PYTHON

remove outliers python pandas

#------------------------------------------------------------------------------
# accept a dataframe, remove outliers, return cleaned data in a new dataframe
# see http://www.itl.nist.gov/div898/handbook/prc/section1/prc16.htm
#------------------------------------------------------------------------------
def remove_outlier(df_in, col_name):
    q1 = df_in[col_name].quantile(0.25)
    q3 = df_in[col_name].quantile(0.75)
    iqr = q3-q1 #Interquartile range
    fence_low  = q1-1.5*iqr
    fence_high = q3+1.5*iqr
    df_out = df_in.loc[(df_in[col_name] > fence_low) & (df_in[col_name] < fence_high)]
    return df_out

remove outliers in dataframe

# Solution is based on this article: 
# http://www.itl.nist.gov/div898/handbook/prc/section1/prc16.htm

import pandas as pd
import numpy as np

def remove_outliers_from_series(series):
    q1 = series.quantile(0.25)
    q3 = series.quantile(0.75)
    intraquartile_range = q3 - q1
    fence_low  = q1 - 1.5 * intraquartile_range
    fence_high = q3 + 1.5 * intraquartile_range
    return series[(series > fence_low) & (series < fence_high)]


def remove_outliers_from_dataframe(self, df, col):
    q1 = df[col].quantile(0.25)
    q3 = df[col].quantile(0.75)
    intraquartile_range = q3 - q1
    fence_low  = q1 - 1.5 * intraquartile_range
    fence_high = q3 + 1.5 * intraquartile_range
    return df.loc[(df[col] > fence_low) & (df[col] < fence_high)]


def remove_outliers_from_np_array(self, arr):
    q1 = np.percentile(arr, 25)
    q3 = np.percentile(arr, 75)
    intraquartile_range = q3 - q1
    fence_low  = q1 - 1.5 * intraquartile_range
    fence_high = q3 + 1.5 * intraquartile_range
    return arr[(arr > fence_low) & (arr < fence_high)]


def remove_outliers_from_python_list(self, _list):
    arr = np.array(_list)
    return list(remove_outliers_from_np_array(arr))


def remove_outliers(*args, **kwargs):
        if isinstance(args[0], pd.DataFrame):
            return remove_outliers_from_dataframe(*args, **kwargs)
        elif isinstance(args[0], pd.Series):
            return remove_outliers_from_series(*args, **kwargs)
        elif isinstance(args[0], np.ndarray):
            return remove_outliers_from_np_array(*args, **kwargs)
        elif isinstance(args[0], list):
            return remove_outliers_from_python_list(*args, **kwargs)
        else:
            raise TypeError(f'{type(args[0])} is not supported.')

remove outliers python dataframe

cols = ['col_1', 'col_2'] # one or more

Q1 = df[cols].quantile(0.25)
Q3 = df[cols].quantile(0.75)
IQR = Q3 - Q1

df = df[~((df[cols] < (Q1 - 1.5 * IQR)) |(df[cols] > (Q3 + 1.5 * IQR))).any(axis=1)]

outliers removal pandas

df = pd.DataFrame(np.random.randn(100, 3))

from scipy import stats
df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]

pandas remove outliers

df = pd.DataFrame(np.random.randn(100, 3))

from scipy import stats
df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]

pandas removing outliers from dataframe

df[(df["col"] >= x ) & (df["col"] <= y )]

but it's more readable to use:

df[df["col"].between(x,y)]

how to remove outliers in dataset in python

You have to define the range of values in that paticular column. 

df_out = df_in.loc[(df_in[col_name] > fence_low) & (df_in[col_name] < fence_high)]

There is no direct code for it.