Python for Finance Cookbook

How to do it...

Execute the following steps to detect outliers using the 3σ approach, and mark them on a plot.

1. Calculate the rolling mean and standard deviation:

df_rolling = df[['simple_rtn']].rolling(window=21) \                               .agg(['mean', 'std'])df_rolling.columns = df_rolling.columns.droplevel()

2. Join the rolling metrics to the original data:

df_outliers = df.join(df_rolling)

3. Define a function for detecting outliers:

def indentify_outliers(row, n_sigmas=3):    x = row['simple_rtn']    mu = row['mean']    sigma = row['std']        if (x > mu + 3 * sigma) | (x < mu - 3 * sigma):        return 1    else:        return 0

4. Identify the outliers and extract their values for later use:

df_outliers['outlier'] = df_outliers.apply(indentify_outliers,                                                axis=1)                                                                                                       outliers = df_outliers.loc[df_outliers['outlier'] ...