combine_dataframes.py

import pandas as pd
from pathlib import Path

def get_ytid(x):
    name = Path(x).name
    ytid = name[: name.rfind('_')]
    return ytid

maybe_noise = pd.read_csv('Engine+noises_2020-08-24T19_34_31.csv')
maybe_healthy = pd.read_csv('Engine+healthy_2_2020-08-24T22_17_40.csv')
noise = maybe_noise[maybe_noise.sound == 'is_sound'].copy()
healthy = maybe_healthy[maybe_healthy.sound == 'is_sound'].copy()

noise['target'] = 1
healthy['target'] = 0

df = pd.concat([noise, healthy])
df['ytid'] = df.sample_uri.apply(get_ytid)
df.to_csv('noise_and_healthy.csv', index=False)