Last active
May 5, 2023 23:18
-
-
Save carleen/467fdcc30f1b8edc731dcbaf66a870e6 to your computer and use it in GitHub Desktop.
Some functions for working with variables on the Airbnb Dataset
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Change some of the variables in room type, prevents errors | |
df.room_type = df.room_type.map({'Private room': 'private_room', | |
'Entire home/apt': 'entire_property', | |
'Shared room': 'shared_room'}) | |
# Adjusts variables for host response times | |
df.host_response_time = df.host_response_time.map({'within an hour': 'lt_hour', | |
'within a few hours': 'lt_few_hours', | |
'within a day': 'lt_day', | |
'a few days or more': 'gt_day'}) | |
# These are the variables that we need to create into dummy variables | |
dummy_var_list = ['host_is_superhost', 'room_type', 'property_type', 'instant_bookable', | |
'neighborhood_label', 'bathroom_type', 'host_response_time'] | |
# Iterate through all of the "dummy variables" | |
for v in dummy_var_list: | |
df = pd.concat([df, pd.get_dummies(df[v], prefix=v)], axis=1) | |
df = df.drop(v, axis=1) | |
# Feature list, so you don't have to manually type all variables | |
feature_list = df.columns[df.columns!='price'] | |
correlations(df, 'price', feature_list) | |
model1 = f'''price ~''' | |
for f in feature_list: | |
model1+= f''' {f} +''' | |
model1 = model1.rstrip(' +') | |
result1 = models.bootstrap_linear_regression(model1, data=df) | |
models.describe_bootstrap_lr(result1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment