Created
January 22, 2022 18:59
-
-
Save francoisstamant/ad3a8ee03a8cf39e3b237decf659222d to your computer and use it in GitHub Desktop.
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
import pandas as pd | |
import numpy as np | |
from sklearn.model_selection import train_test_split | |
df = pd.read_csv('house_prices.csv', sep=';') | |
#One hot encoding | |
neighborhoods = pd.get_dummies(df.Neighborhood, prefix='In_') | |
houses = pd.concat([df,neighborhoods], axis=1) | |
houses = houses.drop(['Neighborhood','House_Id'], axis=1) | |
data_to_use = houses.head(196) | |
potential_houses = houses.tail(4) | |
#Train-test split of the data | |
x = data_to_use.loc[:, data_to_use.columns != 'Price'] | |
y = data_to_use['Price'] | |
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=123) | |
### Build models | |
#I build 3 simple models, i.e. a linear regression, a random forest and gradient boosting regressor | |
# ----------------------- Linear Regression -------------------------------------- | |
from statsmodels.api import OLS | |
reg = OLS(y_train, X_train).fit() | |
# Use the forest's predict method on the test data | |
predictions = reg.predict(X_test) | |
# Calculate the absolute errors | |
errors = abs(predictions - y_test) | |
# Print out the mean absolute error (mae) | |
print('Mean Absolute Error of Regression:', round(np.mean(errors), 2), '$.') | |
# --------------------- Random forest ------------------------------------------------------ | |
from sklearn.ensemble import RandomForestRegressor | |
regr = RandomForestRegressor(max_depth=5, random_state=1234) | |
regr.fit(X_train, y_train) | |
# Use the forest's predict method on the test data | |
predictions = regr.predict(X_test) | |
# Calculate the absolute errors | |
errors = abs(predictions - y_test) | |
# Print out the mean absolute error (mae) | |
print('Mean Absolute Error of Random Forest:', round(np.mean(errors), 2), '$.') | |
# --------------------- Gradient Boosting ------------------------------------------------------ | |
from sklearn.ensemble import GradientBoostingRegressor | |
reg2 = GradientBoostingRegressor() | |
reg2.fit(X_train, y_train) | |
# Use the forest's predict method on the test data | |
predictions = reg2.predict(X_test) | |
# Calculate the absolute errors | |
errors = abs(predictions - y_test) | |
# Print out the mean absolute error (mae) | |
print('Mean Absolute Error of XGBoost:', round(np.mean(errors), 2), '$.') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment