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]:
Revenue | State | |
---|---|---|
2012-01-01 | 1.0 | NY |
2012-02-01 | 2.0 | NY |
2012-03-01 | 3.0 | NY |
2012-04-01 | 4.0 | NY |
2012-05-01 | 5.0 | FL |
2012-06-01 | 6.0 | FL |
2012-07-01 | 7.0 | GA |
2012-08-01 | 8.0 | GA |
2012-09-01 | 9.0 | FL |
2012-10-01 | 10.0 | FL |
2013-01-01 | 10.0 | NY |
2013-02-01 | 10.0 | NY |
2013-03-01 | 9.0 | NY |
2013-04-01 | 9.0 | NY |
2013-05-01 | 8.0 | FL |
2013-06-01 | 8.0 | FL |
2013-07-01 | 7.0 | GA |
2013-08-01 | 7.0 | GA |
2013-09-01 | 6.0 | FL |
2013-10-01 | 6.0 | FL |
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]:
Revenue | State | x-Mean | 1.96*std | Outlier | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | 5.75 | 5.200273 | True |
2012-02-01 | 2.0 | NY | 4.75 | 5.200273 | False |
2012-03-01 | 3.0 | NY | 3.75 | 5.200273 | False |
2012-04-01 | 4.0 | NY | 2.75 | 5.200273 | False |
2012-05-01 | 5.0 | FL | 1.75 | 5.200273 | False |
2012-06-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2012-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2012-08-01 | 8.0 | GA | 1.25 | 5.200273 | False |
2012-09-01 | 9.0 | FL | 2.25 | 5.200273 | False |
2012-10-01 | 10.0 | FL | 3.25 | 5.200273 | False |
2013-01-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-02-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-03-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-04-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-05-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-06-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-08-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-09-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2013-10-01 | 6.0 | FL | 0.75 | 5.200273 | False |
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]:
Revenue | State | Outlier | x-Mean | 1.96*std | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | False | 5.00 | 7.554813 |
2012-02-01 | 2.0 | NY | False | 4.00 | 7.554813 |
2012-03-01 | 3.0 | NY | False | 3.00 | 7.554813 |
2012-04-01 | 4.0 | NY | False | 2.00 | 7.554813 |
2012-05-01 | 5.0 | FL | False | 2.25 | 3.434996 |
2012-06-01 | 6.0 | FL | False | 1.25 | 3.434996 |
2012-07-01 | 7.0 | GA | False | 0.25 | 0.980000 |
2012-08-01 | 8.0 | GA | False | 0.75 | 0.980000 |
2012-09-01 | 9.0 | FL | False | 1.75 | 3.434996 |
2012-10-01 | 10.0 | FL | False | 2.75 | 3.434996 |
2013-01-01 | 10.0 | NY | False | 4.00 | 7.554813 |
2013-02-01 | 10.0 | NY | False | 4.00 | 7.554813 |
2013-03-01 | 9.0 | NY | False | 3.00 | 7.554813 |
2013-04-01 | 9.0 | NY | False | 3.00 | 7.554813 |
2013-05-01 | 8.0 | FL | False | 0.75 | 3.434996 |
2013-06-01 | 8.0 | FL | False | 0.75 | 3.434996 |
2013-07-01 | 7.0 | GA | False | 0.25 | 0.980000 |
2013-08-01 | 7.0 | GA | False | 0.25 | 0.980000 |
2013-09-01 | 6.0 | FL | False | 1.25 | 3.434996 |
2013-10-01 | 6.0 | FL | False | 1.25 | 3.434996 |
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]:
Revenue | State | Outlier | x-Mean | 1.96*std | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | False | 4.5 | 12.473364 |
2012-02-01 | 2.0 | NY | False | 4.0 | 11.087434 |
2012-03-01 | 3.0 | NY | False | 3.0 | 8.315576 |
2012-04-01 | 4.0 | NY | False | 2.5 | 6.929646 |
2012-05-01 | 5.0 | FL | False | 1.5 | 4.157788 |
2012-06-01 | 6.0 | FL | False | 1.0 | 2.771859 |
2012-07-01 | 7.0 | GA | False | 0.0 | 0.000000 |
2012-08-01 | 8.0 | GA | False | 0.5 | 1.385929 |
2012-09-01 | 9.0 | FL | False | 1.5 | 4.157788 |
2012-10-01 | 10.0 | FL | False | 2.0 | 5.543717 |
2013-01-01 | 10.0 | NY | False | 4.5 | 12.473364 |
2013-02-01 | 10.0 | NY | False | 4.0 | 11.087434 |
2013-03-01 | 9.0 | NY | False | 3.0 | 8.315576 |
2013-04-01 | 9.0 | NY | False | 2.5 | 6.929646 |
2013-05-01 | 8.0 | FL | False | 1.5 | 4.157788 |
2013-06-01 | 8.0 | FL | False | 1.0 | 2.771859 |
2013-07-01 | 7.0 | GA | False | 0.0 | 0.000000 |
2013-08-01 | 7.0 | GA | False | 0.5 | 1.385929 |
2013-09-01 | 6.0 | FL | False | 1.5 | 4.157788 |
2013-10-01 | 6.0 | FL | False | 2.0 | 5.543717 |
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]:
Revenue | State | x-Mean | 1.96*std | Outlier | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | 5.75 | 5.200273 | True |
2012-02-01 | 2.0 | NY | 4.75 | 5.200273 | False |
2012-03-01 | 3.0 | NY | 3.75 | 5.200273 | False |
2012-04-01 | 4.0 | NY | 2.75 | 5.200273 | False |
2012-05-01 | 5.0 | FL | 1.75 | 5.200273 | False |
2012-06-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2012-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2012-08-01 | 8.0 | GA | 1.25 | 5.200273 | False |
2012-09-01 | 9.0 | FL | 2.25 | 5.200273 | False |
2012-10-01 | 10.0 | FL | 3.25 | 5.200273 | False |
2013-01-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-02-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-03-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-04-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-05-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-06-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-08-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-09-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2013-10-01 | 6.0 | FL | 0.75 | 5.200273 | False |
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]:
Revenue | State | x-Mean | 1.96*std | Outlier | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | 5.75 | 5.200273 | True |
2012-02-01 | 2.0 | NY | 4.75 | 5.200273 | False |
2012-03-01 | 3.0 | NY | 3.75 | 5.200273 | False |
2012-04-01 | 4.0 | NY | 2.75 | 5.200273 | False |
2012-05-01 | 5.0 | FL | 1.75 | 5.200273 | False |
2012-06-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2012-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2012-08-01 | 8.0 | GA | 1.25 | 5.200273 | False |
2012-09-01 | 9.0 | FL | 2.25 | 5.200273 | False |
2012-10-01 | 10.0 | FL | 3.25 | 5.200273 | False |
2013-01-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-02-01 | 10.0 | NY | 3.25 | 5.200273 | False |
2013-03-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-04-01 | 9.0 | NY | 2.25 | 5.200273 | False |
2013-05-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-06-01 | 8.0 | FL | 1.25 | 5.200273 | False |
2013-07-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-08-01 | 7.0 | GA | 0.25 | 5.200273 | False |
2013-09-01 | 6.0 | FL | 0.75 | 5.200273 | False |
2013-10-01 | 6.0 | FL | 0.75 | 5.200273 | False |
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]:
Revenue | State | Lower | Upper | Outlier | |
---|---|---|---|---|---|
2012-01-01 | 1.0 | NY | -7.000 | 19.000 | False |
2012-02-01 | 2.0 | NY | -7.000 | 19.000 | False |
2012-03-01 | 3.0 | NY | -7.000 | 19.000 | False |
2012-04-01 | 4.0 | NY | -7.000 | 19.000 | False |
2012-05-01 | 5.0 | FL | 2.625 | 11.625 | False |
2012-06-01 | 6.0 | FL | 2.625 | 11.625 | False |
2012-07-01 | 7.0 | GA | 6.625 | 7.625 | False |
2012-08-01 | 8.0 | GA | 6.625 | 7.625 | True |
2012-09-01 | 9.0 | FL | 2.625 | 11.625 | False |
2012-10-01 | 10.0 | FL | 2.625 | 11.625 | False |
2013-01-01 | 10.0 | NY | -7.000 | 19.000 | False |
2013-02-01 | 10.0 | NY | -7.000 | 19.000 | False |
2013-03-01 | 9.0 | NY | -7.000 | 19.000 | False |
2013-04-01 | 9.0 | NY | -7.000 | 19.000 | False |
2013-05-01 | 8.0 | FL | 2.625 | 11.625 | False |
2013-06-01 | 8.0 | FL | 2.625 | 11.625 | False |
2013-07-01 | 7.0 | GA | 6.625 | 7.625 | False |
2013-08-01 | 7.0 | GA | 6.625 | 7.625 | False |
2013-09-01 | 6.0 | FL | 2.625 | 11.625 | False |
2013-10-01 | 6.0 | FL | 2.625 | 11.625 | False |