Ways to calculate outliers in Python Pandas Module. The following code shows how to calculate outliers of DataFrame using pandas module.

In [1]:

import pandas as pd
import sys

In [4]:

# Create a dataframe with dates as your index
States = ['NY', 'NY', 'NY', 'NY', 'FL', 'FL', 'GA', 'GA', 'FL', 'FL'] 
data = [1.0, 2, 3, 4, 5, 6, 7, 8, 9, 10]

index = pd.date_range('1/1/2012', periods=10, freq='MS')
data_frame_1 = pd.DataFrame(data=data, index=index, columns=['Revenue'])
data_frame_1['State'] = States

# Create a second dataframe
data2 = [10.0, 10.0, 9, 9, 8, 8, 7, 7, 6, 6]
index2 = pd.date_range('1/1/2013', periods=10, freq='MS')
data_frame_2 = pd.DataFrame(data2, index=index2, columns=['Revenue'])
data_frame_2['State'] = States

In [5]:

new_data_frame = pd.concat([data_frame_1, data_frame_2])
new_data_frame

Out[5]:

Calculate Outlier:

Method 1:

In [7]:

newdf = new_data_frame.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[7]:

Method 2:

In [12]:

newdf = new_data_frame.copy()

State = newdf.groupby('State')

newdf['Outlier'] = State.transform(lambda x: abs(x-x.mean()) > 1.96*x.std())
newdf['x-Mean'] = State.transform(lambda x: abs(x - x.mean()))
newdf['1.96*std'] = State.transform(lambda x: 1.96*x.std())

newdf

Out[12]:

In [15]:

newdf = new_data_frame.copy()

StateMonth = newdf.groupby(['State', lambda x: x.month])

newdf['Outlier'] = StateMonth.transform( lambda x: abs(x-x.mean()) > 1.96*x.std() )
newdf['x-Mean'] = StateMonth.transform( lambda x: abs(x-x.mean()) )
newdf['1.96*std'] = StateMonth.transform( lambda x: 1.96*x.std() )
newdf

Out[15]:

In [10]:

newdf = new_data_frame.copy()

State = newdf.groupby('State')

def s(group):
    group['x-Mean'] = abs(newdf['Revenue'] - newdf['Revenue'].mean())
    group['1.96*std'] = 1.96*newdf['Revenue'].std()
    group['Outlier'] = abs(newdf['Revenue'] - newdf['Revenue'].mean()) > 1.96*newdf['Revenue'].std()
    return group
    
newdf2 = State.apply(s)
newdf2

Out[10]:

In [16]:

newdf = new_data_frame.copy()

State = newdf.groupby(['State', lambda x: x.month])

def s(group):
    group['x-Mean'] = abs(newdf['Revenue'] - newdf['Revenue'].mean())
    group['1.96*std'] = 1.96*newdf['Revenue'].std()
    group['Outlier'] = abs(newdf['Revenue'] - newdf['Revenue'].mean()) > 1.96*newdf['Revenue'].std()
    return group
    
newdf2 = State.apply(s)
newdf2

Out[16]:

In [17]:

newdf = new_data_frame.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[17]: