adding noise to a signal in python

Question

I want to add some random noise to some 100 bin signal that I am simulating in Python - to make it more realistic.

On a basic level, my first thought was to go bin b

Answer 1

Awesome answers above. I recently had a need to generate simulated data and this is what I landed up using. Sharing in-case helpful to others as well,

import logging
__name__ = "DataSimulator"
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

import numpy as np
import pandas as pd

def generate_simulated_data(add_anomalies:bool=True, random_state:int=42):
    rnd_state = np.random.RandomState(random_state)
    time = np.linspace(0, 200, num=2000)
    pure = 20*np.sin(time/(2*np.pi))

    # concatenate on the second axis; this will allow us to mix different data 
    # distribution
    data = np.c_[pure]
    mu = np.mean(data)
    sd = np.std(data)
    logger.info(f"Data shape : {data.shape}. mu: {mu} with sd: {sd}")
    data_df = pd.DataFrame(data, columns=['Value'])
    data_df['Index'] = data_df.index.values

    # Adding gaussian jitter
    jitter = 0.3*rnd_state.normal(mu, sd, size=data_df.shape[0])
    data_df['with_jitter'] = data_df['Value'] + jitter

    index_further_away = None
    if add_anomalies:
        # As per the 68-95-99.7 rule(also known as the empirical rule) mu+-2*sd 
        # covers 95.4% of the dataset.
        # Since, anomalies are considered to be rare and typically within the 
        # 5-10% of the data; this filtering
        # technique might work 
        #for us(https://en.wikipedia.org/wiki/68%E2%80%9395%E2%80%9399.7_rule)
        indexes_furhter_away = np.where(np.abs(data_df['with_jitter']) > (mu + 
         2*sd))[0]
        logger.info(f"Number of points further away : 
        {len(indexes_furhter_away)}. Indexes: {indexes_furhter_away}")
        # Generate a point uniformly and embed it into the dataset
        random = rnd_state.uniform(0, 5, 1)
        data_df.loc[indexes_furhter_away, 'with_jitter'] +=  
        random*data_df.loc[indexes_furhter_away, 'with_jitter']
    return data_df, indexes_furhter_away