper'] = State['Revenue'].transform( lambda x:
x.quantile(q=.75) + (1.5*(x.quantile(q=.75)-x.quantile(q=.25))) )
newdf['Outlier'] = (newdf['Revenue'] < newdf['Lower']) | (newdf['Revenue'] > newdf['Upper'])
newdf
Out[13]:
In [ ]:
In [ ]: