#------------------------------------------------------------------------------
# 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
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)]
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)]df = pd.DataFrame(np.random.randn(100, 3))
from scipy import stats
df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]
df = pd.DataFrame(np.random.randn(100, 3))
from scipy import stats
df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]