Pinned Loading

1. Clean Property Types in the Data Frame Clean Property Types in the Data Frame

   1

   def clean_property_types(propType):

   2

       # Define the cleaned types without the extra details

   3

       cleanTypes = [                     

   4

           'Condominium',

   5

           'Serviced Residence',

2. Clean the Built_Size column, remove ... Clean the Built_Size column, remove the 'sf. ft.' from the data and along with few other varients of these labels. Also, convert the string into the numeric format for calculations at a later stage

   1

   # Convert Built_Size into numeric value

   2

   def convert_built_size_numeric(bsize):

   3

       try:

   4

           if re.search(r"sq\.*\s*ft\.*", bsize) is None:

   5

               return None

3. Create the plot showing the distribu... Create the plot showing the distribution of properties by Size in Kuala Lumpur

   1

   # highly sqft per area

   2

   all_property_sqft = df.groupby('Location')['Built_Size'].mean().sort_values(ascending=False)

   3

   4

   bx = all_property_sqft.plot(kind='bar', title="Property Size Distribution in Kuala Lumpur", figsize=(15,10), legend=True, fontsize=10, rot=90)

   5

   bx.set_xlabel("Locations", fontsize=10)

4. Split the Built Up Type & Built Up A... Split the Built Up Type & Built Up Area Size into two separate columns, i.e. Built_Type & Built_Size, and show the top 5 rows of the dataframe to view the effect

   1

   # define the function to split Size into an array of two differnt values

   2

   def split_property_size(size, tp=0):

   3

       try:

   4

           return size.split(":")[tp].strip()

   5

       except AttributeError:

5. Plot the Sq per Price for Kuala Lump... Plot the Sq per Price for Kuala Lumpur price

   1

   #  create price per sqft

   2

   df['Price_sqft'] = df['Price'] / df['Built_Size']

   3

   4

   # most expensive area by price per sqft

   5

   dfc = df.copy(deep=True)

6. Imputation of missing values with knn. Imputation of missing values with knn.

   1

   import numpy as np

   2

   import pandas as pd

   3

   from collections import defaultdict

   4

   from scipy.stats import hmean

   5

   from scipy.spatial.distance import cdist