I am trying to apply the function to a different column 'Year', but I seem to be missing something or my syntax is off because I keep getting a NameError thrown.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/46bdcecb-8503-44fc-bd22-3ece9d6e026e/third_df', index_col=0)
# Define function
def func(df, name):
# Create an empty list
list_df = [ ]
# Define the loop
for i in df[name]:
# Check if the length of the element is greater than 4
if len(i) > 4:
# If the condition is True append element
list_df.append(i)
result = set(list_df)
# Return the obtained list
return result
# Apply function to the column 'Year' and output the result
df['Year'].apply(list_df)