Mar 10, 2024

Boosting tree - Xgboost + GridSearchCV


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score, mean_squared_error
from xgboost import XGBRegressor
from sklearn.model_selection import GridSearchCV

# Install ...
!pip install xgboost

# Data load
df = pd.read_csv('./data/xxx.csv')

# Target data separation
y = df['y']
X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed
X_train, X_test, y_train, y_test = train_test_split(X,
                                                    y,
                                                    test_size = 0.3,
                                                    random_state = 42)

# Define a model structure
xgbr = XGBRegressor(random_state = 42)

# Set the range of parameters
params = {
    'max_depth' : [3, 5, 7, 9],
    'n_estimators' : [50, 70, 90, 100],
    'learning_rate' : [0.03, 0.01],
    'subsample' : [0.7, 0.8, 0.9],
    'colsample_bytree' : [0.7, 0.8, 0.9]
    # 'reg_alpha' : [0, 1],
    # 'reg_lambda' : [0, 1]
}

# Set the condition of grid search model
grid = GridSearchCV(estimator = xgbr,
                   param_grid = params,
                   scoring = 'r2',
                   n_jobs = -1, # 최대 사용
                   verbose = 2,
                   cv = 5)

# Train the grid search model
grid.fit(X_train, y_train)

# Confirm the optimal parameters
grid.best_params_

# Model prediction using those optimal parameters
best_pred = grid.predict(X_test)

# Error metric
print("r2 score:", r2_score(y_test, best_pred))
print("RMSE:", np.sqrt(mean_squared_error(y_test, best_pred)))

Mar 2, 2024

Decision tree regressor


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import r2_score, mean_squared_error

# Data load
df = pd.read_csv('./data/xxx.csv')

# Target data separation
y = df['y']
X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed
X_train, X_test, y_train, y_test = train_test_split(X,
                                                    y,
                                                    test_size = 0.3,
                                                    random_state = 42)

# Define a model structure
dtr = DecisionTreeRegressor(max_depth = 16, random_state = 42)

# Train model
dtr.fit(X_train, y_train)

# Model prediction
dtr_pred = dtr.predict(X_test)

# Error metric
print("Ridge-r2 score:", r2_score(y_test, dtr_pred))
print("Ridge-RMSE:", np.sqrt(mean_squared_error(y_test, dtr_pred)))

# Plot
plt.bar(X_train.columns, dtr.feature_importances_)
plot_tree(dtr);

Mar 1, 2024

Decision tree classifier


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

from sklearn.metrics import confusion_matrix, classification_report
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from sklearn.tree import plot_tree

# Data load
from sklearn.datasets import load_iris
iris = load_iris()

# Data separation
X = pd.DataFrame(iris['data'], columns = iris['feature_names'])
y = iris['target']

# Split train : test data set = 7:3 and set random seed
X_train, X_test, y_train, y_test = train_test_split(X,
                                                    y,
                                                    test_size = 0.3,
                                                    random_state = 42,
stratify = y)

# Define a model structure
dtc = DecisionTreeClassifier(max_depth = 3, random_state = 42)

# Train model
dtc.fit(X_train, y_train)

# Model prediction
dtc_pred = dtc.predict(X_test)

# Error metric
print(confusion_matrix(y_test, dtc_pred))
print(classification_report(y_test, dtc_pred))

# Confirm coefficient
dtc.feature_importances_

# Plot
plt.bar(X_train.columns, dtc.feature_importances_)
plt.figure(figsize=(8, 8))
plot_tree(dtc,
         feature_names = iris['feature_names'],
         class_names = iris['target_names'],
         filled = True
);