8 ML

 import pandas as pd

#task 1:

data = pd.read_csv("realestate.csv")

data.columns = data.columns.str.strip()

#task 2:

data.dropna(inplace=True)

#task 4:

filtered_data= data[(data['transactiondate'] >= 2013) & (data['distance'] <= 500)]

#task 5:

filtered_data = pd.get_dummies(filtered_data, columns=['stores'])

#task 6:

average_price_by_age = filtered_data.groupby('houseage')['unit_area'].mean()

#task 7:

lower_bound = filtered_data['unit_area'].quantile(0.05)

upper_bound = filtered_data['unit_area'].quantile(0.95)

filtered_data = filtered_data[(filtered_data['unit_area']>=lower_bound)&(filtered_data['unit_area']<=upper_bound)]

print(filtered_data.head())