mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-12-05 02:40:16 +00:00
3f8b2af14b
* Add autoclave cipher * Update autoclave with the given suggestions * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixing errors * Another fixes * Update and rename autoclave.py to autokey.py * Rename gaussian_naive_bayes.py to gaussian_naive_bayes.py.broken.txt * Rename gradient_boosting_regressor.py to gradient_boosting_regressor.py.broken.txt * Rename random_forest_classifier.py to random_forest_classifier.py.broken.txt * Rename random_forest_regressor.py to random_forest_regressor.py.broken.txt * Rename equal_loudness_filter.py to equal_loudness_filter.py.broken.txt Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Christian Clauss <cclauss@me.com>
67 lines
2.3 KiB
Plaintext
67 lines
2.3 KiB
Plaintext
"""Implementation of GradientBoostingRegressor in sklearn using the
|
|
boston dataset which is very popular for regression problem to
|
|
predict house price.
|
|
"""
|
|
|
|
import matplotlib.pyplot as plt
|
|
import pandas as pd
|
|
from sklearn.datasets import load_boston
|
|
from sklearn.ensemble import GradientBoostingRegressor
|
|
from sklearn.metrics import mean_squared_error, r2_score
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
|
|
def main():
|
|
|
|
# loading the dataset from the sklearn
|
|
df = load_boston()
|
|
print(df.keys())
|
|
# now let construct a data frame
|
|
df_boston = pd.DataFrame(df.data, columns=df.feature_names)
|
|
# let add the target to the dataframe
|
|
df_boston["Price"] = df.target
|
|
# print the first five rows using the head function
|
|
print(df_boston.head())
|
|
# Summary statistics
|
|
print(df_boston.describe().T)
|
|
# Feature selection
|
|
|
|
x = df_boston.iloc[:, :-1]
|
|
y = df_boston.iloc[:, -1] # target variable
|
|
# split the data with 75% train and 25% test sets.
|
|
x_train, x_test, y_train, y_test = train_test_split(
|
|
x, y, random_state=0, test_size=0.25
|
|
)
|
|
|
|
model = GradientBoostingRegressor(
|
|
n_estimators=500, max_depth=5, min_samples_split=4, learning_rate=0.01
|
|
)
|
|
# training the model
|
|
model.fit(x_train, y_train)
|
|
# to see how good the model fit the data
|
|
training_score = model.score(x_train, y_train).round(3)
|
|
test_score = model.score(x_test, y_test).round(3)
|
|
print("Training score of GradientBoosting is :", training_score)
|
|
print("The test score of GradientBoosting is :", test_score)
|
|
# Let us evaluation the model by finding the errors
|
|
y_pred = model.predict(x_test)
|
|
|
|
# The mean squared error
|
|
print(f"Mean squared error: {mean_squared_error(y_test, y_pred):.2f}")
|
|
# Explained variance score: 1 is perfect prediction
|
|
print(f"Test Variance score: {r2_score(y_test, y_pred):.2f}")
|
|
|
|
# So let's run the model against the test data
|
|
fig, ax = plt.subplots()
|
|
ax.scatter(y_test, y_pred, edgecolors=(0, 0, 0))
|
|
ax.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], "k--", lw=4)
|
|
ax.set_xlabel("Actual")
|
|
ax.set_ylabel("Predicted")
|
|
ax.set_title("Truth vs Predicted")
|
|
# this show function will display the plotting
|
|
plt.show()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|